code-audit
Skill0 starsChanged 5 months agoMITView on GitHub
Otonom codebase audit — kesif, tespit, raporlama. Tum projeyi tarar.
30 other projects use a version of this.
Adopted by
Most recently taken up by
- miinhho/skillstheir own version, first seen Nov 16, 2026
- antick/skillstheir own version, first seen Nov 16, 2026
- smarzban/agent-skillstheir own version, first seen Nov 15, 2026
- zhaoxuya520/reverse-skilltheir own version, first seen Nov 14, 2026
- arcasilesgroup/ai-engineeringtheir own version, first seen Nov 8, 2026
- pietz/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use database-security, malware-analysis and 7 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.
JeremyMorganSkilldatabase-security
Examines all database interactions for injection, access control, encryption, and data-exposure risks. Use when auditing database and data-layer security.
Also in 3 projects that use this
tsaleSkillmalware-analysis
Professional malware analysis workflow for PE executables and suspicious files. Triggers on file uploads with requests like "analyze this malware", "analyze this sample", "what does this executable do", "check this file for malware", or any request to examine suspicious files. Performs static analysis, threat intelligence triage, behavioral inference, and produces analyst-grade reports with reasoned conclusions.
Also in 3 projects that use this
jefflesterSkillapi-security
API security best practices and common vulnerability prevention. Enforces security checks for authentication, input validation, SQL injection, XSS, and OWASP Top 10 vulnerabilities. Use when building or modifying APIs.
Also in 3 projects that use this
QiuChenlySkillreverse-engineering
专业二进制逆向工程分析技能。使用IDA Pro MCP工具分析二进制文件、反编译代码、识别漏洞、理解程序逻辑。当用户要求分析可执行文件、反汇编、逆向工程、漏洞挖掘、恶意软件分析时使用此技能。
Also in 3 projects that use this
SentrySkillui-design
Also in 3 projects that use this
GitHubSkillrefactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Also in 3 projects that use this
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 30
- zhaoxuya520/reverse-skill-private★ 45ksame name
- zhaoxuya520/reverse-skill★ 45ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
- pass-with-high-score/blockads-android★ 2.7ksame name
- 3stoneBrother/code-audit★ 893same name
- aspi6246/Claude-Code-Skills-for-Academics★ 153same name
- arcasilesgroup/ai-engineering★ 65same name
- hawkyre/hawk-skills★ 30same name
- greglas75/zuvo★ 7same name
20 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 repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- proje/CLAUDE.mdCLAUDE.md
- adr-writerSkill
- brainstormingSkill
- brainstormSkill
- commitSkill
- create-prSkill
- governance-evalSkill
- governance-kurSkill
- migration-checklistSkill
- security-scanSkill
- stack-loaderSkill
- systematic-debuggingSkill
- tddSkill
- test-scaffoldSkill
- yeni-projeSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Test dosyalarinin konumu ve sayisi
“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Codebase Audit
Tum codebase'i sistematik olarak tara, sorunlari tespit et, rapor olustur. Bu skill quality-gate'ten FARKLIDIR: quality-gate gorev bazli (degisen dosyalar), code-audit proje bazli (tum codebase).
Ne Zaman Kullanilir
- Projeye ilk giristte genel saglik kontrolu
- Sprint sonu / milestone oncesi review
- Buyuk refactor oncesi durum tespiti
- Periyodik bakim (aylik/sprint bazli)
Faz 1: Kesif (Yapi Haritasi)
- Proje kok dizinini tara:
- Klasor yapisi (Controller, Service, Repository, Model, DTO, Middleware)
- Dosya sayilari ve buyuklukleri
- Stack tespiti (csproj, package.json, composer.json)
- Test dosyalarinin konumu ve sayisi
- Giris noktalarini belirle:
- API endpoint'leri (controller/route dosyalari)
- Middleware pipeline
- DI/IoC kayitlari
- Migration dosyalari
- Yapi haritasi ozeti olustur:
src/ Controllers/ (X dosya) Services/ (X dosya) Models/ (X dosya) ... tests/ (X dosya, coverage: ?)
