krea
Use when a task names Krea or Krea 2, when choosing between Krea's hosted API and its open weights, when wiring the Krea 2 Image or Krea 2 Style Reference API nodes, when building with FLUX.1 Krea Dev, when someone asks about Krea Realtime or realtime or streaming video generation, or when a Krea 2 job needs ControlNet, instruction editing, identity preservation or per-layer conditioning control that core ComfyUI does not provide.
dust-breaking-changes
CRITICAL guideline - Never introduce breaking changes to the private API without explicit user approval. Always warn and ask for validation first.
zenrouter
Implement and extend routing using the zenrouter Coordinator pattern. Use this skill when the user asks to add a route, feature module, layout, redirect rule, redirect guard, nested coordinator, or navigate programmatically. Triggers on: route, router, routing, coordinator, CoordinatorModular, RouteModule, NavigationPath, IndexedStackPath, RouteLayout, RouteRedirectRule, RedirectRule, RedirectResult, parseRouteFromUri, push, pop, replace, navigate, deep link, toUri, parentLayoutKey, layoutKey, bindLayout, RouteUnique, RouteGuard, RouteRedirect, notFoundRoute, zenrouter.
capcut-edit
Edit videos and beautify photos in CapCut on mobile. Use when the user asks to open CapCut, create/edit/export videos, add text/effects/music/captions, use templates, or retouch and enhance photos.
ray
Generate code screenshots via ray.tinte.dev API. Use when user asks for code screenshots, code images, code snippets as images, or says "ray". Calls POST https://ray.tinte.dev/api/v1/screenshot and saves the PNG result.
bridge-proof
This skill should be used when the user invokes the bridge-check command or asks to verify the isolated Devin bridge.
install-pymllm
Install the pymllm Python package. Asks the user whether to do a full build (with CMake C++ compilation) or a fast install (Python-only, skip CMake). Use when the user asks to install, set up, or reinstall pymllm.
conductor
Compact Conductor skill. Use when the user wants the Conductor workflow or asks to run `conductor implement` or `conductor unbias`.
brasa-template-writer
Write new brasa YAML templates from scratch or migrate legacy templates (with reader.function and handler-based fields) to the modern pipeline-based format. Use when the user asks to create a new template, write a template, migrate a legacy template, convert an old template, or work with YAML template definitions. Also trigger when the user mentions template creation, template migration, or refers to legacy/old templates.
code-flow-tracer
Trace code execution paths and data flow. Use when user asks "how does X work", "what happens when X", "trace the flow of X", "where does data come from", or needs to understand feature implementation.
changelog-maintenance
Use when asked to update the changelog, document version changes, prepare a release, or add entries for recent work. Handles CHANGELOG.md updates following Keep a Changelog format and Semantic Versioning. Do NOT use for committing (use git-commit) or creating release notes outside CHANGELOG.md.
update-integration-tests
Update the integration tests in this repository after a .NET preview1 or GA release. Use this skill when asked to update tests for a new .NET version release, when an issue mentions updating integration tests for a .NET release, or when test failures indicate a new .NET version has shipped and tests are out of date.
lesson-retro
Turn one batch or term of student feedback into a checked change list for the next one. Use when a teacher shares a feedback export, survey results or ratings and asks what to change next time, or says "retro", "lesson retro" or "what should I change for the next batch".
resume-builder
Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON output for https://rxresu.me.
llk-test-runner-skill
Delegates LLK test runs to the llk-test-runner agent using @.cursor/agents/llk-test-runner.md. Use when the user asks to run tests or mentions LLK tests. Ensure test commands run to completion before reading terminal output (no polling).
nightshift-release
Release a new version of the nightshift Go project using goreleaser. Use when the user asks to cut a release, push a new version, bump the version, publish a release, or verify a release succeeded. Covers version bumping, git tagging, goreleaser dry-run validation, pushing, and post-release verification via GitHub Actions and `gh`.
