repair-missing-output
Produce missing output files by reading the task definition and executing the required work
- License 许可
- MIT
- 最近更新
- 2026-06-13
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- name
- repair-missing-output
- tags
- [ "repair", "gap:output", "gap:corrupted" ]
- context
- [ { "type": "gap", "fields": [ "gapKind", "taskTitle", "taskPrompt", "allMissingItems", "unitPath" ] }, { "path": "{attemptDir}/TASK.md", "type": "file", "label": "task-definition" }, { "path": "{attemptDir}/NEEDS.result.md", "type": "file", "label": "available-inputs" }, { "path": "{attemptDir}/CHECK.md", "type": "file", "label": "checks", "optional": true }, { "path": "{attemptDir}/LEARN.md", "type": "file", "label": "previous-learnings", "optional": true } ]
- description
- Produce missing output files by reading the task definition and executing the required work
- allowed-tools
- [ "Read", "Write", "Edit", "Bash", "Glob", "Grep" ]
03 SKILL.md 正文
Repair Missing Output
A task's expected output file(s) don't exist or are corrupted.
Step 1: Read Context
- Read
repair-context/gap.md— which files are missing - Read
repair-context/task-definition.md— how to produce them - Read
repair-context/available-inputs.md— what input files you have - Read
repair-context/history.md(if exists) — DO NOT repeat failed approaches
Step 2: Produce Outputs
Follow the task definition instructions to create the missing files.
Key principles:
- Write complete, production-quality content (no placeholders)
- Match the expected format (check extension: .json → valid JSON, .html → valid HTML)
- Write to the exact path from the gap
Step 3: For Corrupted Files
If gap kind is corrupted — the file exists but failed validation:
- Read the file first
- Fix the specific issue (wrong magic bytes, invalid syntax, missing structure)
- Do NOT delete and recreate unless the file is beyond repair
Step 4: Verify
- Verify each output:
test -f {path} && test -s {path} - If checks exist in
repair-context/checks.md, run them ALL
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