Bisect PyTorch commits to find the regression that breaks TorchTitan. Use when the user wants to bisect PyTorch or invokes /torch_bisect.

Comprehensive guide for implementing robust testing strategies in JavaScript/TypeScript applications using modern testing frameworks and best practices.

DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.

Structured persona creation and JTBD analysis methodology - persona templates, ODI job step tables, pain point mapping, success metric quantification, and multi-persona segmentation

Automate Datadog tasks via Rube MCP (Composio): query metrics, search logs, manage monitors/dashboards, create events and downtimes. Always search tools first for current schemas.

This skill covers packaging Makepad applications for all supported platforms.

Google C++ Style Guide rules for writing clean, maintainable C++ code. Use when writing C++, reviewing code, discussing naming conventions, formatting, class design, or any C++ best practices. Covers headers, scoping, classes, functions, naming, comments, and formatting.

Modern .NET execution model with process isolation

Chart selection and data visualization guidance for effective data communication. Use when: creating visualizations, choosing chart types, designing dashboards, or when user mentions data visualization, charts, graphs, or needs help presenting data visually.

Manages local data persistence using SQLite or other database solutions. Use when a Flutter app needs to store, query, or synchronize large amounts of structured data on the device.

Generate a codebase health snapshot for technical debt tracking and planning. Analyzes git history, code complexity, debt markers, and dependencies to identify hotspots and refactoring priorities.

Triage operational inputs (email, calendar, tasks) into prioritized action queues with explicit ownership and deadlines.

Search and recommend Claude Code skills from trusted marketplaces

Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns.

I do it

블로거 페르소나: 블로그 전문 작성자 역í•

Create FastAPI routers following established patterns with proper authentication, response models, and HTTP status codes.

NixOS generation-aware debugging and time-travel. Correlate system state changes with application failures. Query "what changed and when."

Use the open-source free `ReportGenerator` tool for turning .NET coverage outputs into HTML, Markdown, Cobertura, badges, and merged reports. Use when raw coverage files are not readable enough for CI or human review.

Build background agents in sandboxed environments. Use for hosted coding agents, sandboxed VMs, Modal sandboxes, and remote coding environments.

> **Purpose:** Easy undo/rollback without knowing git > **Version:** 1.0.0 > **Author:** Toh Framework Team

Formats Claude Code files with markdownlint, prettier, and shellcheck. Use when user asks to "format my files", "fix markdown formatting", "clean up CLAUDE.md", or "check shell scripts". Auto-fixes markdown, JSON, YAML formatting and analyzes shell script quality.

使用 `copaw cron` 命令管理定时任务。

You are running an automated improvement loop for `skills/vibes/SKILL.md`. Each iteration generates apps via sonnet subagents, tests them for per-user state isolation, and uses failures to improve the documentation.

Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API

> **Purpose:** Visual progress tracking for users > **Version:** 1.0.0 > **Author:** Toh Framework Team

Validates Claude Code hooks.json files for schema, events, and commands. Use when user asks to "check my hooks", "validate hooks.json", "hook errors", "why isn't my hook firing", or "hook event types". Validates hook events, types (command, prompt, agent), matcher patterns, and command script references.

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

Design de produto nivel Apple — sistemas visuais, UX flows, acessibilidade, linguagem visual proprietaria, design tokens, prototipagem e handoff. Cobre Figma, design systems, tipografia, cor, espacamento, motion design e principios de design cognitivo.

Generate quality validation checklist from spec, plan, and tasks. Use after creating tasks. Triggers on: create checklist, quality checklist, validation checklist.

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

Naver: 글 목록 조회 및 개별 글 읽기

PC and console game development principles. Engine selection, platform features, optimization strategies.

Draft a new release. Bumps version, generates CHANGELOG.md from git history, and creates a PR.

Capture idea or task as todo from current conversation context

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

Configure voicemail, voice channels, and emergency (E911) services for your phone numbers. This skill provides Java SDK examples.

Standardize coding handoffs between builder, QA, and deploy agents. Use when a coding task moves across stages and requires strict ACK/DONE/BLOCKED status updates, branch metadata, and PR readiness checks.

You are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents, and implementing comprehensive observability solutions.

Help users define their North Star metric. Use when someone is choosing their primary success metric, trying to align the team around a key measure, struggling with metric proliferation, or setting up their measurement strategy.

Lab environment for Claude superpowers

Expert guide for configuring Odoo Accounting: chart of accounts, journals, fiscal positions, taxes, payment terms, and bank reconciliation.

description: Generate and track comprehensive due diligence checklists tailored to the target company's sector, deal type, and complexity. Covers all major workstreams with request lists, status tracking, and red flag escalation. Use when kicking off diligence, organizing a data room review, or trac

Monitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema.

Quick reference for TaskEither. Use when user needs async error handling, API calls, or Promise-based operations that can fail.

Kiln multi-modal software creation pipeline. Orchestrates 7 autonomous steps from project onboarding through brainstorm, research, architecture, iterative build, validation, and final report. Use when the user invokes /kiln-fire.

Investigate datasets from HuggingFace, CSV, or JSON files to understand their structure, fields, and data quality. Trigger whenever you need to explore or inspect a dataset yourself without using pre-written scripts.

Validates MCP server configuration files (.mcp.json). Use when user asks to "check my .mcp.json", "why isn't my MCP working", ".mcp.json errors", "validate MCP servers", or "MCP connection failed". Validates transport types (stdio, sse, http, websocket), server names, and environment variables.

Tạo các sổ tay Jupyter sạch sẽ, có khả năng tái tạo cho hai chế độ chính:

Expert in applying AI to education - AI tutors, personalized learning paths, content generation, automated assessments, and adaptive learning systems. Covers practical implementation of AI to enhance (not replace) human instruction. Use when "ai tutor, ai for learning, personalized learning, adaptive learning, ai assessment, generate course content, ai education, " mentioned.

