提示词
提示词工程与模板
implement-plan
mhylle
Orchestrate the execution of complete implementation plans, delegating each phase to implement-phase skill. This skill manages the full plan lifecycle including phase sequencing, user confirmation between phases, and overall progress tracking. Triggers on "implement the plan", "execute the implementation plan", or when given a path to a plan file.
continuous-learning
mhylle
Pattern extraction framework for learning from sessions. This skill captures valuable patterns discovered during work sessions including error resolutions, user corrections, workarounds, debugging techniques, and project-specific patterns. Triggers on Stop hook, end of session, "save learnings", "extract patterns", or when explicitly asked to capture knowledge from the current session. Outputs learned skills to ~/.claude/skills/learned/.
team-brainstorm
mhylle
Deep brainstorming using agent teams for adversarial multi-perspective analysis. Use when users want thorough idea exploration with real debate between independent perspectives. Triggers on "team brainstorm", "deep brainstorm", "brainstorm with team", "debate this idea", or when the user explicitly requests team-based analysis. Higher token cost but significantly deeper analysis than single-agent brainstorm.
prompt-generator
mhylle
Generate implementation prompts for phase-based project execution using an orchestration pattern. Use when users request prompts for implementing project phases, need orchestration prompts for multi-step implementations, ask for "/prompt", "generate prompt", "create implementation prompt", or want to create structured implementation instructions for subagent delegation. Outputs the prompt to chat and saves to docs/prompts folder.
openclaw-self-healing
Ramsbaby
4-tier autonomous self-healing system for OpenClaw Gateway with persistent learning, reasoning logs, and multi-channel alerts. Features Claude Code as Level 3 emergency doctor for AI-powered diagnosis and repair.
video-creator
yangliu2060
AI短视频创作与多平台发布，使用即梦MCP生成视频，使用Playwright MCP自动发布到YouTube/TikTok/Instagram/Facebook/LinkedIn/Twitter等平台。
Skill Sanitizer
cyberxuan-XBX
First open-source AI sanitizer with local semantic detection. 7 layers + LLM intent analysis. Zero cloud — your prompts stay on your machine.
competitor-price-monitor
yangliu2060
监控竞品网站价格变动，检测到变化时发送通知。支持多个竞品URL批量监控，自动对比历史价格，发现差异立即提醒。
email-assistant
yangliu2060
AI智能邮件助手，分析邮件内容生成摘要，判断是否需要回复，并基于上下文生成专业回复草稿。
linkedin-post-creator
yangliu2060
基于品牌调性和内容主题，AI生成高质量LinkedIn帖子，支持多轮反馈优化，输出可直接发布的专业内容。
creative-direction
dylanfeltus
Image prompt templates, model selection guidance, and anti-generic patterns for generating visual assets. Use when the user needs AI-generated images for landing pages, marketing, or products. Covers hero images, feature illustrations, OG cards, icons, and backgrounds.
save-session
blacktop
Save AI agent session information for later resumption. Use when: (1) Finishing a work session and want to save progress (2) User says "save session", "remember this session", or "save your session ID" (3) Before ending a long coding/debugging session (4) When user wants to be able to resume this conversation later Supports Claude, Codex, Gemini, Copilot, Cursor, and other AI agents.
orchestrate
blacktop
Lead-developer workflow for orchestrating sub-tasks with Claude Code CLI (Opus 4.5/Sonnet) using structured handoffs, review loops, and role specialization. Use when Codex should act as lead/architect, plan architecture and file structure, break work into atomic tasks, delegate bulk boilerplate/docs to Claude, and verify/iterate on Claude output.
handoff
blacktop
Generate optimized handoff prompts for delegating tasks to LLM agents. Use when needing to hand off work to another agent (GPT-5.2/Codex, Claude Opus 4.5/Sonnet 4, or Gemini 3 Pro/Flash), whether for a sub-task/parallel task within the same project or a fresh start handoff to a new agent context. Triggers on requests like "create a handoff prompt", "delegate this task to another agent", "hand this off", or "prepare context for another agent".
moai-foundation-claude
Ven0m0
Core Claude Code extension-authoring playbook for skills, agents, commands, plugins, hooks, and settings. Use when creating or reviewing Claude Code extensions and automation workflows.
agent-teams
DmitriyYukhanov
Set up and orchestrate Claude Code agent teams - multiple Claude Code instances working together with shared tasks, inter-agent messaging, and centralized management. Use when the user wants to (1) create or start an agent team for parallel work, (2) configure agent team settings like display mode or teammate mode or permissions, (3) coordinate teammates for code review or debugging or feature development or research, (4) understand when to use agent teams vs subagents, (5) troubleshoot agent team issues. Triggers include mentions of "agent team", "team of agents", "parallel agents", "teammates", "split pane", "tmux teammates", "delegate mode", "spawn teammates", or wanting multiple Claude instances collaborating.
time-lens
vladmdgolam
Analyze and visualize time spent on software projects by combining data from multiple sources: WakaTime coding time, git commit session detection, Claude Code usage, Codex CLI usage, and Cursor IDE usage. Produces both an interactive HTML dashboard (dark-themed, Chart.js) and a Markdown report with ASCII charts. Use when the user asks to: analyze work hours, calculate time spent on a project, generate a work hours report, visualize coding activity, create a project time breakdown, or summarize development effort across date ranges.
cross-review
DmitriyYukhanov
This skill should be used when performing cross-review, dual review, or multi-model review of plans, implementations, architecture, or code. Applies when the user wants to "review with codex", "get a second opinion", "validate with another model", "dual review", or wants multiple AI perspectives on quality. Orchestrates review-triage-fix cycles between Claude and Codex CLI using the best available skill, repeating until clean or a decision is needed.
boost-modules
av
Create custom modules for Harbor Boost, an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.
managing-artifacts
axiomantic
Use when generating documents, reports, plans, audits, or when asked where to save files. Triggers on "save report", "write plan", "where should I put", "project-encoded path"
council
rube-de
Consult external AI council (Gemini, Codex, Qwen, GLM-5) for thorough reviews and consensus-driven decisions. Use ONLY when explicitly invoked with "/council" or when user says "consult the council", "invoke council", or "council review". Do NOT auto-trigger on generic phrases like "thorough review".
sharpening-prompts
axiomantic
Use when reviewing LLM prompts, skill instructions, subagent prompts, or any text that will instruct an AI. Triggers: "review this prompt", "audit instructions", "sharpen prompt", "is this clear enough", "would an LLM understand this", "ambiguity check". Also invoked by instruction-engineering, reviewing-design-docs, and reviewing-impl-plans for instruction quality gates.
claude-code-web-docker
TrevorS
Set up and use Docker in Claude Code for Web environments. Use when Docker builds fail with bridge/iptables errors, SSL certificate errors through proxy, or when working in containerized web environments.
maintaining-claude-code
TrevorS
Validate and improve Claude Code configurations (CLAUDE.md, skills, commands, hooks). Use when auditing config quality, checking skill discoverability, organizing .claude directory, or deciding which entity type to use.