Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

prompt-polisher

Use when receiving messy, unstructured input like voice transcriptions, stream-of-consciousness notes, or rough document content that needs to be transformed into a polished, optimized prompt. Cleans up filler words, extracts intent, asks clarifying questions, applies Claude 4.x/Opus 4.5/Sonnet 4.5 best practices, and previews the polished prompt for approval before execution. Trigger phrases include "polish this", "clean this up", "turn this into a prompt", or when input is clearly rough/unstructured.

415 repo starsObserved in 2 repos

Agent Building

skill-governance-loop

Use when the user asks to review a skill, analyze skill quality, update a skill version, or run a repeatable keep/disable/archive decision loop from real failures instead of abstract best practices.

415 repo starsObserved in 2 repos

Agent Building

skills-governance

Use when auditing a large local skill collection, identifying duplicate or imported skills, comparing skill roots, or deciding what to keep, disable, or archive across Codex and adjacent agent skill directories.

415 repo starsObserved in 2 repos

Agent Building

lijigang-skill

李继刚（Prompt布道师/Prompt之神）的AI提示词创作思维——Lisp压缩美学+哲学底色+结构化写作+极简主义。触发词：「李继刚视角」「像李继刚那样写」「Prompt之神」「汉语新解」「压缩美学」「ljg-skills」「Lisp提示词」。擅长：Lisp伪代码风格提示词编写（公文笔杆子/汉语新解/七把武器系列）、哲学级Prompt思考框架（从工具论到道）、结构化写作方法论、认知工作流设计（13+1 Skills）、技术大会演讲、深度播客对话。

415 repo starsObserved in 1 repos

Agent Building

mega-goal-prompt

Generate a /goal mega prompt for Claude Code or Codex CLI by interviewing the user about their task. Use when the user wants to define a long-horizon autonomous goal — migration, refactor, feature build, optimization loop, test fixing, research project, learning system, or any task where the agent should run end-to-end without hand-holding. Trigger on: "help me write a goal", "I want Claude to keep working until...", "run this autonomously", "set a /goal", or any request that implies sustained agentic execution toward a non-trivial outcome. The skill conducts a structured interview (one question at a time) to extract outcome, context, success criteria, constraints, and quality bar — then outputs a filled-in mega prompt ready to paste into Claude Code or Codex.

415 repo starsObserved in 1 repos

Agent Building

statewright

Start, stop, or manage statewright workflows

415 repo starsObserved in 1 repos

Agent Building

tianya-gods-team

天涯神贴大神智囊团 — 20位传奇大神组成的多Agent决策系统。基于ClawTeam多Agent协作原理，实现「一个目标 → 20位大神并行分析 → 综合决策」的完整工作流。核心机制： - 智能领导者Agent（协调者）接收目标，分配给20位专业大神 - 20位大神并行分析，各自输出专业视角 - 综合决策Agent整合所有视角，输出最终决策使用方式： - 「启动天涯智囊团」+ 你的问题/目标 - 「召集大神」+ 你的问题/目标 - 「20位大神分析」+ 你的问题/目标涵盖领域：权谋分析、经济预言、历史解读、文化解构、都市情感、技术分析、黑帮江湖、盗墓探险、玄幻武侠、都市异能、悬疑推理、法医刑侦、历史穿越等。

415 repo starsObserved in 1 repos

Agent Building

workflow-builder

根据自然语言描述生成 flocks 内置工作流（workflow.md, workflow.json）。当用户提出创建/设计/生成/搭建工作流或任何多步骤流程（如告警调查、事件响应、SOP/Runbook 自动化）时使用本 skill。

415 repo starsObserved in 1 repos

Agent Building

iterative-loop

Runs continuous AI iteration loops that repeat build-test-fix cycles until success criteria are met. Use when building features requiring test-driven refinement, implementing tasks with clear pass/fail criteria, or automating iterative improvement workflows.

413 repo starsObserved in 1 repos

Agent Building

pr-loop

Shepherd open pull requests toward merge without a human watching them. Discover open PRs, review each new commit against a calibrated rubric, run the project's own checks as a verifier, post one concise signed review, and escalate anything risky to a human. NEVER merges, force-pushes, or edits CI. Runs headless inside a warm sandbox, one tick per PR code change.

413 repo starsObserved in 1 repos

Agent Building