vibe-ship
Generates a complete, production-ready deployment setup for any app in one pass -- Dockerfile, docker-compose.yml, .dockerignore, CI/CD (GitHub Actions), scalability config (health checks, resource limits, K8s on request), and security hardening (non-root user, secrets, dependency scanning). Auto-detects the stack from repo files (package.json, requirements.txt, go.mod, pom.xml, Gemfile, etc.) and writes real working files, not just advice. Also audits an EXISTING Dockerfile/compose/CI setup with a static scoring script and reports concrete findings. Use whenever the user asks to "dockerize", "containerize", "make this deployable", "production-ready", "vibe ship this", "add CI/CD", "set up deployment", "ship this app", requests a Dockerfile/docker-compose/GitHub Actions workflow, or wants a deployment setup reviewed -- even for just one piece (e.g. "add a Dockerfile"), since the full set is interdependent.
codex-implementation-loop
Delegate implementation work to Codex (via the codex-companion runtime), then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex to write code, mentions handing off / delegating implementation to Codex, asks to work through a plan or spec unit-by-unit with Codex doing the coding, or wants a review-and-merge loop wrapped around Codex output â and also when resuming such a loop ("keep going", "next unit", "继ç»ä¸ä¸ä¸ª"). It encodes constraints that are expensive to rediscover: Codex runs in the real environment with effectively read-only git, must not be pointed at a full test suite by default, accepts only specific --effort values, and its self-report is a claim rather than evidence.
kimi-ask
Ask Kimi a read-only free-form question about the current repository. Use for prose explanations, flow tracing, module comparisons, or conceptual reasoning when the user wants an independent Kimi answer rather than implementation.
technical-seo-audit
Comprehensive technical SEO audit skill that analyses crawl data to identify issues, prioritise actions by business impact, and produce a detailed report plus actionable spreadsheet. Use this skill whenever the user wants to: run a technical SEO audit, analyse a website's technical health, review crawl data from Screaming Frog or Sitebulb, crawl a site via API (Firecrawl or similar), find indexability or crawlability issues, check Core Web Vitals, audit structured data or schema markup, detect cannibalisation or thin content, review redirect chains, find orphan pages, assess site architecture, or produce a prioritised list of SEO fixes. Also trigger when the user uploads a CSV from any crawl tool and asks for analysis, mentions "technical SEO", "site audit", "crawl audit", "SEO health check", or wants to understand why pages are not ranking from a technical perspective. This skill handles everything from data ingestion through to a business-impact-prioritised action plan.
llm-docs-optimizer
Optimize documentation for AI coding assistants and LLMs. Improves docs for Claude, Copilot, and other AI tools through c7score optimization, llms.txt generation, question-driven restructuring, and automated quality scoring. Use when asked to improve, optimize, or enhance documentation for AI assistants, LLMs, c7score, Context7, or when creating llms.txt files. Also use for documentation quality analysis, README optimization, or ensuring docs follow best practices for LLM retrieval systems.
alpha-insights
Business Analyst Skill. Triggered when users ask about business analysis, industry research, competitive analysis, product analysis, business model analysis, business opportunity discovery, market entry strategy, investment decisions, strategic planning, due diligence, and other strategic topics. Delivers in-depth, decision-grade HTML research reports through a seven-stage workflow (Briefing â Framing â Planning â Research â Insights â Report â Iteration).
create-changeset
Create changesets for the ledger-live monorepo using @changesets/cli. Use when the user asks to add a changeset, prepare a release, or document package changes for a PR.
format-cc
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.
PaperReport â Deep Structured Paper Report
This skill is the user-facing spec for a deep single-paper report. In the current local workflow, use it as the writing contract when a user asks for a deep report, detailed paper analysis, or formula derivation.
coder
Code specialist in a multi-bot group chat â writes, reviews, debugs, and explains code. Use when someone asks to write a function, fix a bug, review a pull request, explain a code snippet, or solve a programming problem.
improve-skill
Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.
