Agent Building skills

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

skill-co-learn

用于在检测到高价值开发经验、功能模式、设计最佳实践,或用户明确要求“记住这个”“提炼Skill”“让其他Agent也学会”时,提炼可直接落盘的共享 Skill 文件,并在全局/项目级 Scope 之间做智能判断与路径适配。适用于 /skill-co-learn、/skill-colearn,以及相关中文触发语境。

151 repo starsObserved in 1 repos
Agent Building

skill-logger

Logs and scores skill usage quality, tracking output effectiveness, user satisfaction signals, and improvement opportunities. Expert in skill analytics, quality metrics, feedback loops, and continuous improvement. Activate on "skill logging", "skill quality", "skill analytics", "skill scoring", "skill performance", "skill metrics", "track skill usage", "skill improvement". NOT for creating skills (use agent-creator), skill documentation (use skill-coach), or runtime debugging (use debugger skills).

151 repo starsObserved in 1 repos
Agent Building

using-subagents

指导如何可靠使用 subagents、多个 Agents、并行 Agent 审查、集群搜索和项目分片处理。当用户要求使用 Agents/SubAgents、并行 Agent、对抗审查、多角色审查、集群搜索、项目分片处理,或明确说出“进入agents approve迭代模式”时使用。

151 repo starsObserved in 1 repos
Agent Building

vibe-pipeline

Author and run VibeFrame YAML pipelines with vibe run, checkpoints, and budget controls.

151 repo starsObserved in 1 repos
Agent Building

write-a-skill

创建、审查和维护 agent 技能(Skill)。Use when creating/refining a Skill or deciding whether Skill、command、hook、rule、AGENTS.md guidance is the right carrier.

151 repo starsObserved in 1 repos
Agent Building

zeroid

Identity infrastructure for AI agents — register identities, issue tokens, delegate to sub-agents, revoke credentials, manage policies

151 repo starsObserved in 1 repos
Agent Building

compose-team

Assemble the context bundles for each sub-agent based on evaluate-story output. Produces spawn-ready packages for Planning, Implementation, QA, or MicroDelivery sub-agents. Activate after evaluate-story, before spawning any sub-agent.

150 repo starsObserved in 2 repos
Agent Building

memory-compact

Emergency single-pass memory compression when context window pressure is high mid-task. Activate when approaching token limits during active work. For scheduled end-of-phase cleanup, use memory-refresh instead.

150 repo starsObserved in 2 repos
Agent Building

memory-refresh

Periodic memory maintenance — archive session files, convert recurring knowledge into summaries, update the memory index. Activate at end of a major phase (Discovery complete, sprint done) or when memory spans many sessions. For emergency context-window pressure mid-task, use memory-compact instead.

150 repo starsObserved in 2 repos
Agent Building

rules-normalize

Convert implicit or scattered project conventions into governed GAAI rule files, and create or modify rule files with integrity. Activate during Bootstrap, when creating a new rule, or when modifying an existing rule.

150 repo starsObserved in 2 repos
Agent Building