repair-router
Triage — diagnoses gap root cause and routes to the correct repair skill
- License 许可
- MIT
- 最近更新
- 2026-06-13
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- name
- repair-router
- context
- [ { "type": "gap", "fields": [ "gapKind", "checkCmd", "checkOutput", "taskTitle", "inputPattern", "unitPath", "allMissingItems" ] }, { "path": "{attemptDir}/TASK.md", "type": "file", "label": "task-definition", "optional": true }, { "path": "{attemptDir}/CHECK.md", "type": "file", "label": "checks", "optional": true } ]
- description
- Triage — diagnoses gap root cause and routes to the correct repair skill
- allowed-tools
- [ "Read", "Glob", "Bash" ]
- related-skills
- [ "repair-check-failed", "repair-missing-output", "repair-dependency" ]
03 SKILL.md 正文
Repair Router
You are a repair triage agent. Diagnose the root cause and invoke the correct repair skill.
Step 1: Read Context
- Read
repair-context/gap.md— what's broken - Read
repair-context/history.md(if exists) — what was already tried
CRITICAL: Do NOT repeat failed approaches.
Step 2: Route
| Gap Kind | Repair Skill | When |
|---|---|---|
check-failed |
/repair-check-failed |
Check command returned non-zero |
output / corrupted |
/repair-missing-output |
Expected file doesn't exist or is invalid |
blocker / input |
/repair-dependency |
Required input missing from upstream |
Step 3: Invoke
Read the selected repair skill's SKILL.md and follow its instructions. The context files are already gathered — use them.
Red Flags
- Same gap attempted 3+ times → task definition may be wrong, write LEARN.md
- Inputs missing from upstream → dependency issue, not local
- Check command itself broken → fix the check, not the output
04 同仓库更多 Skills
hello-checker
Use this skill when asked to "verify", "check", or "validate" a file's existence and content. It provides a reliable workflow for confirming files meet their spec.
ask-skill
暂无简介
html-review-artifact
Framework-wide guidance for crafting polished human-review artifacts as markdown or HTML
converge-planning
Design a Converge playbook end-to-end. Use when the user says "plan a project", "design a playbook", "decompose into tasks", "scaffold a Converge workflow", "onboard to Converge", or asks how to write TASK.md / playbook.yml. Two entry points: plan a new playbook or update an existing one. Hand off to `/converge-control` after producing the playbook structure.
converge-control
Operate a Converge playbook end-to-end — start runs, monitor progress, narrow failures with `--select`, inspect runtime state, validate definitions, surgically reset subtrees, and stop stuck or orphaned runs. Use this skill whenever the user says "run my playbook", "execute this", "monitor the run", "converge failed", "the run is stuck", "retry failures", "babysit this playbook", "what's the status?", "show me the gantt", or asks how to use `converge run` / `--select` / `inspect` / `doctor` / `clean` / `stop`. Also use it for `HTTP 401` / `Invalid API key` failures on the first task — those are environment-not-playbook problems — and for any post-run cleanup work. Hand off to `converge-planning` if the user wants to design or restructure the playbook itself.
repair-taskts
Fix task.ts definition issues — Seed syntax, missing .build(), empty checks, import errors, TypeScript errors