bzfs-experimental-script-generator
Generate or change idiomatic minimal Bash and Python scripts that use bzfs and bzfs_jobrunner for ZFS snapshot management workflows in a sandboxed test VM: snapshot creation, replication/backup, restore rehearsal, snapshot pruning, snapshot monitoring, and snapshot list comparison. Use when asked to create or change ad hoc/manual or periodic/automatic scripts for these tasks. Do not use this skill for general ZFS administration or non-bzfs tooling.
configuring-agent-brain
Installation and configuration skill for Agent Brain document search system. Use when asked to "install agent brain", "setup agent brain", "configure agent brain", "setting up document search", "installing agent-brain packages", "configuring API keys", "initializing project for search", "troubleshooting agent brain", "pip install agent-brain", "agent brain not working", "agent brain setup error", "configure embeddings provider", "setup ollama for agent brain", or "agent brain environment variables". Covers package installation, provider configuration, project initialization, and server management.
qmd
Search markdown knowledge bases, notes, and documentation using QMD. Use when users ask to search notes, find documents, or look up information.
broken-link-checker
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".
pr-describe
Write a pull-request title and body from the current branch's commits and diff against the base branch. Invoke when the user asks to open a PR, draft a PR description, or summarize a branch.
agent-memory
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean up memories'. Also use proactively when discovering valuable findings worth preserving.
create-java-pr
Create a pull request in sentry-java. Use when asked to "create pr", "prepare pr", "prep pr", "open pr", "ready for pr", "prepare for review", "finalize changes". Handles branch creation, code formatting, API dump, committing, pushing, PR creation, changelog, and stacked PRs.
duckduckgo-websearch
Search the web using DuckDuckGo. Use when the user wants to search the internet, find current information, look up facts, search for news, or find websites about specific topics. Triggers include requests like "search for X", "look up Y", "find information about Z", "what is X" (when X may be recent, niche, or unknown), "tell me about Y", "what's the latest on", "news about", or any query requiring up-to-date web information. Also use when the user asks about a specific named entity (product, company, tool, person, event) that might not be in the training data.
bb-video
Code-made videos (mp4, 16:9 / 9:16 / 1:1): narrated explainers and beat-synced promos for sites / apps. The user picks only the style: whiteboard, risograph, ink-wash, launch motion, origami, pop art, op art, Matisse cut-outs, ASCII art, shadow puppets, Bauhaus, pixel art, chat log, toy 3D, newsreel, film-room breakdown, suspense mystery, isometric miniatures, movie trailer, news clippings, manga, animated map, Swiss kinetic type, dark motivational short, blueprint, paper collage, flat grain illustration, storybook mascot, Bayeux tapestry, 3D stick-figure parable, pencil-test animation, pen-drawn picture washed with colour, golden-age American cartoon, 1930s black-and-white rubber-hose cartoon. For explainers, history, news, promos from a URL. Use when asked for an "explainer video", "a promo for this site / app", or in Chinese "å个ç§æ®è§é¢" "ç½æ¿å¨ç»" "讲个åå²æ äº" "ç»è¿ä¸ªç½ç« / App åä¸ªå®£ä¼ ç" "产ååå¸è§é¢", or names a style (åçå°å·, 水墨, æ纸, æ³¢æ®, 欧æ®, åªçº¸, å符ç», ç®å½±æ, å 豪æ¯, åç´ , è天记å½, ç©å ·ä¸ç»´, èæ°é»ç, å½ååæ, æ¬çæ¢ç§, çè·å¾®ç¼©ä¸ç, çµå½±é¢åç, åªæ¥è§£è¯´, æ¥æ¼«, å°å¾å¨ç», ç士é£å¨ææç, æè°å±å¿å¨ç», èå¾å·¥ç¨å¾, 纸èºæ¼è´´, æå¹³é¢ç²æç», æç»ç»æ¬å祥ç©, è´å¶æ毯, 3Dç«æ´äººå¯è¨, é ç¬æç», 线稿æä¸ç, ç¾å¼é»éå¡é, ç¾å¼èå¨ç», é»ç½æ©¡ç®ç®¡å¡é, æ©¡ç®ç®¡å¡é, 30年代é»ç½å¡é, é»ç½èå¨ç»).
