菜单
Validate task implementations by running the project's test suite, linters, and CI checks. Discovers test commands from common project patterns (package.json, Makefile, pytest, cargo, go) and reports pass/fail with details. Use after a sub-agent completes a task.
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
Validate that a pull request follows principled conventions: references a plan or proposal, has correct labels, includes required sections in the description, and links to relevant documents. Use in CI or before merging to enforce PR quality.
Generate a structured pull request description from a DDD plan task. Reads the plan, task manifest, and implementation branch to produce a PR body with references to the originating proposal, plan, ADRs, and related tasks. Use when opening a PR for plan-driven work.
Process open GitHub issues through the principled pipeline. Lists untriaged issues, normalizes their metadata, ingests them into the documentation pipeline, and reports a summary. Operates as the batch entry point — delegates to /ingest-issue for each individual issue.
Implementation orchestration strategy for the Principled framework. Consult when working with DDD plan execution, git worktrees for task isolation, task manifests, or the decompose-spawn-validate-merge lifecycle. Covers worktree management, sub-agent patterns, task state machines, and manifest schema.
Top-level orchestrator for DDD plan execution. Decomposes a plan into tasks, iterates through phases respecting dependencies, spawns worktree-isolated agents, validates implementations, and merges results. Runs inline to coordinate multiple sub-agent spawns. Use for automated end-to-end plan execution.
Audit ADR coverage across modules. Identifies modules with no architectural governance, orphaned ADRs referencing removed modules, and stale architecture docs. Classifies findings by severity.
| name | check-impl |
| description | Validate task implementations by running the project's test suite, linters, and CI checks. Discovers test commands from common project patterns (package.json, Makefile, pytest, cargo, go) and reports pass/fail with details. Use after a sub-agent completes a task. |
| allowed-tools | Read, Bash(npm *), Bash(npx *), Bash(make *), Bash(bash *), Bash(git *), Bash(ls *), Bash(grep *), Bash(find *) |
| user-invocable | true |
Run the project's test suite and checks against a task's implementation to verify correctness.
/check-impl [--task <task-id>] [--all]
| Argument | Required | Description |
|---|---|---|
--task <id> | Yes (unless --all) | Specific task to validate |
--all | No | Validate all tasks with status validating |
Parse arguments. Determine target task(s) from $ARGUMENTS.
Identify worktree path(s). For each target task:
bash scripts/task-manifest.sh --get-task --task-id <id>git worktree list matching the branch nameDiscover check commands. Run:
bash scripts/run-checks.sh --discover --cwd <worktree-path>
Reports which checks were discovered and their sources. See reference/check-discovery.md for supported project types.
Run checks. For each task, within its worktree:
bash scripts/run-checks.sh --execute --cwd <worktree-path>
Runs each discovered check and captures exit code + output.
Update manifest. Run:
bash scripts/task-manifest.sh --update-status \
--task-id <task-id> \
--status passed|failed \
--check-results "<summary>"
Report results. For each task:
/merge-work <task-id> to merge."/spawn <task-id> to retry, or address manually in the worktree."scripts/run-checks.sh — Check discovery and execution (canonical copy)scripts/task-manifest.sh — Task manifest CRUD (copy from decompose)reference/check-discovery.md — How check commands are discovered from various project types