Skill

project-audit

Runs deterministic project health audit across 5 dimensions (OSS, robustness, scope, runnability, stability) with scores, status, findings for quality evaluation, onboarding, periodic checks.

code-quality

npx claudepluginhub sd0xdev/sd0x-dev-flow --plugin sd0x-dev-flow

Tool Access

This skill uses the workspace's default tool permissions.

Preview

- Security-specific review (use `/codex-security`)

Supporting Assets

references/check-catalog.mdreferences/output-template.mdscripts/audit.js

SKILL.md

Similar Skills

ai-readiness-audit

Orchestrates extensible code quality audits: discovers dimensions, builds DAG for phased parallel execution via subagents, each in isolated context window.

11 files

awos

phx:audit

180

Audits project health across architecture, performance, security, tests, and dependencies using 5 parallel subagents. Run quarterly, before releases, after refactors, or for onboarding.

2 files

elixir-phoenix

project-health-check

Conducts 7-point project health audit covering documentation, test coverage, security, code quality, dependencies, database schema/migrations, and build/CI-CD. Generates scored Markdown report with issues.

director-mode-lite

Stats

Stars147

Forks20

Last CommitMar 5, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Project Audit

When NOT to Use

Security-specific review (use /codex-security)
Runtime performance profiling
Mid-development review (use /codex-review-fast)

Procedure

Run bash scripts/run-skill.sh project-audit audit.js --json to collect deterministic scores
Parse the JSON output — overall_score, status, dimensions, checks, findings, next_actions
If status = Blocked (P0 findings) — highlight critical gaps, suggest immediate fixes
If status = Needs Work (P1 findings) — format improvement roadmap by dimension
If status = Healthy — summarize strengths, note any P2 improvements
Add qualitative interpretation beyond the scores (e.g., "test ratio is good but concentrated in unit tests")

Script Integration

The audit script runs 12 deterministic checks across 5 dimensions:

Dimension	Checks	What It Measures
oss	2	LICENSE, README quality
robustness	3	CI config, lint/typecheck, test ratio
scope	2	Declared features vs implementation, AC completion
runnability	3	Package manifest, scripts, env/Docker setup
stability	2	Lock file + audit, type configuration

Scoring Model

Each check: 1 (pass) / 0.5 (partial) / 0 (fail) / N/A (skipped)
Dimension score: applicable_sum / applicable_count * 100
Overall score: average of dimension scores
Confidence: applicable_checks / total_checks per dimension

Status Determination

Status	Condition	Exit Code
Blocked	Any P0 finding	2
Needs Work	No P0, has P1	1
Healthy	No P0/P1	0

Script Failure Fallback

If the script fails, report the error and suggest running manually:

bash scripts/run-skill.sh project-audit audit.js --json

Output Format

## Project Audit Report

| Field | Value |
|-------|-------|
| Repo | [name] |
| Score | **[N]/100** |
| Status | [icon] [status] |

### Dimensions
[table of dimension scores]

### Checks
[list of check results with suggestions]

### Next Actions
[prioritized action items]

## Gate: ✅/⛔

References

references/check-catalog.md — Check definitions, scoring criteria, ecosystem detection (read when investigating a specific check result)
references/output-template.md — Report format examples and JSON schema (read when customizing output)

Verification

Script ran successfully
All 12 checks executed (or marked N/A with reason)
Qualitative interpretation added beyond raw scores
Next actions are actionable (include commands where applicable)