Publish content to Nosi and get a shareable URL. Use when the user wants to publish text, markdown, or files to nosi.pub for sharing.

Post code review comments to GitHub PR

Guides performance optimization for MSBuild engine code. Consult when working on hot paths in evaluation or execution, reducing allocations, choosing collection types, handling strings efficiently, modifying Expander.cs or Evaluator.cs, using Span<T>/stackalloc, caching values, or profiling build performance. Also applies when reviewing PRs for performance regression.

Create a new custom slash command following conventions and best practices

Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.

Automate Figma tasks via Rube MCP (Composio): files, components, design tokens, comments, exports. Always search tools first for current schemas.

How the Zig S-expression engine and typed KiCad models work, how they are exposed to Python (pyzig_sexp), and the invariants around parsing, formatting, and freeing. Use when working with KiCad file parsing, S-expression generation, or layout sync.

Review all evaluations in the repository against a single code quality standard. Checks ALL evals against ONE standard for periodic quality reviews. Use when user asks to review/audit/check all evaluations for a specific topic or standard. Do NOT use for reviewing a single eval (use eval-quality-workflow instead) or for test coverage (use ensure-test-coverage instead).

Specializes in chapter openings (hooks) and chapter endings (pulls). Every chapter must start with a reason to keep reading and end with a reason to turn the page. Runs after prose-craft, before chaos-engine. The skill that prevents the reader from putting the book down.

Control Spotify playback using the `spogo` CLI. Play, pause, skip, search tracks/albums/playlists, manage the queue, and browse your library.

SEO and AEO best practices for metadata, Open Graph, sitemaps, robots.txt, hreflang, JSON-LD structured data, EEAT, and content optimized for search engines and AI answer surfaces. Use this skill when implementing page SEO, technical SEO, schema markup, international SEO, AI-overview readiness, or improving content for Google, ChatGPT, Perplexity, and similar assistants.

Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.

Provide a comprehensive command reference for penetration testing tools including network scanning, exploitation, password cracking, and web application testing. Enable quick command lookup during security assessments.

Qualify leads against ICP with transparent scoring and clear next steps. Use when converting raw prospects into prioritized outreach queues.

Generate a complete, idiomatic Foldkit program from a natural language description. Use when the user wants to create a new Foldkit program, scaffold a project, or says things like "build me a..." or "I want a program that..."

Use when planning or building a SaaS MVP from scratch. Provides a structured roadmap covering tech stack, architecture, auth, payments, and launch checklist.

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

3D game development principles. Rendering, shaders, physics, cameras.

Performs a systematic, multi-category audit of the ELPS codebase. Modeled on the approach used in PR #74 (25-commit multi-category audit).

Analyze any topic, domain, or paper and generate a beautiful HTML report using **Actionbook Browser** — featuring SPA-aware navigation, network idle detection, batch operations, and intelligent page analysis.

Correlate content attributes with GA4 and GSC metrics to identify performance drivers

Expert guidance for Spring Boot application development with best practices for RESTful APIs, testing, security, and deployment

**Status:** Done **Date:** 2026-01-30

You are a master narrative architect. You design the deep structure of books — characters, themes, emotional arcs, and chapter blueprints. You are the bridge between a raw idea and a writer who can execute it. You build the skeleton; the Writer adds flesh.

Write text that avoids all known AI writing patterns and passes human detection. Use when writing articles, essays, blog posts, social media copy, or any content that must read as authentically human. Triggers on requests to write naturally, avoid AI slop, avoid AI detection, humanize writing, write like a human, or make text sound authentic.

Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K, 10-Q), proxy statements (DEF 14A), 8-K current events, company screening by ticker/CIK/industry, multi-period financial analysis, or any SEC regulatory filings.

Generate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product Hunt, social media, landing pages, or documentation.

Automated quality enforcement loop. Evaluates chapters against configurable thresholds, synthesizes actionable feedback, dispatches targeted revisions, re-evaluates, and tracks improvement across iterations. Eliminates manual babysitting between evaluate-fix-reevaluate cycles. The central self-correction mechanism of the entire pipeline.

Creates execution plan (PLAN.md) from SPEC or Plan Mode file.

Review content against your brand voice, style guide, and messaging pillars, flagging deviations by severity with specific before/after fixes. Use when checking a draft before it ships, when auditing copy for voice consistency and terminology, or when screening for unsubstantiated claims, missing disclaimers, and other legal flags.

Validates Claude Code settings.json files for schema, permissions, and security. Use when user asks to "check my settings", "validate settings.json", "permission errors", "environment variable issues", or "settings syntax errors". Validates model names, permission rules, hooks configuration, and environment variables.

Builds 3-5 reader personas representing the book's target audience segments. Each persona has reading habits, emotional triggers, deal-breakers, discovery channels, and comp title preferences. Used by writer (voice calibration), evaluator (4-reader simulation), and packager (marketing targeting).

Prose writer for the Book Genesis pipeline. Writes one chapter at a time with voice inhabitation (not imitation), emotional anchors, character chaos, expanded 20-pattern anti-AI protocol, and the impulse instruction. Follows the blueprint but deviates when the text demands it.

Calculate PI/PID controller gains using Internal Model Control (IMC) tuning rules for first-order systems.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Agente que simula Bill Gates — cofundador da Microsoft, arquiteto da industria de software comercial, estrategista tecnologico global, investidor sistemico e filantropo baseado em dados.

Automate Box operations including file upload/download, content search, folder management, collaboration, metadata queries, and sign requests through Composio's Box toolkit.

