Agent Building skills

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

code-as-harness

检测摩擦信号或陌生任务 → 搜证据确认重复 → 诊断根因 → 用代码修已有 harness 或建新 harness。 两种模式：Fix（确认重复后 → 写 hook/lint/guard）+ Build（反复出现的新任务类型 → Agent Team Leadership 规划新 skill/tool/流程）。 Use when: operator表达不满且搜证据确认历史上确实重复出现过同类问题（不是字面匹配"又"）、 连续 cancel 工具调用、收到反复出现的陌生任务类型且无对应 skill、 自己撞到工具/runtime 摩擦需要上报（雨刮器条款细则见正文"猫侧主动上报"节）。 Not for: 一次性批评（搜证据未发现重复）、玩笑式"笨猫"（后跟哈哈哈）、 有明确 error message 的首次代码 bug（用 debugging）、reviewer P1/P2 反馈（用 receive-review）、 一次性新任务（直接做，不建 harness）。 Output: Rich block 诊断卡（根因 + 证据 + 建议）+ 可选 F128 新 thread 提议（平行修复不打断当前任务）。 GOTCHA: 不是每次被批评都弹诊断卡——必须先搜证据确认重复，才进入诊断流程。 过度触发 = 猫在逃避批评。一次性陌生任务直接做不建 harness，只有反复出现才沉淀。

2.37k repo starsObserved in 1 repos
Agent Building
GitHub

memory-navigation

记忆系统三入口路由（search_evidence / graph_resolve / list_recent）决策树 + 噪音控制 + 加载时机。F188 Phase F (AC-F6) 配套 skill。 Use when: 没先验、压缩后回顾、"我记得最近讨论过 X"、search_evidence 反复 low-hit。 Not for: 已有精确 anchor 直接 Read；代码符号查 Grep/LSP。 Output: 选定入口 + 噪音控制参数 + 进入对应 MCP 工具。

2.37k repo starsObserved in 1 repos
Agent Building
GitHub

self-evolution

Scope Guard + Process Evolution + Knowledge Evolution — 主动护栏与自我进化。 Use when: operator scope 发散偏离愿景、同类错误反复出现、SOP 流程缺口、有价值的知识/方法论值得沉淀。 Not for: 日常 SOP 推进（正常执行）、一次性个案 bug fix。 Output: Scope Guard Log 记录 / Evolution Proposal 提案 / Episode Card → Method/Skill 蒸馏 → Eval 验证。

2.37k repo starsObserved in 1 repos
Agent Building
GitHub

cmux-orchestration

Orchestrate Claude Opus and Codex GPT-5.5 worker TUIs from a controller agent in the current cmux workspace. Use when delegating bounded tasks to worker panes, running plan-first delegations (Claude Code plan mode, Codex Plan mode), monitoring and tracking worker state, or verifying worker reports. Not for end-user cmux control (see cmux, cmux-workspace) — this drives agent workers.

2.37k repo starsObserved in 2 repos
Agent Building
GitHub

compozy

Explains Compozy capabilities, CLI commands, core workflow skills, optional extension skills, configuration, artifact structure, reusable agents, and extensions. Use when the user asks how to use Compozy, what commands are available, how the workflow pipeline works, or how to configure a workspace. Do not use for executing workflow steps — use the specific cy- skills instead.

2.37k repo starsObserved in 2 repos
Agent Building
GitHub

glmv-prompt-gen

Analyze images/videos and generate professional prompts for text-to-image and text-to-video AI tools (Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika). Use when the user wants to generate prompts from reference images/videos, create AI art prompts, or get prompt engineering suggestions from visual content.

2.35k repo starsObserved in 2 repos
Agent Building
GitHub

prompt-review

This skill should be used when the user asks to "review the prompt", "audit the system prompt", "check prompt quality", "inspect what the LLM sees", "debug prompt issues", or "find prompt engineering problems". Pulls the live rendered prompt via the API, explains how it's composed, and reviews it for issues.

2.33k repo starsObserved in 1 repos
Agent Building
GitHub

provider-integration-checklist

This skill should be used when the user asks to add or modify an "LLM provider", "model routing", "OAuth flow", "auth token handling", "provider config", or "fallback chain". Enforces provider integration completeness across config, routing, docs, and verification.

2.33k repo starsObserved in 1 repos
Agent Building
GitHub

prompt-engineering

Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design

2.33k repo starsObserved in 1 repos
Agent Building
GitHub

cancel-ralph

Cancel an active Ralph Loop. Use when the user wants to stop, cancel, or abort a running ralph loop.

2.31k repo starsObserved in 5 repos
Agent Building
GitHub