
Quality
- 37 installs
- 217 repo stars
- Updated March 19, 2026
- poteto/noodle
quality is a Claude Code skill for ai & agent building.
About
quality is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.
- quality
- AI & Agent Building
- AI-coding skill
Quality by the numbers
- 37 all-time installs (skills.sh)
- Ranked #8,545 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/poteto/noodle --skill qualityAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 37 |
|---|---|
| repo stars | ★ 217 |
| Last updated | March 19, 2026 |
| Repository | poteto/noodle ↗ |
How do I helps with ai & agent building tasks.?
Helps with ai & agent building tasks.
Who is it for?
Best when you're working on ai & agent building and need structured help with quality.
Skip if: Teams with no ai & agent building needs, or anyone wanting a generic chat assistant without this specific workflow.
When should I use this skill?
When you need to helps with ai & agent building tasks., or when quality is a claude code skill for ai & agent building.
What you get
Structured output aligned to quality: quality, AI & Agent Building.
Files
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 --statandgit log --onelinefor the cook's commits. - Flag files changed outside the plan phase's stated scope as scope violations.
2. Code Quality
go vet ./...andgo test ./...must pass.- Run
sh scripts/lint-arch.shif 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]]
Stage Message Schema
Emitted by agents via noodle event emit --session $NOODLE_SESSION_ID stage_message --payload '<json>'.
{
"message": "string — content for the scheduler, natural language",
"blocking": "boolean — if true, scheduler must decide before stage advances. Omit or null = true"
}Blocking Behavior
- `blocking: true` (or omitted) — loop forwards message to scheduler, does NOT auto-advance. Scheduler must issue a control command (advance, add stage, etc.) before the pipeline continues.
- `blocking: false` — loop auto-advances AND forwards the message to the scheduler for information. The scheduler sees it but doesn't need to act.
Examples
Quality accept:
{ "message": "All checks pass. Tests green, scope clean.", "blocking": false }Quality reject:
{ "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 }Execute complete:
{ "message": "Implementation complete. 3 files changed, 2 new tests added. Ready for review.", "blocking": true }Related skills
FAQ
What does quality do?
quality is a Claude Code skill for ai & agent building.
When should I use quality?
When you need to helps with ai & agent building tasks., or when quality is a claude code skill for ai & agent building.
What are the main capabilities?
quality; AI & Agent Building; AI-coding skill.