bug-echo
After fixing a bug, find and rate other instances of the same pattern in the codebase. Two modes: described, or inferred from a recent fix with self-validation. Triggers: "run bug-echo", "echo this fix", "scan for similar bugs", "find other instances", "after-fix scan".
agent-repo-init
One-click initialization of a multi-agent repository from the Antigravity template. Use this skill when users want to scaffold a new project quickly (`quick` mode) or with runtime defaults (`full` mode) including LLM provider profile, MCP toggle, swarm preference context, sandbox type, and optional git init.
Io.Github.ArkTechNWA/Zsh Tool
Zsh for Claude Code. PTY mode lets Claude type passwords. NEVERHANG + A.L.A.N.
bash-safety
Enforce safe bash scripting practices when writing, reviewing, or fixing shell scripts. Covers quoting, arrays, conditionals, arithmetic, redirections, strict mode, and static analysis. Use when editing .sh/.bash files, reviewing shell scripts, fixing shellcheck warnings, or writing new bash code.
zafrida-http-control
Control ZAFrida in PyCharm through local HTTP APIs. Supports project query/switch/create, device and connection mode setup, target/script/extra args setup, run/attach/stop actions, run/attach log path, log content reading, and a summary state endpoint.
Adopted from ck:ship: argument flags for ship modes and pipeline control
argument-hint: "[official|beta] [--skip-tests] [--dry-run]" allowed-tools: - Bash - Read - Write - Edit - Grep - Glob - Agent - AskUserQuestion - WebSearch source: gstack/claudekit-engineer ---
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.
enrichment-module-builder
Build a new Nemesis file enrichment module end-to-end with explicit user approval gates for output mode, library choice, sample files, and integration testing.
Agent Loop Skill â Claude Code Native Mode
This skill lets you run the `coding-review-agent-loop` orchestration directly inside an interactive Claude Code session, without calling `claude -p` for Claude turns.
anonymous
Enable or disable anonymous mode on DevGlobe
pump-admin-ops
Admin and authority operations for the Pump protocol â set coin creator, update token incentives, set IDL authority, claim cashback, Mayhem mode, and BothPrograms cross-program admin instructions.
create-supervisor
Distill a graduate advisor into an AI Skill. Import comments, meeting notes, chat logs, and docs to generate Method Core + Academic Style + Persona + Graduation Playbook, with explicit mode switch and distill strategy switch (strict/hybrid/template-first). Use for /create-supervisor, /update-supervisor, /list-supervisors.
Io.Github.Tjp2021/Mcp Thinkgate
Auto-classifies prompt complexity and routes to the right Claude thinking mode. No API key needed.
haiku-pilot
Haiku-first execution playbook: through deliberate prompt structure, sub-agent delegation, and quantitative escalation gates, get Haiku 4.5 to produce near-Opus quality on most tasks. Escalate to Sonnet/Opus only when gates trigger. Triggers: "haiku", "Haiku", "Haiku mode", "haiku-pilot". Do NOT use for: cost-only token optimization, file-count cognitive heuristic, agent dispatch table, CLAUDE.md / rules audit, harness health check. This SKILL is a runtime router + escalation gate, not a decision tree or directory.
memory-bank
Token-efficient persistent memory system for Claude Code that extends your session limits by 3-5x. Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode. Activates at session start (if MEMORY.md exists), on "remember this", "pick up where we left off", "what were we doing", "wrap up", "save progress", "don't forget", "switch context", "hand off", "memory health", "save state", "continue where I left off", "context budget", "how much context left", or any session start on a project with existing memory files. This skill solves two problems at once: Claude forgetting everything between sessions, AND sessions hitting context limits too fast. It replaces thousands of wasted re-explanation tokens with a compact, structured memory load that gives Claude full project context in under 2,000 tokens.
