Prompts
Prompt engineering and templates
update-issue
by ruchernchong
Update a GitHub issue with new title, body, labels, or assignees
mula-refine
by carvalab
Unified prompt engineering and requirements planning. Use when exploring ideas, improving prompts, creating PRDs, generating task breakdowns, or iterating on existing plans. Includes Jira integration for creating subtasks from plans.
auto-evolution
by squirrel289
"Memory-driven self-evolution layer for Agent Skills. Captures usage patterns, learns from errors, and automatically generates reusable knowledge. Use when you want your agent to learn from experience, track skill effectiveness, or generate improvement suggestions."
create-agent
by kangnam7654
"Use when the user wants to create a new custom agent for Claude Code. Generates a properly formatted agent .md file in ~/.claude/agents/ following the user's established conventions.\n\nExamples:\n- \"/create-agent\" → Launch skill to create a new agent\n- \"새 에이전트 만들어줘\" → Launch skill\n- \"QA 테스터 에이전트 추가해\" → Launch skill with context"
code-review
by YPYT1
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
prompt-optimizer
by aleister1102
Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology. This skill should be used when users provide loose requirements, ambiguous feature descriptions, or need to enhance prompts for AI-generated code, products, or documents. Triggers include requests to "optimize my prompt", "improve this requirement", "make this more specific", or when raw requirements lack detail and structure.
repomix-gh
by CUG-hydro
GitHub 仓库打包工具（gh + zip download，默认 lean 模式）
wanx-img
by mebusw
Generate or edit images using WanX (Alibaba's text-to-image model)
Prompt Condenser
by christopherlhammer11-ai
"Condenses prompts into more efficient forms for faster processing."
vibe-coding-setup
by CarolMonroe22
Set up a complete vibe coding workflow with Claude Code after migrating from a platform. Covers Supabase MCP, Netlify MCP, Vercel, API keys, GitHub, and decision framework for when to stay vs migrate. Use when users want to set up MCPs, connect hosting/database, or start a new project with the "all-in-one" experience in Claude Code.
dialog
by pompeii-labs
Fast product research with Dialog. Use when the user wants to validate ideas, test concepts, or get customer feedback before building.
stats
by rozwer
stats.jsonl からの使用統計を表示します — ツール/スキル使用回数、トップ5、最適化提案。
self-improving-agent
by kimasplund
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
openclaw-leaderboard
by jamipuchi
Submit your OpenClaw agent's autonomous earnings to the public leaderboard with proof. Get verified by the community.
sentry
by Sytex
Monitor errors and issues from Sentry. Supports multiple organizations. Use when user asks about errors, exceptions, issues, or wants to check Sentry.
steve2
by aaarnv
The ultimate autonomous dev pipeline. Combines wavybaby (CoVe verification, skill discovery, MCP tooling) + GSD (roadmaps, phases, plans, discovery, state tracking) + Ralph (autonomous loop with circuit breakers). Generates a PRD, equips itself with the best tools, bootstraps a full GSD .planning/ structure, then runs Ralph to autonomously execute each plan with CoVe-verified code until the milestone is complete.
tmux
by samuerio
"Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output."
pipes-template-dex-swaps
by subsquid-labs
Production-ready template for indexing decentralized exchange (DEX) swap events. Includes schema, transformers, and examples for Uniswap, SushiSwap, PancakeSwap, and other AMM protocols.
agent-md-refactor
by VisualxIntelligence
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
oatda-vision-analysis
by devcsde
Use when the user wants to analyze images using vision-capable AI models through OATDA's unified API. Supports OpenAI GPT-4o, Anthropic Claude, and Google Gemini vision models.
truth-shield
by BAS-More
"Fact-verification layer v3 — catches hallucinations using 10 verification tiers, self-consistency sampling, isolated-context verification (CoVe), package existence checking (DepScope), and multi-judge arbitration. Cross-checks claims against local files, stored knowledge, live docs, web search, multi-model cross-check, and external fact-checkers. Every contradiction is persisted so the same lie is never repeated. MANDATORY TRIGGERS: 'verify this', 'truth-check this', 'fact-check this', 'shield this', 'truth shield', 'truth-shield', 'is this true', 'check your work'. STRONG TRIGGERS: 'are you sure', 'really?', 'source?', 'prove it', 'how do you know', 'is that right', 'double-check that'. PASSIVE MODE: 'shield on' / 'shield off'. Do NOT trigger on opinions, creative writing, brainstorming, or subjective preferences."
codex-audit
by Kanshan03
Codex 内容安全审计 — 每次用户输入时通过审计模型检测违规内容，防止 Pro 账号因滥用被封。
prompt-caching
by anilsoylu
Guide for optimizing prompt caching in agentic AI applications. Use when building Claude agents, optimizing API costs, designing system prompts, managing tool definitions, implementing compaction, or troubleshooting cache miss rates. Triggers: "prompt caching", "cache hit rate", "reduce API costs", "system prompt ordering", "tool definitions caching", "compaction", "context window management", "agent cost optimization", "prefix caching", "cache-safe forking", "agentic loop cost", "token cost reduction", "cache miss debugging".
Init Project
by midhunxavier
Initialize paper projects with venue-specific templates (LaTeX or DOCX). Detects existing repositories and creates subfolders to keep project root clean.