Quality Loop

Drive a project hardening + full quality-sweep loop in an isolated worktree. Use when the user wants to harden/improve a project autonomously — security, prod-readiness, deps/CVEs, tests/coverage, dead-code, perf, a11y, ux, docs — with self-verification before anything merges to main, and clean queueing of anything that needs the operator. Trigger: /quality-loop. Runs standalone (auto-pushes verified batches) or staged under an orchestrator like /battle-test (--staged: commit only, parent controls the push). Claude-only (no codex/auto-harness); runs locally.

41 stars 1 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add wolverin0/claude-skills --skill quality-loop
Manual install
git clone --depth 1 https://github.com/wolverin0/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/quality-loop ~/.claude/skills/quality-loop

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# quality-loop

Run THIS project through a hardening + quality sweep as a **self-verifying loop in an isolated git
worktree**. You work the AUTO list, prove every change before it can reach `main`, and queue
anything that needs a human. Minimal diffs. No rewrites. No scope creep.

```
/quality-loop                      # standalone: audit if needed, fix, verify, AUTO-PUSH green batches to main
/quality-loop ../crm               # a specific project path
/quality-loop --staged             # orchestrated: commit to loop branch, DO NOT push (parent pushes after its gate)
/quality-loop --from-tracks        # never run /audit; work the existing pre-seeded TRACKS.md as-is
```
`--no-push` is an alias for `--staged`. Default (no flag) = standalone auto-push.

Optional loop scaffold files: `.loop/DRIVER.md`, `TRACKS.md`, `KICK.md`.

## 0. Setup (isolated, from deployed main)
**If the parent orchestrator hands you a worktree and base, use them.** Skip this step except branch
creation: work in that tree and create `loop/<project>` at the base SHA inside it
(`git switch -c loop/<project> <base>`; on resume, switch to the existing branch). Do not fetch,
do not branch from `origin/main`, and do not remove the tree: the parent still needs it for its own
re-verification and removes it.
Read the full skill on GitHub

Details

Skill name
quality-loop
Path
skills/quality-loop/SKILL.md
Repo updated
17 November 2026

FAQ

What does the Quality Loop skill do?

Drive a project hardening + full quality-sweep loop in an isolated worktree. Use when the user wants to harden/improve a project autonomously — security, prod-readiness, deps/CVEs, tests/coverage, dead-code, perf, a11y, ux, docs — with self-verification before anything merges to main, and clean queueing of anything that needs the operator. Trigger: /quality-loop. Runs standalone (auto-pushes verified batches) or staged under an orchestrator like /battle-test (--staged: commit only, parent controls the push). Claude-only (no codex/auto-harness); runs locally.

How do I install the Quality Loop skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add wolverin0/claude-skills --skill quality-loop. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Quality Loop popular?

It lives in wolverin0/claude-skills, which has 41 GitHub stars and 1 forks.

Related skills

UI UX Pro Max

41

wolverin0/claude-skills

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism,

Frontend & Design

Audit Blind Spots

41

wolverin0/claude-skills

Walk the B1-B19 AI-to-AI blind-spot catalog systematically. Use during the audit pipeline AFTER hard-stops and Tambon hunt and BEFORE the 13 domain audits. Output: PRESENT / NOT PRESENT for each B-class with evidence. Findings flow into the appropriate domains.

AI, LLMs & Agents

Audit Decisions

41

wolverin0/claude-skills

Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.

Marketing, Sales & Business

Security Audit Codebase

45

pjt222/agent-almanac

Perform a security audit of a codebase checking for exposed secrets, vulnerable dependencies, injection vulnerabilities, insecure configurations, and OWASP Top 10 issues. Use before publishing or deploying a project, for periodic security reviews, after adding authentication or API integration, before open-sourcing a private repository, or when preparing for a security compliance audit.

SecurityIn 1 list

Navigate Dach Bureaucracy

45

pjt222/agent-almanac

Step-by-step guidance for DACH-specific governmental procedures including Anmeldung, Finanzamt registration, health insurance enrollment, and social security coordination. Use after arriving in a DACH country and needing to complete mandatory registrations, before a specific appointment to understand what to expect, when an initial registration attempt was rejected, when transitioning between DACH countries, or when handling registrations for dependents alongside your own.

SecurityIn 1 list

Security Review

41

wolverin0/claude-skills

Review security-sensitive code changes involving auth, user input, secrets, APIs, payments, files, RLS, or third-party integrations.

Security

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.