Prompts
Prompt engineering and templates
git-workflow
by pmco23
Use before any destructive git operation (force-push, reset --hard, branch -D, rebase on published commits). Verifies the target, explains the consequences, and requires explicit confirmation. Not needed for routine commits, branch creation, or PRs — those are governed by CLAUDE.md git conventions.
apple-tv-plus
by CodeDraig
Stream Apple TV+ original content and manage watchlist
idapt-mcp
by idapt
Connect to idapt via MCP — single idapt dispatcher tool exposing Drive (cloud files), agents, Idapt Memory, tasks, computers, and 200+ AI models from any MCP-compatible client.
comfyui-comics-03
by tippyentertainment
Skill for generating Dark Horse Comics–style graphic novel characters, images, videos, sound effects, and voices via ComfyUI Cloud with a gritty, high-contrast aesthetic.
blockrun
by automindtechnologie-jpg
Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")
second-opinion
by asharma567
Get a second opinion from another LLM (Codex, Grok, Claude, Gemini) — smart-routed by task type, with optional deep-research and fan-out-to-all modes. Use when the user wants a sanity check, an outside critique, a different style ("ask grok", "ask gemini"), a synthesis across providers, or a deep-research dive on a question that benefits from web-grounded multi-step research.
commit
by zolbooo
Commit changes made in current session
nexus
by Creativityliberty
Unified mission engine + AI-agent skill system. Intercepts any project request (SaaS, app, API, CLI, agent) and decomposes into Goal → Mission → Task → Flow with quality gates and deliverable artifacts. Also installs and generates llms.txt / SKILL.md for 39+ AI agents with agent-native optimization from 32 system prompt profiles. Trigger on: project ideas, "je veux faire", "build me", "create a", SaaS, MVP, app, platform, skill setup, llms.txt, SKILL.md, agent docs, or any complex task needing structured decomposition before execution.
managing-skills
by mikekelly
Install, update, list, and remove Claude Code skills. Supports GitHub repositories (user/repo), GitHub subdirectory URLs (github.com/user/repo/tree/branch/path), and .skill zip files. Use when user wants to install, add, download, update, sync, list, remove, uninstall, or delete skills.
linear
by Sytex
Manage Linear issues, projects, and cycles. Use when user asks about issues, tasks, tickets, sprints, or Linear.
sandbox-agent
by sztwiorok
Delegate AI tasks to Claude agents running in isolated Buddy Sandbox environments. Use when user asks to "delegate task", "run task in sandbox", "parallel agent execution", "isolated AI task", "YOLO mode", "sub-agent", "compare solutions", "multi-agent", or mentions running AI tasks in sandboxes.
best-practices-reviewer
by 884js
実装中にClaude Codeのベストプラクティスに沿っているか確認し、改善が必要な場合は質問やアドバイスを促すスキル。 以下の場面で自動的に発動: - 複数ファイルを横断する大きな変更を始める前 - 長いセッションで多くのファイルを読み込んでいる時 - 曖昧なプロンプトで実装を開始しようとしている時 - テストや検証手段なしに実装を進めている時 - 何度も同じ修正を繰り返している時 「実装レビュー」「ベストプラクティス確認」「進め方チェック」などでも呼び出し可能。
claude-agents
by simplerick0
Create and configure Claude Code subagents for task-specific workflows. Use when creating new agents, updating agent configurations, or understanding agent best practices.
setup-context-docs
by wizact
Creates comprehensive context-driven development documentation structure for repositories. Analyzes codebase, generates multi-document constitution pattern (product.md, tech.md), language-agnostic feature specification templates, and updates README. Auto-invoked when setting up project documentation, context docs, or CLAUDE.md setup.
session-start-hook
by kangnam7654
Creating and developing startup hooks for Claude Code on the web. Use when the user wants to set up a repository for Claude Code on the web, create a SessionStart hook to ensure their project can run tests and linters during web sessions.
self-improvement
by cgk-platform
"Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks."
skill-seekers
by DriveSpark
"-Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes."
council
by rahulgi
Consult an advisory council of three AI personas — Cato (skeptic), Ada (optimist), Marcus (pragmatist) — backed by different frontier LLM agents (Gemini, Claude, Codex). Each persona runs as a separate agent process with full repo context and returns independent feedback. Use when the user says "/council", asks for a second opinion, wants feedback on code changes, needs a premortem, wants to pressure-test a decision, or asks "what do you think about this approach?" Claude may also proactively suggest consulting the council before major architectural decisions, risky deploys, or ambiguous trade-offs (but should ask for user approval first).
preflight
by rozwer
Run preflight safety check. Reads CLAUDE.md and Plans.md to list permissions and flag dangerous commands.
api-contract-sync-manager
by YPYT1
集合了所有的openclaw,claudecode,open等各个平台所有的skills
self-subagent
by pc-style
Orchestrate parallel sub-tasks by spawning non-interactive instances of your own CLI as subagents. Use when you need to parallelize work across multiple files, run independent investigations simultaneously, or delegate heavy multi-step tasks. Works with ANY AI coding CLI agent (Amp, Claude Code, Codex, Cursor, OpenCode, aider, Cline, Roo, goose, Windsurf, Copilot CLI, pi, etc.). Triggers on "run in parallel", "subagent", "delegate", "fan out", "concurrent tasks", or any complex task that benefits from parallel execution.
autopilot
by ianphil
This skill should be used when the user asks to "run autopilot", "autopilot feature N", "implement all phases", "run all phases sequentially", "autopilot 003", or wants to automatically implement all phases of a feature in sequence without manual intervention.
idea
by ppx123-web
Record ideas and thoughts to Obsidian vault. Creates structured idea notes with problem analysis and tags. Use when user says "记录想法", "有个idea", "记一下", "记录疑问", or captures inspiration/questions about technical problems, architecture, or research.
fetch-rules
by dolessHQ
Fetch and apply Cursor-style workspace rules supporting all rule formats (.cursor/rules/.md, .mdc, AGENTS.md, and legacy .cursorrules).