This skill audits a bare React Native project and produces a structured `MIGRATION_AUDIT.md` report. It does NOT rewrite code — it identifies what needs to change, classifies severity, and gives the developer a clear, prioritized plan.

Enforces the project's core TypeScript standards including explicit typing, import organization, class member ordering, and code safety rules. ALWAYS apply when creating, modifying, or reviewing any TypeScript (.ts/.tsx) file.

Azure Tables SDK for Python (Storage and Cosmos DB). Use for NoSQL key-value storage, entity CRUD, and batch operations.

> Comprehensive AI-powered code review for PRs and local changes — enterprise-grade alternative to CodeRabbit

> moai-product | UX/사용자 연구 전문 스킬

Azure Monitor Query SDK for Python. Use for querying Log Analytics workspaces and Azure Monitor metrics.

Create, search, and manage Bear notes via grizzly CLI.

Build a growth strategy with frameworks, metrics, and experimentation. Use when the user says "growth strategy", "growth plan", "AARRR", "growth loops", "North Star Metric", "growth model", "activation rate", "retention strategy", "churn reduction", "growth experiments", or asks about overall growth frameworks and metrics for their product.

This skill should be used when enhancing the visual design and aesthetics of Next.js web applications. It provides modern UI components, design patterns, color palettes, animations, and layout templates. Use this skill for tasks like improving styling, creating responsive designs, implementing modern UI patterns, adding animations, selecting color schemes, or building aesthetically pleasing frontend interfaces.

当用户要求“让 agent 自己想策略并写代码”时，使用这个技能。

Azure Key Vault Keys SDK for Rust. Use for creating, managing, and using cryptographic keys. Triggers: "keyvault keys rust", "KeyClient rust", "create key rust", "encrypt rust", "sign rust".

Rust systems programming patterns including ownership, traits, async runtime, error handling, and unsafe guidelines

You are an architect of worlds that persist across multiple volumes. Your role is not to write — it is to build the STRUCTURE that prevents contradictions, preserves momentum between volumes, and ensures each book is satisfying on its own and irresistible as part of a whole. Series that fail usual

Kill all agent sessions for a feature/research ID and close Warp tab

Generate custom tool boilerplate with @tool decorator for Claude Agent SDK. Use when adding new tools to custom agents.

Guide for working with and updating insta snapshot tests in Oxc without terminal interaction.

This skill helps you implement Figma designs 1:1 using the OneKey component library.

Portfolio risk analysis including Value at Risk (parametric, historical, Monte Carlo), Conditional VaR, stress testing, drawdown analysis, and factor exposure assessment.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

JavaScript and TypeScript development with ES6+, Node.js, React, and modern web frameworks. Use for frontend, backend, or full-stack JavaScript/TypeScript projects.

Guide for adding new wsh commands to Wave Terminal. Use when implementing new CLI commands, adding command-line functionality, or extending the wsh command interface.

Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or agent; brief a colleague taking over; prepare a shift change summary; or onboard someone mid-task. Produces ready-to-use handoff documents covering current status, next steps, known issues, technical context, and communication templates for both planned and unplanned transfers.

Expert-level Home Assistant configuration management with efficient deployment workflows (git and rapid scp iteration), remote CLI access via SSH and hass-cli, automation verification protocols, log analysis, reload vs restart optimization, and comprehensive Lovelace dashboard management for tablet-optimized UIs. Includes template patterns, card types, debugging strategies, and real-world examples.

Remotely control a target host via GLKVM HTTP API, supporting keyboard/mouse input, screenshot capture, OCR recognition, Fingerbot physical button control, and ATX power management. Access via HTTPS with certificate errors ignored.

Open Source Intelligence (OSINT) gathering is the first active phase of a red team engagement, where operators collect publicly available information about the target organization to identify attack s

Send text and markdown messages to `WeCom` (`企业微信`) via incoming webhooks (ENV: `WECOM_WEBHOOK_URL`).

Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.

Manage kind (Kubernetes IN Docker) local clusters. Use when creating, testing, or developing with local Kubernetes clusters in Docker containers.

Azure Cosmos DB SDK for Java. NoSQL database operations with global distribution, multi-model support, and reactive patterns.

API documentation workflow for generating OpenAPI specs, creating developer guides, and maintaining comprehensive API documentation.

Naver: 블로그 글 발행 — 5종 포맷 템플릿 (story/howto/list/review/qa)

Draft a knowledge base article from a resolved issue or common question. Use when a ticket resolution is worth documenting for self-service, the same question keeps coming up, a workaround needs to be published, or a known issue should be communicated to customers.

Use the free official .NET diagnostics CLI tools for profiling and runtime investigation in .NET repositories. Use when a repo needs CPU tracing, live counters, GC and allocation investigation, exception or contention tracing, heap snapshots, or startup diagnostics without GUI-only tooling.

Ticket management best practices for Linear or equivalent project tracker. Use when creating issues, updating ticket status, attaching evidence, parsing acceptance criteria, or working with ticket UUIDs. Provides evidence templates for dev/staging/done phases.

You are the project's persistent memory system. Without you, every session starts from zero. With you, 50 sessions build a coherent book. You don't write — you TRACK. Every decision, every change, every score, every pending handoff.

Show Kanban board or list view

Use when user mentions fantasy, magic system, or world-building for fantastical settings - provides fantasy genre conventions, magic system design patterns, and world-building frameworks

Query JASPAR for transcription factor binding site (TFBS) profiles (PWMs/PFMs). Search by TF name, species, or class; scan DNA sequences for TF binding sites; compare matrices; essential for regulatory genomics, motif analysis, and GWAS regulatory variant interpretation.

Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies, NetworkPolicies, storage configuration, performance optimization, GitOps pipelines, and multi-cluster management.

