project-audit
Skill1 starsChanged 45 days agoMITView on GitHub
Use this skill when asked to audit, assess, or health-check an existing software project or codebase - "audit project ini", "kondisi codebase gimana", "layak dilanjut/diambil alih?", due diligence on inherited code, "kenapa project ini lambat terus", or producing a findings report with priorities. Produces a scored, evidence-based audit report. Do NOT use for reviewing a single diff/PR (code-review-hardening) or a live incident (incident-debugging).
15 other projects use a version of this.
Adopted by
Most recently taken up by
- blamechris/chroxytheir own version, first seen Nov 8, 2026
- AhmedAbdelfattah0/AI-Skillstheir own version, first seen Nov 4, 2026
- grooownow/qa-pilottheir own version, first seen Nov 1, 2026
- hmj1026/dhpktheir own version, first seen Nov 1, 2026
- Kin9Zeus/senior-engineer-skillstheir own version, first seen Nov 1, 2026
- Khaymah/sabry-claude-kittheir own version, first seen Nov 1, 2026
Used with
Projects with it also use merge-prep, repo-intake and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
sd0xdevSkillmerge-prep
Pre-merge analysis and preparation. Analyzes source branch vs target branch: commit stats, conflict detection, file impact. Analysis-only v1 — outputs report + suggested commands, does not auto-merge. Use when: user says 'merge prep', 'pre-merge', 'merge analysis', or /merge-prep
Also in 3 projects that use this
AuroraBackcountrySkillrepo-intake
Get a picked-up repo ready to work in. Unfamiliar repo: ask intent, map it by reading, write the canonical AGENTS.md, wire the vault, propose a first task. Already-documented repo with no vault space: wire-only — connect it and leave the docs alone. Use when picking up a codebase: "onboard me", "get me set up on this repo", "I cloned/forked this", "map this repo", "wire this into the vault" — or proactively when a repo has no AGENTS.md/CLAUDE.md and real work starts. Check ownership first: on a repo the user doesn't own, intake is vault-first and writes nothing into tracked files. NOT memory refresh (that's memory-checkpoint) or greenfield scaffolding (/scaffold); documented AND wired = nothing to do.
Also in 3 projects that use this
sd0xdevSkillissue-analyze
GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + verdict assessment + investigation strategy.
Also in 3 projects that use this
apacheSkillprecommit
Validate and fix Pinot pre-commit checks on affected modules before a commit or PR.
Also in 3 projects that use this
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- sd0xdev/sd0x-dev-flow★ 192same name
- sd0xdev/sd0x-harness★ 192same name
- danmaps/gis-agent-skills★ 30same name
- NeuralTrust/TrustGate★ 17same name
- blamechris/chroxy★ 8same name
- grooownow/qa-pilot★ 6same name
- AhmedAbdelfattah0/AI-Skills★ 4same name
- Kin9Zeus/senior-engineer-skills★ 3same name
- hmj1026/dhpk★ 2same name
- DentalEdge-Solutions/claude_code★ 1same name
5 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accounting-coreSkill
- admin-opsSkill
- agent-skill-authorSkill
- code-review-hardeningSkill
- content-creatorSkill
- content-editorSkill
- continuous-learningSkill
- coo-orchestratorSkill
- finance-analystSkill
- hr-adminSkill
- hr-officerSkill
- incident-debuggingSkill
- marketing-growthSkill
- prd-creatorSkill
- principal-engineeringSkill
- product-designerSkill
- project-timeline-creatorSkill
- sales-pipelineSkill
- sdlc-masterSkill
- secure-deploy-opsSkill
- social-media-specialistSkill
- strategic-approachSkill
- tech-scoutSkill
- uiux-engineerSkill
The file
Files
Project Audit
An audit is evidence + score + prioritized fixes - never impressions. Every finding cites a file/config/commit; every recommendation has effort and impact.
Audit dimensions (score each 1-5, with written evidence)
1. Arsitektur & kode Struktur modul jelas dan konsisten? Dependency antar modul searah atau spaghetti? Duplikasi besar (cek dengan grep pola berulang)? Dead code? Ukuran file/fungsi ekstrem? Framework/library versi berapa jauh di belakang?
2. Keamanan (pakai lensa code-review-hardening pada skala repo)
Secrets di repo/history (git log -p | grep -i untuk key/password/token)? Auth di setiap endpoint sensitif? Input validation di boundary? Dependency dengan CVE dikenal? Konfigurasi produksi (CORS, debug mode, verbose errors)?
3. Data & migrasi Skema terdokumentasi? Migrasi versioned dan reversible? Backup ada, off-box, dan pernah di-restore? Data sensitif terenkripsi/di-mask di log?
4. Testing & CI Coverage alur kritis (bukan angka % global - cek spesifik: auth, pembayaran, data-write utama). CI jalan dan hijau? Berapa lama? Tes flaky? Bisakah orang baru menjalankan tes secara lokal dalam < 30 menit?
5. Operasional Deploy: berapa langkah manual? Rollback pernah dicoba? Logging cukup untuk debug insiden nyata? Monitoring/alerting ada? Single point of failure (satu server, satu orang, satu cron)?
6. Deliverability (kesehatan proses) Dari git history: frekuensi commit/merge, ukuran PR, berapa lama PR menggantung, bus factor (berapa % commit dari 1 orang), TODO/FIXME yang membusuk, issue tracker vs realita kode.
7. Dokumentasi & onboarding README bisa membuat orang baru menjalankan project? Keputusan arsitektur tercatat? Runbook operasional ada?
Method (in order - don't skip the cheap steps)
- Recon: baca README, struktur folder, file konfigurasi, CI config, dependency manifest. 30 menit ini membentuk peta.
- Git archaeology:
git log --stat, kontributor, hotspot file (file yang paling sering diubah = pusat risiko), umur branch. - Automated sweep: dependency audit, grep secrets, hitung LOC/duplikasi, jalankan tes.
- Deep dive hanya pada 3-5 area yang recon tunjuk sebagai berisiko - bukan seluruh repo merata.
- Verify findings: tiap temuan besar dicek ulang di kode aslinya sebelum masuk laporan.
Report format
# Audit <project> - <tanggal>
## Ringkasan eksekutif (≤ 5 kalimat: kondisi umum, risiko terbesar, rekomendasi utama)
## Skor per dimensi (tabel 1-5 + satu kalimat bukti per dimensi)
## Temuan (urut prioritas)
[P1-BLOCKER|P2-HIGH|P3-MEDIUM|P4-LOW] <judul>
Bukti: <file:line / commit / output perintah>
Dampak: <apa yang rusak/berisiko, dalam istilah bisnis bila mungkin>
Rekomendasi: <aksi konkret> | Effort: S/M/L
## Roadmap perbaikan: batch 1 (blocker), batch 2 (high), debt register sisanya
## Yang SUDAH baik (wajib - kalibrasi kepercayaan laporan)Verdict scale (for "layak dilanjut?" questions)
Sehat (lanjut normal) · Perlu perawatan (alokasikan 20-30% kapasitas ke perbaikan) · Kritis (hentikan fitur baru, stabilisasi dulu) · Jangan diambil alih / tulis ulang bertahap - sertakan estimasi biaya tiap jalur. Jangan pernah memberi verdict tanpa menyebut apa yang akan mengubahnya.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

