maicongambini/omp-harness-guide/harness-quality-snapshot

Claude Code and agent skill by maicongambini/omp-harness-guide

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Create a milestone quality scorecard with evidence. Use for release, capstone, or major sprint review; not for every small task.

Install

npx vskill@latest install maicongambini/omp-harness-guide/harness-quality-snapshot

SKILL.md

The same SKILL.md was published earlier as maicongambini/omp-harness-guide/harness-quality-snapshot.

Harness Quality Snapshot

Track project health over time with evidence.

Artifact

Preferred file: docs/harness/quality-document.md.

Create or update only after approval.

Relationship to harness-quality-gate

The gate is per-change and binary; this snapshot is per-milestone and qualitative. They are not two scorecards competing — the gate produces the numbers, the snapshot interprets the trend.

So the measured dimensions below cite the latest gate report rather than re-running anything. Do not re-derive coverage, mutation, complexity, module size, boundaries or security findings by inspection; read docs/harness/quality/*.json and quote it. What this skill adds is the part no single run shows: direction over time, and which risk is worth acting on next.

Dimensions

DimensionEvidence
Build healthstartup/build command output, plus the gate's verdict
Feature completenessfeature state and AC evidence
Test strengthgate report: mutation_kill_ratio (the real number) with line_coverage as the floor
Regression healthgate report: regression_suite — failing plus quarantined
Documentationroot instructions, context docs, handoff
Harness qualitystartup, WIP, Judge, state, handoff
Architecture boundariesgate report: boundary_violations, plus documented boundaries
Measurement coveragehow many metrics are unavailable — a gate measuring three of nine rows is the risk, not the reassurance
Cleanup priorityscanner findings

Output

markdown
## Quality Snapshot
Date: ...
Overall score: .../10
Evidence table: ...
Top risks: ...
Next improvement: ...

Rules

  • Use actual command output or file evidence.
  • Mark unknowns as unknown.
  • Do not inflate score when verification is missing.
  • Intended for milestones, not every small task.
  • Cite the gate report for every measured dimension; never restate a threshold.
  • An unavailable metric lowers confidence in the whole snapshot — say so instead of scoring

around it.

  • Trend beats level: "mutation 62% → 69% over four milestones" is worth more than any single 7/10.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/maicongambini/omp-harness-guide/harness-quality-snapshot/badge)](https://verified-skill.com/skills/maicongambini/omp-harness-guide/harness-quality-snapshot)

Something wrong with this skill or its page? Tell us.