You are a voice architect. You take the narrative blueprint (foundation.md, outline.md) and produce a formal Voice DNA document so precise that a writer agent can pass the cover-the-name test on first draft. You do not write prose. You define how prose sounds.

Start feature autonomous execution with explicit stop-after

Read flagged emails from Maildir (mblaze) and draft replies via n8n-hooks.

Diagnoses pipeline weakness and identifies the highest-leverage fix in founder-led sales. Use when demos are happening but closes are weak. Produces pipeline-review.md.

Transit Least Squares (TLS) algorithm for detecting exoplanet transits in light curves. Use when searching for transiting exoplanets specifically, as TLS is more sensitive than Lomb-Scargle for transit-shaped signals. Based on the transitleastsquares Python package.

Use when updating major Node.js versions across ng-mocks projects, including CI/CD, .nvmrc, Docker images, npm compatibility, @types/node, and wrapper-based validation.

Cleanup feature <ID> [--push] - remove all worktrees and branches

Defines the one metric that best captures delivered value and future company health. Use when the founder is tracking too many metrics or lacks one leading signal. Produces north-star.md.

Discover novel miRNAs and quantify known miRNAs using miRDeep2 de novo prediction from small RNA-seq data. Use when identifying new miRNAs or performing comprehensive miRNA profiling with discovery.

Ordo JIT compilation and performance optimization guide. Includes Schema-aware JIT, TypedContext derive macro, Cranelift compilation, performance tuning. Use for optimizing rule execution performance, reducing latency, increasing throughput.

Continuous self-improvement through structured reflection and memory

Close feature <ID> [agent] [--adopt] - merges branch, cleans up, optionally adopts from losers

Plan and build comprehensive Playwright E2E test suites with Page Object Model, authentication state persistence, custom fixtures, visual regression, and CI integration. Uses interview-driven planning to clarify critical user flows, auth strategy, test data approach, and parallelization before writing any tests.

将讲稿转换为乔布斯风极简科技感竖屏HTML演示稿。

Strategic test data generation, management, and privacy compliance. Use when creating test data, handling PII, ensuring GDPR/CCPA compliance, or scaling data generation for realistic testing scenarios.

Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket.

The knowledge graph is your persistent, structured memory of the user's world — entities, relationships, communities, and how they all connect. It is built from the user's documents and persists across sessions.

Interactively create a new User Story work item as a child of an existing Feature in Azure DevOps.

Orchestrate complex multi-step workflows using babysitter SDK

High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.

Review feature <ID> - code review with fixes by a different agent

Run AEO audits, fix site issues, validate schema, generate llms.txt, and compare sites.

Create feature <name> - creates spec in inbox

Do feature <ID> - works in both Drive and Fleet modes

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

The Block Collection and Block Party are repositories for existing AEM blocks, build tools, code snippets, integration patterns, plugins, and more. Use this skill anytime you are developing something and want to find a reference to use as a starting point.

Comprehensive, data-backed email marketing consultant for audits, win-back/re-engagement flows, copy, deliverability, compliance, and campaign/platform strategy.

Implementing multi-layer security scanning (container, SAST, DAST, SCA, secrets), SBOM generation, and risk-based vulnerability prioritization in CI/CD pipelines. Use when building DevSecOps workflows, ensuring compliance, or establishing security gates for container deployments.

Guidelines for interacting with the Medusa API in Litekart Admin.

Orchestration pattern for large-scale processing where work is distributed, processed independently, then combined. Map phase splits and processes, Reduce phase aggregates results. Use for codebase-wide analysis, bulk transformations, or any task where "do X to everything, then summarize."

Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.

Search, manage, and organize your contact network via the Clay CLI.

Search, view, update, and merge contacts in the local CRM

Generates Spring Boot 3.x configurations, creates REST controllers, implements Spring Security 6 authentication flows, sets up Spring Data JPA repositories, and configures reactive WebFlux endpoints. Use when building Spring Boot 3.x applications, microservices, or reactive Java applications; invoke for Spring Data JPA, Spring Security 6, WebFlux, Spring Cloud integration, Java REST API design, or Microservices Java architecture.

Runs multi-pass automated code review with per-issue fix subagents. Triggers when preparing a branch for PR, reviewing code changes, or when thorough automated code quality review is needed.

Writing clear, discoverable software documentation following the Eight Rules and Diataxis framework. Use when creating README files, API docs, tutorials, how-to guides, or any project documentation. Automatically enforces docs/ location, linking requirements, and runnable examples.

Comprehensive guide for Firestore Standard Edition, including provisioning, security rules, and SDK usage. Use this skill when the user needs help setting up Firestore, writing security rules, or using the Firestore SDK in their application.

SIWA (Sign-In With Agent) authentication for ERC-8004 registered agents.

This skill has proper frontmatter but absolutely no body content. No instructions, no steps, no examples, nothing after the frontmatter.

Create high-quality Pull Requests with conventional commits and proper descriptions. Trigger: When creating PRs, writing PR descriptions, or using gh CLI for pull requests.

actrun は MoonBit で構築されたローカル GitHub Actions ランナー。GitHub Actions ワークフローをローカルで実行・デバッグする。

Evaluate feature <ID> - code review or comparison

Tests APIs for mass assignment (auto-binding) vulnerabilities where clients can modify object properties they should not have access to by including additional parameters in API requests. The tester identifies writable endpoints, adds undocumented fields to request bodies (role, isAdmin, price, balance), and checks if the server binds these to the data model without filtering. Part of OWASP API3:2023 Broken Object Property Level Authorization. Activates for requests involving mass assignment testing, parameter binding abuse, auto-binding vulnerability, or API over-posting.

Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.

Guide for Splitrail's terminal UI and file watching. Use when modifying the TUI, stats display, or real-time update logic.

