AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Quality Scan

Runs a scoped, read-only quality gate scan and reports execution evidence, failures, and frozen debt without touching product code.

Dev & CodingAdvanced★ 85,858⑂ 13,013AI score 7/10Last updated: Nov 9, 2026

What it does

  • Forces an explicit scope decision first: default static profile, quality-scan-fast, a named npm alias, or remote base-health evidence.
  • Measures the real gate inventory from config/quality/gate-manifest.json and package.json (via --list and check:gate-manifest) instead of trusting remembered counts.
  • Pins base and candidate SHAs in an isolated worktree, runs the actual npm entrypoints, and records command, cwd, runtime versions, timings, exit/signal, and log paths.
  • Treats missing dependencies, timeouts, cancellations, and unavailable artifacts as incomplete evidence — never as PASS.
  • Separates frozen debt from new findings, and stops after reporting: fixes and baseline changes need their own change request.

Who it's for

  • Release and platform engineers running pre-release gate sweeps.
  • Monorepo maintainers whose quality gates are wrapped as npm scripts.
  • Teams that want every "it passed" claim backed by raw logs and exit codes.

Example uses

  1. "Run the full quality-scan profile for release prep" — pins SHAs, executes the scan, and reports executed/failed/not-run counts plus log paths.
  2. "Just do a fast check with quality-scan-fast" — runs the fast profile while explicitly listing the gates it skipped.
  3. "Was main already red before this PR?" — inspects remote evidence rather than implying a local suite, then applies the shared base-green causal comparison.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/cheaper-inference/OmniRoute/HEAD/config/quality/skill-templates/quality-scan/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the config/quality/skill-templates/quality-scan folder from the GitHub repo cheaper-inference/OmniRoute into my ~/.claude/skills/quality-scan/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/cheaper-inference/OmniRoute /tmp/omniroute && mkdir -p ~/.claude/skills && cp -r /tmp/omniroute/config/quality/skill-templates/quality-scan ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/cheaper-inference/OmniRoute /tmp/omniroute
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r /tmp/omniroute/config/quality/skill-templates/quality-scan ~/.claude/skills/
  5. It references ../_shared/base-green.md and ../validate-release-green/SKILL.md, so copy those too: cp -r /tmp/omniroute/config/quality/skill-templates/_shared /tmp/omniroute/config/quality/skill-templates/validate-release-green ~/.claude/skills/ 2>/dev/null
  6. Restart Claude Code and ask it to "run a quality gate scan".
  7. If your project has no npm run quality:scan script, substitute the actual script names from your own package.json.
View source on GitHub ↗License: MIT