wavespeed
Generate or edit AI media (image, video, audio, 3D) on WaveSpeed, through the WaveSpeed MCP tools when they are connected or the wavespeed CLI on the user's machine. Use whenever the user asks to create, edit, animate, extend, upscale, or transform an image or video, generate audio/TTS/music or 3D, or produce marketing creatives.
codex-orchestrator
DEFAULT PIPELINE for all tasks requiring execution. You (Claude) are the strategic orchestrator. Codex agents are your implementation army - hyper-focused coding specialists. Trigger on ANY task involving code, file modifications, codebase research, multi-step work, or implementation. This is NOT optional - Codex agents are the default for all execution work. Only skip if the user explicitly asks you to do something yourself.
document-project
Generate comprehensive, professional project documentation structures including README, ARCHITECTURE, USER_GUIDE, DEVELOPER_GUIDE, and CONTRIBUTING files. Use when the user requests project documentation creation, asks to "document a project", needs standard documentation files, or wants to set up docs for a new repository. Adapts to Python/Go projects and OpenSource/internal contexts.
customise-workflow
Customise the prd-taskmaster-v2 skill workflow via curated brainstorm questions. AI asks, user answers in plain English, the skill writes their preferences to .taskmaster/config/user-workflow.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default provider, preferred execution mode, and template choice. Use when user says "customise workflow", "adjust my PRD settings", "tune the skill", or wants to change how prd-taskmaster behaves.
fii-dii-flow-tracker
Track and analyze FII/DII daily buy/sell flows in Indian markets. Use when user asks about institutional flows, FII selling/buying trends, DII activity, or institutional impact on Nifty/market direction.
compat-tests
Run cross-provider compatibility tests for specific algorithms and providers in the cryptography-kotlin project. Use this skill when the user asks to run compatibility tests, cross-provider validation, or wants to verify that a specific algorithm (like AES-GCM, ECDSA, HMAC, etc.) produces consistent results across different providers (JDK, OpenSSL3, Apple, CryptoKit, WebCrypto). Also use when the user mentions "generate and validate" test data, or references the compatibility test pipeline.
Io.Github.Lykhoyda/Ask Gemini
Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions
android-development
Create production-quality Android applications following Google's official architecture guidance and NowInAndroid best practices. Use when building Android apps with Kotlin, Jetpack Compose, MVVM architecture, Hilt dependency injection, Room database, or multi-module projects. Triggers on requests to create Android projects, screens, ViewModels, repositories, feature modules, or when asked about Android architecture patterns.
fix-intellij-observations
Fix IntelliJ observations in changed files. Use when the user asks to fix IntelliJ observations, warnings, inspections, or code problems. No need to list specific warnings â the skill discovers them automatically.
mo-arch
Query code architecture using README_AI.md index files. Use when user asks about project structure, where features are implemented, how modules work, or wants to understand codebase architecture. Triggered by questions like "what does this do", "where is X implemented", "how does module Y work".
ci-analysis
Analyze CI build and test status from Azure DevOps and Helix for dotnet repository PRs. Use when checking CI status, investigating failures, determining if a PR is ready to merge, or given URLs containing dev.azure.com or helix.dot.net. Also use when asked "why is CI red", "test failures", "retry CI", "rerun tests", "is CI green", "build failed", "checks failing", or "flaky tests".
cinematic-ui
Design and build websites with film-inspired visual systems, director-driven art direction, storyboard-first layout planning, and cinematic motion. Use when the user asks for a cinematic site, movie-style landing page, director-inspired UI, film-noir, sci-fi, romance, thriller, action, animation, or a movie-like website aesthetic, including requests phrased in Chinese. Do not use for generic web design unless the user explicitly wants a film or director reference.
Lassare
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace. Use when the user asks to inspect Claude Code, Codex CLI, Gemini CLI, Qwen Code, Aider, Cursor, OpenCode, Oh My Pi, Kimi, Copilot-style, or generic JSON/JSONL sessions for cost, tokens, tool failures, latency, anomalies, health, diffs, or CI gates.