Faz 2: Tespit (Sorun Tarama)
Asagidaki kategorilerde sistematik tarama yap. Her kategori icin grep pattern'leri ve dosya okuma kullan.
2A: Guvenlik (bkz. .claude/rules/guvenlik.md)
- Hardcoded secret/password/API key
- SQL/NoSQL injection riski (raw query + string concatenation)
- IDOR potansiyeli (kullanici ID dogrudan parametre)
- Hassas veri response'da (password, token, hash alanlari)
- CORS wildcard (
*) kullanimi - Rate limiting eksikligi
Grep pattern'leri:
- password|secret|api.?key|token.*=.*["']
- raw.*query|exec.*sql|string.*format.*select
- cors.*origin.*\*2B: Performans (bkz. .claude/rules/kalite.md Madde 6)
- N+1 sorgu potansiyeli (dongu icinde DB cagrisi)
- SELECT * kullanimi
- Pagination eksikligi (liste endpoint'leri)
- Index eksikligi (sik sorgulanan alanlar)
- Gereksiz eager loading veya eksik include
2C: Kod Kalitesi (bkz. .claude/rules/kalite.md Madde 9)
- Controller'da is mantigi (Controller → Service katmanlasma ihlali)
- Kullanilmayan import/using/require
- Tekrar eden kod bloklari (copy-paste)
- Cok buyuk dosyalar (>300 satir controller, >500 satir service)
- TODO/FIXME/HACK yorumlari
2D: Hata Yonetimi (bkz. .claude/rules/kalite.md Madde 7)
- Bos catch bloklari (exception yutma)
- Generic exception yakalama (catch-all)
- 500 hatasinda detay sizintisi
- Tutarsiz hata formati
2E: Test Durumu (bkz. .claude/rules/test.md)
- Test dosyasi olmayan service'ler
- Integration test olmayan endpoint'ler
- Assertion'siz testler
- Coverage orani (olculebiliyorsa)
2F: Veritabani (bkz. .claude/rules/veri.md)
- Rollback'siz migration
- FK/index eksikligi
- Isimlendirme ihlalleri (camelCase tablo/kolon)
- Cascade delete kuralsizligi
Faz 3: Raporlama
Bulgulari asagidaki formatta raporla:
CODEBASE AUDIT RAPORU
=====================
Tarih: {tarih}
Proje: {proje adi}
Stack: {tespit edilen stack}
OZET
----
Toplam dosya: X
Toplam sorun: X (Kritik: X, Yuksek: X, Orta: X, Dusuk: X)
BULGULAR
--------
[KRITIK] {kategori} — {dosya:satir}
Sorun: {aciklama}
Oneri: {ne yapilmali}
[YUKSEK] {kategori} — {dosya:satir}
Sorun: {aciklama}
Oneri: {ne yapilmali}
...
GENEL SAGLIK
------------
Guvenlik: [X/6 kontrol gecti]
Performans: [X/5 kontrol gecti]
Kod Kalitesi: [X/5 kontrol gecti]
Hata Yonetimi: [X/4 kontrol gecti]
Test: [X/5 kontrol gecti]
Veritabani: [X/4 kontrol gecti]
ONCELIKLI AKSIYONLAR
--------------------
1. {en kritik sorun + cozum onerisi}
2. {ikinci oncelikli}
3. {ucuncu oncelikli}Onemli Kurallar
- Bu skill KOD DEGISTIRMEZ — sadece tespit ve rapor
- Fix onerileri Team Lead'e sunulur, otomatik duzeltme YAPILMAZ
- Mevcut
kalite.mdveguvenlik.mdkurallarini referans alir, duplicate etmez - Raporu kullaniciya goster, dosyaya kaydetme gereksiz (istenirse kaydedilir)
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.

