Agent Skills › poteto/noodle › quality

quality

GitHub

代码质量门禁技能,审查已完成工作的正确性、范围纪律及原则合规性。通过检查范围、代码规范、测试证据等触发评审,并输出评估结果以决定流水线是否继续。

.agents/skills/quality/SKILL.md poteto/noodle

Trigger Scenarios

执行阶段完成后 /quality review this check the work assess quality

Install

npx skills add poteto/noodle --skill quality -g -y
More Options

Non-standard path

npx skills add https://github.com/poteto/noodle/tree/main/.agents/skills/quality -g -y

Use without installing

npx skills use poteto/noodle@quality

指定 Agent (Claude Code)

npx skills add poteto/noodle --skill quality -a claude-code -g -y

安装 repo 全部 skill

npx skills add poteto/noodle --all -g -y

预览 repo 内 skill

npx skills add poteto/noodle --list

SKILL.md

Frontmatter
{
    "name": "quality",
    "schedule": "Follow-up stage after execute. Cross-provider review preferred — if codex executed, schedule quality on claude; if claude executed, schedule on codex.",
    "description": "Post-cook quality gate. Reviews completed cook work for correctness, scope discipline, and principle compliance. Emits stage_message events with findings. Triggers after execute stages, on '\/quality', 'review this', 'check the work', 'assess quality'."
}

Quality

Review completed cook work. Emit a stage_message event with your assessment. See references/stage-message-schema.md for the event schema.

Operate fully autonomously. Never ask the user.

Step 0 -- Load Principles

Read brain/principles.md and follow every [[wikilink]]. These govern the review. Do NOT skip this.

Assessment Pipeline

Run in order. Stop early and reject on any high-severity finding.

1. Scope Check

  • Read the plan phase the cook was assigned (from the cook's initial prompt or mise context).
  • Run git diff --stat and git log --oneline for the cook's commits.
  • Flag files changed outside the plan phase's stated scope as scope violations.

2. Code Quality

  • go vet ./... and go test ./... must pass.
  • Run sh scripts/lint-arch.sh if it exists.
  • Check error handling follows project conventions (failure-state messages, not expectation messages).

3. Principle Compliance

  • For each changed file, check against loaded principles.
  • Common violations: bolted-on changes instead of redesign (redesign-from-first-principles), missing verification (prove-it-works), unnecessarily added complexity (subtract-before-you-add).

4. Test Evidence

  • New behavior must have new tests.
  • Tests must assert outcomes, not implementation details.
  • Check coverage of edge cases mentioned in the plan phase.

5. Runtime Verification

  • If the plan phase specifies runtime checks, verify they were performed.
  • "It compiles" is not verification.

Verdict

Emit a stage_message event with your assessment:

noodle event emit --session $NOODLE_SESSION_ID stage_message --payload '<json>'

Accept: Emit with blocking: false. The pipeline continues and the scheduler sees the green light.

{ "message": "All checks pass. Tests green, scope clean.", "blocking": false }

Reject: Emit with blocking: true (or omit blocking). The scheduler reads findings and decides (retry, add oops stage, or abort).

{ "message": "Rejected: 3 high issues. [1] Missing test for edge case in handleCompletion. [2] Scope violation: modified cook_merge.go outside plan phase scope. [3] Error message uses expectation form.", "blocking": true }

Write the message as natural language the scheduler can act on. Include specific file paths, line context, and principle violations so the scheduler can brief the retry cook.

Non-blocking Issues

Issues that don't warrant rejection (style nits, minor improvements, documentation gaps): file as backlog items via the backlog adapter.

Principles

  • [[prove-it-works]]
  • [[outcome-oriented-execution]]

Version History

  • 82d2921 Current 2026-11-19 21:08

Same Skill Collection

.agents/skills/adversarial-review/SKILL.md
.agents/skills/ast-grep/SKILL.md
.agents/skills/brain/SKILL.md
.agents/skills/codex/SKILL.md
.agents/skills/commit/SKILL.md
.agents/skills/debugging/SKILL.md
.agents/skills/execute/SKILL.md
.agents/skills/find-skills/SKILL.md
.agents/skills/frontend-design/SKILL.md
.agents/skills/go-best-practices/SKILL.md
.agents/skills/interaction-design/SKILL.md
.agents/skills/make-interfaces-feel-better/SKILL.md
.agents/skills/meditate/SKILL.md
.agents/skills/noodle/SKILL.md
.agents/skills/oops/SKILL.md
.agents/skills/plan/SKILL.md
.agents/skills/react-best-practices/SKILL.md
.agents/skills/refine/SKILL.md
.agents/skills/reflect/SKILL.md
.agents/skills/review/SKILL.md
.agents/skills/ruminate/SKILL.md
.agents/skills/schedule/SKILL.md
.agents/skills/skill-creator/SKILL.md
.agents/skills/testing/SKILL.md
.agents/skills/todo/SKILL.md
.agents/skills/unslop/SKILL.md
.agents/skills/worktree/SKILL.md
examples/minimal/.agents/skills/execute/SKILL.md
examples/minimal/.agents/skills/schedule/SKILL.md
examples/multi-skill/.agents/skills/execute/SKILL.md
examples/multi-skill/.agents/skills/schedule/SKILL.md
skills/skill-creator/SKILL.md
.agents/skills/ts-best-practices/SKILL.md
examples/multi-skill/.agents/skills/deploy/SKILL.md
examples/multi-skill/.agents/skills/test/SKILL.md

Metadata

Files
0
Version
82d2921
Hash
89af8637
Indexed
2026-11-19 21:08

홈 - 위키
Copyright © 2011-2026 iteam. Current version is 2.156.0. UTC+08:00, 2026-11-19 22:13
浙ICP备14020137号-1