Prompts
Prompt engineering and templates
prompt-refinement
by v1truv1us
Transform prompts into structured TCRO format with phase-specific clarification. Automatically invoked by /ai-eng/research, /ai-eng/plan, /ai-eng/work, and /ai-eng/specify commands. Use when refining vague prompts, structuring requirements, or enhancing user input quality before execution.
knowledge-fetch
by cuipengfei
知识召回技能 - 从 Project CLAUDE.md、User CLAUDE.md 和 Memory MCP 查询历史知识
improve-prompt
by cuipengfei
优化提示词 - 结构化改写后立即执行，禁止扩展范围
pywayne-llm-chat-window
by wangyendt
PyQt5-based GUI chat window for LLM conversations with streaming responses and stop functionality. Use when working with pywayne.llm.chat_window module to create desktop chat applications with customizable window configuration, system message management, and real-time streaming display.
git-commit-analyzer
by shaoxyz
用 AI 分析 git 提交，鉴定你今天是「夯」还是「拉完了」。 支持 GitHub、GitLab、本地仓库。双语输出，两种风格（打工人/Linus）。
pywayne-llm-chat-bot
by wangyendt
LLM chat interface using OpenAI-compatible APIs with streaming support and session management. Use when working with pywayne.llm.chat_bot module for creating LLM chat instances with custom configuration, managing multi-turn conversations with history, handling streaming responses, or managing multiple chat sessions with ChatManager
agent-creator
by WalletConnect
Guide for creating custom Claude Code subagents. Use when user wants to create a new agent (or update an existing agent) that handles specific types of tasks with custom prompts, tool restrictions, and permissions. Triggers on requests to create agents, subagents, custom agents, or when user wants specialized AI assistants for specific workflows.
claude-mem
by enuno
Persistent memory compression system for Claude Code enabling context preservation across sessions with automatic observations, semantic search, and privacy controls
docu-optimizer
by kojott
Optimize CLAUDE.md and docs/ ecosystem following Boris Cherny's best practices
cnki-aigc-rewrite
by qingshanliuci
改写中文学术论文中被知网AIGC检测器标为"红色显著"的段落，目标是将AI率落出红色区间且不改变事实/数字/术语/引用。基于实战将20.6%降至10.1%（净降10.5个百分点）的工作流提炼。使用场景：用户提到"知网AIGC""降AI率""红色显著""降重"或贴出AIGC检测报告片段时触发。
solo-founder-gtm
by chadboyda
"When the user is a solo founder building their GTM motion, wants to scale without hiring, or needs to design an AI agent team for go-to-market. Also use when the user mentions 'solo founder,' 'one-person startup,' 'solopreneur,' 'bootstrapped,' 'no team,' 'AI agents as team,' 'scaling without hiring,' 'founder-led sales,' 'lean GTM,' 'one-person company,' or 'no employees.' This skill covers the complete solo founder GTM playbook from stack selection through agent team design, revenue-stage transitions, time allocation, and when to finally hire."
spec-kit-checklist
by ahgraber
Use when a Spec Kit feature has spec.md and you need a requirements-quality checklist (clarity, completeness, consistency, measurability, coverage), not implementation/runtime test cases.
writing-prompts
by bnadlerjr
Write agentic prompts including system prompts, workflow prompts, delegation prompts, and meta prompts. Use when creating commands, automating workflows, making tasks reusable, or when the user says "write a prompt", "create a command", or "automate this".
spec-kit-plan
by ahgraber
Use when an approved Spec Kit spec.md must be translated into technical design artifacts (plan.md, research.md, data-model.md, contracts/, quickstart.md) before spec-kit-tasks, or when plan.md is missing/outdated after spec or constitution changes.
commit
by cblecker
Enhanced git commit with mainline protection, conventional commits detection, and pre-commit verification
transcribe-audio
by markus1189
"Transcribes audio files (mp3, wav, ogg, m4a, flac, webm) using Gemini API via Portkey, saves transcripts as markdown, and supports follow-up analysis. Use when the user asks to transcribe audio, summarize a meeting recording, check a voice note, extract action items from a recording, asks what was discussed in an audio file, or mentions processing audio files in any way."
handoff
by ahgraber
"Use when ongoing work must continue in a new conversation, session, or agent with no shared history. Triggers: 'handoff', 'prepare context for next chat', 'summarize for a new session', 'continue this in another conversation'. Not for same-chat status updates or repository documentation."
build
by slamb2k
Context-isolated feature development pipeline. Takes a detailed design/plan as argument and executes the full feature-dev lifecycle (explore, question, architect, implement, review, ship) inside subagents so the primary conversation stays compact. Use when you have a well-defined plan and want autonomous execution with minimal context window consumption.
skill-creator
by arisng
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
prime
by slamb2k
Load project context before implementing features or making architectural decisions. Invoke proactively when starting significant work on DexAI. Supports domain-specific context loading: security (vault, RBAC, audit), routing (OpenRouter, model selection), adhd (design principles, RSD-safe), dashboard (frontend, backend, API), office (OAuth, email, calendar), memory (context capture, commitments), tasks (decomposition, friction-solving), channels (Telegram, Discord, Slack).
graphite-skill
by slamb2k
Context-efficient Git and Graphite workflows for Claude Code. Automatically delegates verbose git/Graphite CLI operations to isolated subagents, reducing context pollution by 225x. Use when working with git operations, Graphite stacked diffs, or any git workflow that produces verbose output. Prevents context window exhaustion by automatically applying delegation patterns via SessionStart hooks.
refactoring-agent-instructions
by bnadlerjr
Refactors bloated agent instruction files (CLAUDE.md, AGENTS.md, COPILOT.md, .cursorrules, etc.) to follow progressive disclosure — minimal root file linking to categorized files in guidelines/. Use when agent instructions are too long, hard to maintain, contain contradictions, or need reorganization.
copilot-vscode-docs
by arisng
Comprehensive research and grounding of answers using official VS Code and GitHub Copilot documentation. Use before conducting web searches for VS Code features, Copilot capabilities, configuration, debugging, extensions, remote development, or any official Microsoft documentation queries.
domain-planner
by build000r
Guide the 6-phase human-in-the-loop planning process for new domain slices spanning multiple repositories. Also orchestrates implementation when a plan is ready. Use when: - User says "let's plan the X slice" or "plan the X feature" - User wants to create a new feature spanning frontend and backend - User needs API contracts before implementation - User says "implement the X slice" or "build X" (orchestration mode) - User says "check plan quality for X" or "assess the X plan" (quality assessment mode) - User asks about planning a multi-repo feature Planning mode: Produces plan.md, shared.md, backend.md, frontend.md, flows.md, schema.mmd. Quality assessment mode: Runs assess-fix-reassess against the rubric before sign-off. Orchestration mode: Launches parallel agents per repo for scaffolding, audit, and fix loops. NOT for: bug fixes, small changes, refactoring, single-repo work.