Generate or update the 5 core project knowledge documents (overview, architecture, domain, source-base, standards) in ./documents/. Performs autonomous codebase scanning, gap analysis, and produces enterprise-grade documentation for rapid onboarding. Use when user says 'generate docs', 'update docs', 'create project documentation', 'docs-core', '/docs-core', 'onboarding docs', or wants to create/refresh the knowledge base.

Step-by-step workflow for adding a new reusable component to pulse-ui. Use when creating a shared component in pulse-ui/src/components/ (not a full screen/page).

Headless UI for virtualizing scrollable elements in Vue. ALWAYS use when writing code importing "@tanstack/vue-virtual". Consult for debugging, best practices, or modifying @tanstack/vue-virtual, tanstack/vue-virtual, tanstack vue-virtual, tanstack vue virtual, virtual.

When a session contains a significant failure, misunderstanding, or repeated mistake, analyse the root cause and draft a new skill that would have prevented it. The skill library should grow from real failures, not hypothetical improvements. Every painful debugging session is a skill waiting to be written.

Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content policy enforcement, and the Guardrails AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts, stripping PII, enforcing topic boundaries) and model outputs (detecting hallucinations, filtering toxic content, validating JSON schema compliance). Activates for requests involving LLM output validation, AI content filtering, guardrail implementation, or LLM safety enforcement.

Assess UK Government AI Playbook compliance for responsible AI deployment

Complete plugin development workflow: build, test, icon, troubleshoot, and setup. Use when the user wants to build a plugin, create a plugin, troubleshoot issues, add icons, or install/configure plugins. Triggers on: build plugin, create plugin, develop plugin, new plugin, plugin icon, troubleshoot, debug, setup plugin, install plugin.

Recover deleted files from disk images and storage media using PhotoRec's file signature-based carving engine regardless of file system damage.

自动从多种来源获取内容，上传到 NotebookLM，并根据自然语言指令生成播客、PPT、思维导图等多种格式。

Generate developer handoff specs from a design. Use when a design is ready for engineering and needs a spec sheet covering layout, design tokens, component props, interaction states, responsive breakpoints, edge cases, and animation details.

Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.

Comprehensive PM resume review and tailoring against 10 best practices including XYZ+S formula, keyword optimization, job-specific tailoring, and structure. Use when reviewing a PM resume, preparing for job applications, or improving resume impact.

Fast-track feature <name> - create + setup + implement in one step

Create effective content models for your blocks that are easy for authors to work with. Use this skill anytime you are building new blocks, making changes to existing blocks that modify the initial structure authors work with.

Configure ReinforceNow training runs with config.yml and train.jsonl. Also covers converting HuggingFace datasets to ReinforceNow format. Triggers on "config.yml", "train.jsonl", "training config", "batch_size", "group_size", "max_turns", "qlora", "HuggingFace", "dataset", "convert dataset".

Catch mistakes before they waste GPU hours. Verify configs, code, and math against documented framework behavior.

Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change"

Classify a GitHub issue into a problem class (chore, bug, or feature) for ADW routing. Use to determine which planning template to apply.

Use when configuring CDN for media delivery, implementing cache invalidation, or designing signed URL patterns. Covers CDN configuration, edge caching, origin shielding, and secure media access for headless CMS.

Format train.jsonl training data for ReinforceNow. Use when creating train.jsonl, formatting training entries, using tools/rewards per entry, or setting up sandbox/docker. Triggers on "train.jsonl", "training data", "docker", "sandbox", "entry format".

Multi-agent orchestration for GitHub Issues using BEADS task tracking

Open feature worktree in terminal and start agent

Centralized 'Truth Engine' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding.

Prioritise feature <name> - assigns ID, moves to backlog

Design closed-loop prompts with Request-Validate-Resolve structure for reliable agentic workflows. Use when creating self-validating agents, adding feedback loops, or improving agent reliability through verification.

> **⚠️ IMPORTANT**: Before using any F8Framework features, you **MUST** formally initialize the framework. Ensure `ModuleCenter.Initialize(this);` and all required modules (e.g. `FF8.Message = ModuleCenter.CreateModule<MessageManager>();`) are instantiated in the launch sequence (e.g. `GameLaunc

Generates high-quality, non-generic UI designs with a focus on performance, progressive disclosure, and distinctive aesthetics.

Collaborative documentation and test code writing workflow using zen mcp's clink to launch gemini CLI session in WSL (via 'gemini' command) where all writing operations are executed. Use this skill when the user requests "use gemini to write test files", "use gemini to write documentation", "generate related test files", "generate an explanatory document", or similar document/test writing tasks. The gemini CLI session acts as the specialist writer, working with the main Claude model for context gathering, outline approval, and final review. For test code, codex CLI (also launched via clink) validates quality after gemini completes writing.

Before declaring work complete, checks for loose ends: unused imports, TODO comments created, missing tests, stale references, incomplete error handling. Activates after implementing features or fixes. The cleanup that always gets skipped.

Review feature <ID> - code review with fixes by a different agent

Interactively create a new Feature work item in Azure DevOps using configured conventions.

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Authentication and authorization expert specializing in JWT, OAuth 2.0, session management, RBAC, password security. Use for auth implementation, token management, or security issues.

Check the review just done on the current feature worktree and decide accept/challenge/modify

Start feature <ID> [agents...] - create workspace and begin implementation

Generate AI videos and images via LibTV Gateway. Supports text-to-video, image-to-video, video continuation, style transfer, short drama generation, and more.

Ordo visual editor component development guide. Includes Vue/React component usage, flow diagram integration, WASM calls, rule import/export. Use for frontend integration of rule editor, custom editor UI, extending editor functionality.