Io.Github.User0856/Snaprender
Screenshot any website as PNG, JPEG, WebP, or PDF. Device emulation, dark mode, ad blocking.
context-monitor
Monitor conversation context and prevent MAX mode by warning at token thresholds and generating handoff summaries. Use when context approaches 100K/150K/180K tokens or when working with high-cost files.
macos
Control macOS via AppleScript/osascript. Manage windows (move, resize, tile), apps (launch, quit, focus), system (volume, dark mode, notifications), Spotify, browsers, Calendar, Reminders, Finder, and clipboard. Use when the user asks to control their Mac, arrange windows, manage apps, or interact with native macOS features.
design-compare
Compare Figma designs against implementation screenshots, identifying layout, typography, color, and sizing discrepancies. Generates a structured visual review table and an interactive HTML comparison page with swipe and side-by-side modes. Use when the user asks to compare design with preview, compare Figma with screenshot, check design implementation, or provides a Figma URL alongside a screenshot.
ai-psychosis-mode
True alias for reality-check-mode. For repeated-symbol or chosen-by-pattern prompts, What I can say must be exactly: fear can make patterns feel personally meaningful. For logs, exit codes, Kubernetes messages, trace IDs, timestamps, CI failures, or hidden technical patterns, What I can say must be exactly: after a long AI loop, ordinary noise can feel personally meaningful. Use only Grounding, What I can say, and Safer next step. Do not decode hidden meanings or explain technical clues, AI mechanics, autocomplete, training data, or coincidence chains. Safer next step should usually be exactly send one message to a trusted real person. No bullets, numbered lists, message drafts, or pattern analysis.
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
turkey-build
Multi-agent app builder with 7 modes - greenfield, iteration, bugfix, refactor, UI polish, migration, and audit. PM orchestrates specialized agents with feature branches. 98%+ quality gate, runtime verified, visual QA.
mcpmu
Install, set up, and manage MCP servers using the mcpmu CLI. Use when the user wants to install mcpmu, register it as an MCP server, add/remove/list MCP servers, manage namespaces, set tool permissions, or expose servers via serve mode.
nuxt-best-practices
Nuxt 3/4 performance optimization and architecture guidelines for building fast, maintainable full-stack applications. This skill should be used when writing, reviewing, or refactoring Nuxt code to ensure optimal patterns. Triggers on tasks involving data fetching, server routes, auto-imports, rendering modes, or Nuxt-specific features.
agent-estimation
Accurately estimate AI agent work effort using the agent's own operational units (tool-call rounds) instead of human time. Use when asked to estimate, scope, plan, or evaluate how long a coding task will take. Prevents the common failure mode where agents anchor to human developer timelines and massively overestimate. Outputs a structured breakdown with round counts, risk factors, and a final wallclock conversion.
AIGC Detection, Rewriting & Thesis Writing Assistant
Bilingual academic paper assistant. Two modes: **Detection & Rewrite** (analyze existing papers for AI-generated content) and **Thesis Writing** (generate full thesis drafts from templates and code). Supports Chinese and English academic papers.
Io.Github.PyJudge/Pdf4vllm
PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.
context-modes
Structured work modes for agent sessions. Set LACP_CONTEXT_MODE to activate: tdd (red-green-refactor), debugging (4-phase root cause), sprint (pre-agreed criteria), verification (evidence-before-claims), brainstorm (design first), think (pause-and-reflect), orchestrate (task decomposition). Each mode injects behavioral rules at session start.
react-router-data-mode
Build React applications using React Router's data mode with createBrowserRouter and RouterProvider. Use when working with route objects, loaders, actions, Form, useFetcher, or pending/optimistic UI without the Vite plugin.
caveman
Ultra-compressed communication mode. Slash token usage ~75% by speaking like caveman while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Humanizer PRO
Humanize AI text to bypass GPTZero, Turnitin, Originality.ai. Stealth, Academic, SEO modes.
Coding CLI Delegation
When the Manager assigns you a task with a "## Coding CLI Mode" section in `spec.md`, you do **not** write the code yourself. Instead, you:
github-issue-solver
Accept a GitHub issue URL or issue details, create a comprehensive plan (in plan mode - shows plan first), then implement the solution including tests and documentation, create/update release notes for Home Assistant users, and update the README roadmap for new features. Use when the user provides a GitHub issue or asks to solve an issue. ALWAYS presents the plan first and waits for user approval before implementing.
executor
Focused implementation mode for one planned slice with explicit verification and handoff.
learn-on
Enable continuous learning mode for automatic insight extraction
ai-advise
Proactive governance advisor â checks standards, decisions, and quality trends during development. Always advisory, NEVER blocks. Three modes: `advise` (post-edit), `gate` (pre-dispatch), `drift` (on-demand decision audit). Trigger for 'governance check', 'advise on this change', 'check for drift', 'is this aligned with active decisions', 'shift-left advisory'. Not for blocking gates â use /ai-verify. Not for narrative code review â use /ai-review.
