Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tonours-code-quality
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/code-quality
What's inside
- Skill name
code-quality- Description
- Runs the bounded convention and stack-quality pass on a diff. Use after implementation or during review; not for feature work or deep refactors.
- License
- MIT
- Instructions
- 61 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Code Quality Thin orchestrator for **convention + pattern fit** on a bounded change. It does not invent style rules. It loads the skill that already owns the practice and compares the diff to **sibling implementations in this repo**. ## When to run - After the simplification pass in `implementation-loop` - During `review` when the diff touches language or UI surface - Explicit user request for quality, conventions, patterns, or best practices - React convention pass on a bounded diff ## Procedure 1. **Bound the target** — current uncommitted diff, named paths, or PR diff. Never whole-repo audit unless asked. 2. **Detect domain** — match signals from the diff directly. This skill does not depend on another router or suite. 3. **Load practice skills** for the matched domain only: | Domain | Skills to apply | | -------- | ----------------- | | TypeScript / implementation | `codebase-design` on Claude; on Pi, 1–3 local siblings (step 4) | | CSS / layout / visual | Local sibling components and styles; apply a narrower CSS skill only when the runtime exposes one | | Project-specific code | Prefer the matching project skill when the runtime exposes one | 4. **Compare to local convention** — open 1–3 sibling files that already implement the same kind of change. The pattern to match is what the repo does, not a generic blog post. If a named practice skill is unavailable, continue with these siblings. If no relevant sibling exists either, report `quality: unavailable` and stop; do not call the pass clean. 5. **Classify findings**: - **Mechanical** — clear, local, no behavior change (import order already enforced by lint, missing `type` import, dead branch introduced by this diff, obvious composition smell with a sibling pattern). Fix directly when running inside implement. - **Behavioral** — would change runtime behavior or API. Report only; do not fix in a pure review. 6. **Evidence bar** — a finding ships only with: - changed `file:line` in the target diff - the **sibling pattern** `file:line` being violated (or the skill rule name when no sibling exists) - concrete impact (correctness, operability, or consistency that blocks maintenance) Abstract “best practice” opinions without a local anchor are discarded. 7. **Report** one line per pass run: ```text quality: <domains> | mechanical fixed: N | findings: N | status: clean|findings|unavailable ``` ## Rules - Prefer the narrowest exposed skill. - No style nits that the project's linter or formatter already owns unless the tool is broken on this diff. - Do not widen scope to unrelated files. - Quality pass does not replace correctness review or tests. - If the diff has no language/UI convention surface, say `quality: none` and stop. ## Related - `workflow/review-rubric.md` § Convention & pattern fit - `workflow/skills/implementation-loop.md` quality pass
From Tonours/etabli, MIT.
More from Tonours/etabli
- 0.570score
react-doctor-100
Tonours
Runs react-doctor on React codebases and iteratively fixes diagnosed issues until the project reaches a verified score of 100 without shortcuts.
SkillAFreshness: AClaude Code +9 - 0.570score
adr
Tonours
Records a lightweight Architecture Decision Record for a decision made in this session.
SkillAFreshness: AClaude Code +9 - 0.567score
employer-docs-writing
Tonours
Writes or rewrites pages for the employer Mintlify documentation (~/work/docs) in the corpus voice.
SkillAFreshness: AClaude Code +9 - 0.565score
thermo-nuclear-code-quality-review
Tonours
Runs an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth.
SkillAFreshness: AClaude Code +9 - 0.561score
write-direct
Tonours
Writes or rewrites internal docs and messages in Anthony's direct, informal voice (French by default).
SkillAFreshness: AClaude Code +9 - 0.561score
coolify
Tonours
Manages Coolify Cloud via its official CLI (servers, apps, databases, deployments, logs, env, backups).
SkillAFreshness: AClaude Code +9 - 0.561score
spec
Tonours
Writes or revises employer specs, technical Epics and design docs from the bundled templates.
SkillAFreshness: AClaude Code +9 - 0.560score
pr-council-review
Tonours
Runs a three-pass review of one PR (code-review + thermo-nuclear, then forest:validator as the council), dry-run by default.
SkillAFreshness: AClaude Code +9 - 0.560score
adversary
Tonours
Red-teams a PLAN.md, diff or design as a hostile challenger.
SkillAFreshness: AClaude Code +9 - 0.560score
implement
Tonours
Implements an existing READY PLAN.md without replanning.
SkillAFreshness: AClaude Code +9 - 0.557score
plan-implement
Tonours
Plans, then implements the same task in one run once PLAN.md is READY.
SkillAFreshness: AClaude Code +9 - 0.556score
employer-backend-suite
Tonours
Routes employer server, agent-nodejs, BFF, MCP, OAuth/JWT, permissions v4, workflow execution and Zendesk work to existing KB notes.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (6 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Tonours/etabli
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Tonours
- 0.570score
react-doctor-100
Tonours
Runs react-doctor on React codebases and iteratively fixes diagnosed issues until the project reaches a verified score of 100 without shortcuts.
SkillAFreshness: AClaude Code +9 - 0.570score
adr
Tonours
Records a lightweight Architecture Decision Record for a decision made in this session.
SkillAFreshness: AClaude Code +9 - 0.567score
employer-docs-writing
Tonours
Writes or rewrites pages for the employer Mintlify documentation (~/work/docs) in the corpus voice.
SkillAFreshness: AClaude Code +9 - 0.565score
thermo-nuclear-code-quality-review
Tonours
Runs an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth.
SkillAFreshness: AClaude Code +9 - 0.561score
coolify
Tonours
Manages Coolify Cloud via its official CLI (servers, apps, databases, deployments, logs, env, backups).
SkillAFreshness: AClaude Code +9 - 0.561score
spec
Tonours
Writes or revises employer specs, technical Epics and design docs from the bundled templates.
SkillAFreshness: AClaude Code +9
Cite this page
code-quality skill. Agent Mart. https://agentmart.dev/skills/tonours-code-quality (last updated 2026-10-24)