SNS 마케터 페르소나: 블로그와 인스타 연계 마케팅 전략

Hand a stuck or paywalled in-progress feature from its current agent to a different agent, **without** losing commits or in-flight work. Intended for: - An agent hitting a usage/token limit mid-implementation (Codex paywall, Claude 5h limit). - An agent stalling on a prompt, auth flow, or tool confu

Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating performance optimization across the stack.

Azure Event Hubs SDK for Rust. Use for sending and receiving events, streaming data ingestion.

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.

Financial enablement & accounting platform for Bots, Agents, and OpenClaw. Multiple methods for enabling and managing agentic spending and purchases, with consolidated accounts and guardrails on transactions across wallets.

SQLAlchemy ORM patterns for Python database access. Use when defining models, writing queries, implementing upserts, working with JSON columns, or managing database sessions.

Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified.

Fetch a user's recent tweets (tweets, replies, retweets) using Playwright + Nitter fallbacks and produce compact JSON/Markdown summaries.

Transform any Claude Code session into an Automagik Genie orchestrator — guide users through brainstorm, wish, team, and PR lifecycle.

Azure AI Agents Persistent SDK for Java. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.

Real-time market data feeds from 8 prediction market platforms

Ordo rule engine Rust development guide. Helps create RuleSet, Step, conditional branches, terminal results. Use for writing rule definitions, understanding Step Flow model, creating Decision/Action/Terminal steps.

Create feedback <title>

Use when you need a deep-dive explanation of a specific file, function, or module in the codebase

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

Slash command prompt review - prompt quality, workflow completeness, cross-command consistency. Use for reviewing .claude/commands/*.md or .claude/skills/*/SKILL.md files.

List feedback items with filters

Удаляет блок публикации из `httpd.conf` и каталог `publish/{appname}` внутри Apache. Если других публикаций не осталось — удаляет глобальный блок 1C и останавливает Apache. С флагом `--all`

Build and train machine learning models using scikit-learn, PyTorch, and TensorFlow for classification, regression, and clustering tasks

All commands: `nansen research profiler <sub> [options]`

Ordo expression syntax quick reference. Includes comparison operators, logical operators, built-in functions, conditional expressions, field access syntax. Use for writing rule conditions, calculating output values, data transformation.

Proof-driven exploitation with 4-level evidence system, bypass exhaustion protocol, mandatory evidence checklists, and strict EXPLOITED/POTENTIAL/FALSE_POSITIVE classification.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, or using OpenAI-compatible clients. This is the high-level Foundry SDK - for low-level agent operations, use azure-ai-agents-python skill.

Ordo server deployment and configuration guide. Includes HTTP/gRPC configuration, environment variables, Nomad deployment, Docker, monitoring metrics, audit logging, multi-tenancy configuration. Use for production deployment, operations management, monitoring and alerting.

Build elegant frontend UIs following Microsoft Foundry's NextGen Design System using Vite + React + pnpm + Framer Motion. Use when creating dashboards, agent builders, data grids, entity management interfaces, or any application matching Foundry's refined dark-themed aesthetic.

Use the GitHub CLI (gh) to perform core GitHub operations: auth status, repo create/clone/fork, issues, pull requests, releases, and basic repo management. Trigger for requests to use gh, manage GitHub repos, PRs, or issues from the CLI.

9 editing & proofreading skills. Trigger: polishing drafts, academic tone, proofreading, translation. Design: style checkers and editing workflows for clear, concise academic English.

JSX syntax in Vue (e.g., class vs className, JSX plugin config).

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.

Managing database migrations with dbmate

Generate or edit images using AI models (FLUX, Nano Banana 2). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

Shell script development workflow. Use when modifying files in scripts/ directory or any *.sh files.

Opinionated guide for building dApps on Arbitrum using Stylus (Rust) and/or Solidity. Covers local devnode setup, contract development, testing, deployment, and React frontend integration with viem. Use when starting a new Arbitrum project, writing Stylus or Solidity contracts, deploying to Arbitrum, or building a frontend that interacts with Arbitrum contracts.

去不图床(7bu.top)图片上传。

Show Aigon commands

Intelligent skill router that analyzes user requests and automatically dispatches to the most appropriate skill(s) or zen-mcp tools. Routes to zen-chat for Q&A, zen-thinkdeep for deep problem investigation, codex-code-reviewer for code quality, simple-gemini for standard docs/tests, deep-gemini for deep analysis, or plan-down for planning. Use this skill proactively to interpret all user requests and determine the optimal execution path.

Deep technical documentation generation workflow using zen mcp's clink and docgen tools. First uses clink to launch gemini CLI in WSL for code analysis, then uses docgen for structured document generation with complexity analysis. Specializes in documents requiring deep understanding of code logic, model architecture, or performance bottleneck analysis. Use when user requests "use gemini for deep analysis", "generate architecture analysis document", "analyze performance bottlenecks", "deeply understand code logic", or similar deep analysis tasks. Default output is .md format.

Debug the Anomstack demo instance on Fly.io - check schedules, jobs, LLM alerts, and PostHog tracking

Full-site migration from Beaver Builder to the WordPress block editor (Gutenberg). Audits every Beaver Builder page, maps modules to their Gutenberg block equivalents, builds a migration plan for approval, and executes page-by-page conversion into native block markup — all through duplicates so yo

Where is this token moving and why? Large transfers, flow trends over time, and breakdown by wallet label.

Plan and track execution of a task. Use when starting implementation of a task defined in a milestone plan.

Generate or update infographic Structure components for this repo (TypeScript/TSX in src/designs/structures). Use when asked to design, implement, or modify structure layouts (list/compare/sequence/hierarchy/relation/geo/chart), including layout logic, component composition, and registration.

Operational knowledge for the grid_ctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging grid_ctf strategies.

9 economics skills. Trigger: economic modeling, policy analysis, macroeconomic data, FRED. Design: theory plus empirical methods with standard economics databases.

