菜单
Read FIRST in any loopany workspace. Routes user intent to the correct skill, enforces bootstrap, and orchestrates cross-skill chaining. Triggers: any loopany interaction, session start, ambiguous request, 'what should I do', multi-skill workflow.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Artifact lifecycle for loopany — the agent brain. Use when creating, modifying, or querying any artifact (task, signal, learning, skill-proposal, mission, person, note, brief, journal). Read this SKILL.md first for routing, then the relevant kind's Playbook. Triggers: any artifact CRUD, 'create a task', 'write a signal', 'dismiss signal', 'flip to done', 'what kind should this be', choosing a relation verb.
Self-improvement loop for loopany. Reads recent task outcomes + dismissed signals, discovers patterns, writes learning and skill-proposal artifacts. Also handles accepting/rejecting proposals. Triggers: 'reflect', 'what have we learned', 'improve yourself', ≥3 tasks done recently, 'accept <proposal-id>', 'reject <proposal-id>', 'review proposals', writing a learning or skill-proposal from any source.
Periodic review for loopany — daily, weekly, or monthly. Triggers: 'what's due today', 'what am I forgetting', 'what's slipping', 'weekly check', 'is the workspace healthy', 'is this still the right mission?', 'anything structural?', session start, daily/weekly/monthly cadence.
Migrate a loopany workspace from v0.1.0 to v0.2.0. Strips kind ID prefixes (tsk-/sig-/lrn-/...), flattens date-bucketed storage to artifacts/<dirName>/, renames snake_case frontmatter to camelCase, auto-stamps createdAt/updatedAt, builds the journal index, and adds the journal kind. Triggers when bootstrap throws SchemaVersionMismatchError pointing at this skill.
Auto-capture after substantive work concludes. Routes events (PR shipped, incident resolved, decision made, problem noticed) to the right loopany artifact kind with a quality gate. Should run proactively — check this skill at the end of every user-requested task. Triggers: after any substantive work, 'record this', 'log this outcome', PR shipped, incident resolved, decision made, problem noticed but deferred.
| name | loopany-resolver |
| description | Read FIRST in any loopany workspace. Routes user intent to the correct skill, enforces bootstrap, and orchestrates cross-skill chaining. Triggers: any loopany interaction, session start, ambiguous request, 'what should I do', multi-skill workflow. |
Read this before acting in a loopany workspace. It decides which skill to load. Two skills match → read both; they chain.
loopany artifact list --kind mission --status active
No active mission → run onboarding (ONBOARDING.md). Stop here — nothing
else fires without a mission.
Match the trigger, read the target skill, then act.
| Trigger | Skill | Read |
|---|---|---|
| Any artifact CRUD (create/get/list/append/status/set) | core | ../loopany-core/SKILL.md |
| Substantive work just ended (PR shipped, incident resolved, decision made) | capture | ../loopany-capture/SKILL.md |
| "reflect" / "what have we learned" / ≥3 tasks done / writing learning or skill-proposal | reflect | ../loopany-reflect/SKILL.md |
| "accept <proposal-slug>" / "reject <proposal-slug>" / review proposals | reflect | ../loopany-reflect/SKILL.md |
| "what's due today" / daily check-in / session start | review (daily) | ../loopany-review/SKILL.md |
| "what's slipping" / "weekly check" / "is the workspace healthy" | review (weekly) | ../loopany-review/SKILL.md |
| "is this still the right mission?" / "anything structural?" / monthly | review (monthly) | ../loopany-review/SKILL.md |
Choosing a relation verb / loopany refs add | core conventions | ../loopany-core/conventions/relations.md |
| Deciding note vs kind vs domain | core conventions | ../loopany-core/conventions/taxonomy.md |
Some workflows span multiple skills in sequence:
refs add.