PageShot MCP
Capture webpage screenshots with format, viewport, and dark mode options
aura
All-in-one fullstack dev engine for Claude Code. Build, fix, clean, deploy, review in one /aura command. Discovery-First · Tiered Model · 6-Layer Security · 33 Modes · 8 Languages · 23 Hooks · 75% Token Savings. Use when user asks to build, fix, clean, deploy, review, debug, qa, brainstorm, orchestrate, or create content.
hyperfocus
ADHD-friendly output formatting for Codex. Restructures responses with evidence-based cognitive accessibility: chunking, visual hierarchy, front-loaded key points, and progressive disclosure. Three modes: clean, flow (default), zen. Use when user says "hyperfocus", "focus mode", "adhd mode", "adhd friendly", or invokes /hyperfocus.
game-art-direction
Direct game art and creative vision. Turn GAME_DESIGN into a production-level ART_DIRECTION defining a recognizable visual style, camera and composition, world and character grammar, functional colour/light/material, HUD feedback, motion and transition specs, audio direction, and a signature moment for every screen and mode. Use for what should the game look like, set the art direction, define the visual style. 游æç¾æ¯ä¸åææ¹åãæ GAME_DESIGN 转æçå级 ART_DIRECTIONï¼å®ä¹å¯è¾¨è¯è§è§é£æ ¼ãé头æå¾ãä¸çä¸è§è²è¯æ³ãåè½æ§è²å æè´¨ãçé¢åé¦ãè¿å¨ä¸è½¬åºè§æ ¼ã声é³æ¹ååæ¯ä¸ªçé¢/模å¼çç¾å游ææ¶å»ãç¨äºå¤æ游æåºè¯¥é¿ä»ä¹æ ·ãå¶å®æ¸¸æç¾æ¯æ¹åçéæ±ã
Context management plugin for Claude Code. Your AI remembers your projects, people, and decisions across every session. Plain files on your machine.
Use when external content arrives in the session â emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture â the skill checks 03_Inputs/ for unrouted files and enters inbox scan mode. Stores raw content, routes to capsules, extracts tasks and insights into the stash.
nerv-ui
NERV Operations Console v2 â Evangelion-inspired UI component library. Data-driven Three.js MAGI visualization (yield surface mesh + organic flow curves + bar columns), blockchain event log terminal, dense metrics grid, vault cards, oracle consensus display, CRT effects, emergency mode. Noto Serif Display (weight 900) + Shippori Mincho B1 + JetBrains Mono. NO HELVETICA. Every pixel conveys information.
2-repro-issue
Reproduce a single LinkedIn-MCP issue locally on the current branch against the real authenticated LinkedIn session at ~/.linkedin-mcp/profile/, using the MCP streamable-http server. Captures the exact failure mode (tool output, error, missing data) and maps it back to the scraper code path. Use when the user says "reproduce
PaperJury (CS-conference paper review and editing)
PaperJury edits and hardens any CS-conference paper. It runs in three modes. In **direct-edit mode** (the common case) the user describes a change in Chinese or English and the LaTeX is edited directly through a CS-venue writing toolkit, with author sign-off. In **review mode** (occasional, pre-subm
ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
lidguard-cli-runtime
LidGuard CLI, settings, permission commands, examples, and failure modes reference. Use when working on command routing/help, settings defaults and validation, linux-permission or macos-permission commands, CLI examples, suspend history, or user-facing operational failures.
add-agent-target
Use when adding support for a new AI agent target to agentsmesh. Covers official format research, canonical mapping, importer/generator/linter work, realistic fixtures, unit/integration/e2e coverage, matrix/docs updates, and final verification. Includes both project and global mode from day one.
pi-statusbar-release
End-to-end release workflow for pi-statusbar, including mode selection, version/tag releases, formula-only revisions, tap sync, and post-release verification.
Audio Jingle Skill
Three sub-modes. The active project's `audioKind` decides which one runs:
adding-ai-agent-rendering-system
Implement a new Packmind AI agent rendering/deployer pipeline (single-file or multi-file) with type and registry wiring, frontend UI/docs updates, and thorough unit/integration tests to reliably support additional coding assistants and distribution formats when introducing a new agent integration or render mode.