Guides Tailwind CSS v4 patterns for buttons and components. Use this skill when creating components with variants, choosing between CVA/tailwind-variants, or configuring Tailwind v4's CSS-first approach.

Manages practice rules. Use when user states a preference or approach, or asks to add/modify rules for coding, architecture, tooling, or best practices.

Guidelines for system design, project structure, and architectural decisions.

You are working inside a project that uses **learnship** — a multi-platform agentic engineering system for building real products with spec-driven workflows, integrated learning, and impeccable design.

Upload messy CSVs with minimal prompting for deep automated analysis

Semantic code navigation and editing triggered by speq-skills.

本仓库是 `pnpm` workspace，多包发布由 `changesets` 统一驱动。

Facilitate the EOS implementation kickoff sequence — the three foundational sessions where a leadership team first implements EOS. Focus Day introduces the tools and establishes the foundation. Vision Building Day 1 defines the Vision component (Core Values, Core Focus, 10-Year Target, Marketing S

What DeFi positions does a wallet hold? Protocol-by-protocol breakdown of assets, debts, and rewards across chains.

Manages the end-to-end cyber threat intelligence lifecycle from planning and direction through collection, processing, analysis, dissemination, and feedback to ensure intelligence products meet stakeholder requirements and continuously improve. Use when establishing or maturing a CTI program, defining intelligence requirements with business stakeholders, or building feedback loops between intelligence consumers and producers. Activates for requests involving CTI program maturity, intelligence requirements, PIRs, or intelligence lifecycle management.

Suggest the most likely next workflow action based on current context

Use when identifying, discussing, or solving issues using the EOS IDS process

Research autopilot <ID> [agents...] - Fleet setup + spawn + monitor + evaluate

You are a **senior ML engineer** with access to **Leeroopedia** — 27,667 pages of verified framework documentation covering vLLM, SGLang, DeepSpeed, Axolotl, TRL, PEFT, LLaMA-Factory, ColossalAI, and many more.

Creates a new Stitch project container (a design workspace). Call this when starting a new design session to get a projectId for screen generation.

Do research <ID> - agent writes findings

Optimize cloud infrastructure costs through FinOps practices, commitment discounts, right-sizing, and automated cost management. Use when reducing cloud spend, implementing budget controls, or establishing cost visibility across AWS, Azure, GCP, and Kubernetes environments.

Computational methods for humanities research including text mining and netwo...

Complete feature development workflow from design to deployment. Use when implementing new features or functionality.

Estimate market size using TAM, SAM, and SOM with top-down and bottom-up approaches. Use when sizing a market opportunity, estimating addressable market, preparing for investor pitches, or evaluating market entry.

使用此技能生成完整的HTML5小游戏代码。支持**模板模式**和**AI生成模式**。

Evaluate research <ID> - synthesize findings and recommend features

Step-by-step guide for creating new widgets in the Hex1b TUI library. Use when implementing new widgets from scratch, including widget records, nodes, extension methods, theming, reconciliation, and tests.

Import memories from other AI memory systems into Cortex. Supports claude-mem (SQLite), Claude Desktop sessions, ChatGPT web export (JSON), Gemini Takeout (JSON), Cursor conversations, and Claude Code JSONL. Use when the user says 'import from claude-mem', 'migrate memories', 'import ChatGPT history', 'import from Gemini', 'transfer memories', or when Cortex detects another memory system is installed.

Help users communicate more effectively in writing. Use when someone is drafting memos, emails, strategy docs, announcements, or any written communication that needs to be clear, concise, and persuasive.

After modifying any F# file, use this to get quick parse errors and typecheck warnings+errors. Also finds symbol references and inferred type hints.

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full ASM JSON, flattened CSV for easy import, and exportable Python code for data engineers. Common triggers include converting instrument files, standardizing lab data, preparing data for upload to LIMS/ELN systems, or generating parser code for production pipelines.

A complete working skill that fetches weather data using an API.

Use when you need to ask questions about a codebase or understand code using a knowledge graph

Open all Fleet research agents side-by-side in terminal

Convert Markdown files to PDF, DOCX, or HTML with advanced features.

Inspect a repository and draft an AGENTS.md file using the standard template, capturing commands, structure, and workflow rules.

Use when you need to generate an onboarding guide for new team members joining a project

Expert knowledge for Azure HDInsight development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when working with HDInsight Spark/Hive/Kafka/HBase, Ambari configs, VNet security, autoscale, or ARM/CLI deployment, and other Azure HDInsight related development tasks. Not for Azure Databricks (use azure-databricks), Azure Synapse Analytics (use azure-synapse-analytics), Azure Stream Analytics (use azure-stream-analytics), Azure Data Factory (use azure-data-factory).

This skill should be used whenever users need help with resume creation, updating professional profiles, tracking career experiences, managing projects portfolio, or generating tailored resumes for job applications. On first use, extracts data from user's existing resume and maintains a structured database of experiences, projects, education, and skills. Generates professionally styled one-page PDF resumes customized for specific job roles by selecting only the most relevant information from the database.

Takes any material and produces a complete, ready-to-publish Knox Hub blog post. Human-written tone. SEO+GEO optimized. All editor fields filled.

ast-grep NAPI reference and patterns for the packages/codemods project. Use when working with @ast-grep/napi in schema-migration codemods or packages/codemods/ directory, writing AST queries, or debugging tree-sitter node matching.

Interact with Zulip chat platform via REST API and Python client. Use when you need to read messages from streams/topics, send messages to channels or users, manage DM conversations, list users, or integrate with Zulip organizations for team communication workflows.

Scans GitHub Actions workflows and CI/CD pipeline configurations for supply chain attack vectors including unpinned actions, script injection via expressions, dependency confusion, and secrets exposure. Uses PyGithub and YAML parsing for automated audit. Use when hardening CI/CD pipelines or investigating compromised build systems.

End-to-end PR workflow for the hyperswitch-control-center repo. Use this skill whenever the user wants to raise a PR, submit changes, open a pull request, commit and push, or ship their work. Triggers on phrases like "raise a PR", "open a PR", "submit my changes", "commit and push", "ship this", "create a pull request". Even if the user just says "PR please" or "push my changes", use this skill.

Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

This skill should be used when the user asks to "check email", "read emails", "send email", "reply to email", "search inbox", or manages Gmail. Supports multi-account Gmail integration for reading, searching, sending, and label management.

Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode.

Local Solana agent wallet with local infra for transfers (SOL, USDC, USDT), Jupiter swaps, and x402 purch.

Prepares and automates the release process for multi-storage-client (version bump, release notes, checklist). Use when the user wants to cut a release, bump version, prepare release, publish a new version, or automate release steps.

Работа с Yandex Metrika Reporting API v1. Отчёты по трафику, конверсиям, UTM-меткам, поисковым системам.

Maintainer workflow for reviewing, triaging, preparing, closing, or landing OpenClaw pull requests and related issues. Use when Codex needs to validate bug-fix claims, search for related issues or PRs, apply or recommend close/reason labels, prepare GitHub comments safely, check review-thread follow-up, or perform maintainer-style PR decision making before merge or closure.

10 computer science skills. Trigger: algorithms, systems research, software engineering, security papers. Design: theory, complexity analysis, code-centric research, and security methods.

Generates detailed implementation plans from finalized designs

Manage the Accountability Chart — the organizational structure that defines who owns what seat, what each seat's 5 key responsibilities are, and the reporting hierarchy. Every function of the business has one clear owner. A person can own multiple seats, but every seat needs exactly one owner.

Interactive agent creation and improvement orchestrator. Create or improve Claude Code agents.

14 data visualization skills. Trigger: charts, plots, figures, publication-quality graphics. Design: one skill per tool with code templates and academic formatting conventions.

Applies WCAG 2.2 Level AA accessibility standards to UI components. Use when creating or modifying UI components, reviewing accessibility, or when users mention accessibility-related terms or concepts (e.g., WCAG, ARIA, a11y, screen readers, keyboard navigation, or contrast).

Formats SQL queries for better readability and consistency. Supports PostgreSQL, MySQL, and SQLite syntax. Not for: database schema design, query optimization, or data migration.

Extract numerical data from scientific figure images using Claude vision + OpenCV calibration. Supports 26+ plot types including bar charts, scatter plots, forest plots, Kaplan-Meier curves, box plots, and more.

The handle is direct invocation. The evidence is stdout/stderr/exit code.

Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync.

Is smart money exiting a token I hold? Net flow direction, seller breakdown by label, and recent SM trades.

Produces a comprehensive, cross-referenced audit of any SDK documentation site with a fully styled downloadable HTML report.

Cross-cutting validation methodology for verifying phase outputs and project integrity

Optimization without gradient information

Design memory hierarchy with progressive loading for optimal context management. Use when organizing CLAUDE.md imports, implementing just-in-time context loading, or designing priming hierarchies for agents.

When the user wants to configure, audit, or optimize robots.txt. Also use when the user mentions "robots.txt," "crawler rules," "block crawlers," "AI crawlers," "GPTBot," "allow/disallow," "disallow path," "crawl directives," "user-agent," "block Googlebot," "fix robots.txt," "robots.txt blocking," or "search engine crawling."

Dump Kurtosis state for debugging and sharing. Export enclave state including service logs, configurations, and file artifacts to a local directory. Use when you need to capture state for offline analysis or to share with others for debugging.

你的任務是在用戶的專案中實作統一金流 UPP 幕前支付功能。

Start an implementation task with proper planning, TDD workflow, and session hand-off. Use when beginning work on a Jira issue, starting a new feature, or resuming implementation work. Triggers on phrases like "start task", "begin implementation", "work on issue", or "implement feature".

Comprehensive guide for building Node.js command-line interfaces using Commander.js. Use when creating CLI tools with options, commands, subcommands, arguments, and help system customization.

Governance + tooling pattern for storing research artifacts, tagging, and discovery.

Prioritise research <name> - assigns ID, moves to backlog

How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management

<required_reading> **Read these reference files NOW:** 1. references/skill-structure.md </required_reading>

Use when acting as a project manager that delegates tasks to other Claude Code sessions - launch workers, assign them work, monitor progress, review their tool calls, and collect results

Guides maintainers through Hookdeck CLI releases (stable GA, beta from main, beta from feature branches) and user-centric GitHub release notes. Validates proposed versions against SemVer from the actual change set (e.g. breaking changes require a major bump). Use when cutting a release, publishing a tag, drafting release notes, choosing vMAJOR.MINOR.PATCH, GoReleaser, npm publish, pre-releases, following the release checklist, or `gh release create`.

Review research <ID> - review findings with a different agent

Interact with Calendar.app using a Swift CLI that wraps EventKit.

Audit current context composition and identify optimization opportunities. Use when context window is overloaded, agents are underperforming, or applying the R&D framework to optimize token usage.

Review research spec <ID> - improve the research brief before execution

When the user wants to create, optimize, or audit glossary page content and structure. Also use when the user mentions "glossary," "definitions," "terminology," "industry terms," "glossary page," "term definitions," "vocabulary," "glossary SEO," or "definition page."

Discovers and installs community skills from the public registry. Use when the user mentions a technology, framework, or task that could benefit from specialized skills not yet installed, asks 'how do I do X', 'find a skill for X', or starts work in a new technology area. Proactively suggest when the user's task involves tools or frameworks without existing skills.

Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in the future.