systematic-debugging
Skill0 starsChanged 5 months agoMITView on GitHub
Bug, test hatasi veya beklenmeyen davranis ile karsilasinca, fix onerisinden ONCE kullan
190 other projects use a version of this.
Adopted by
Most recently taken up by
- metaspartan/cybaratheir own version, first seen Nov 15, 2026
- alexj11324/Mikkatheir own version, first seen Nov 15, 2026
- mdiri-ai/SoduWorktheir own version, first seen Nov 15, 2026
- komluk/scaffoldingtheir own version, first seen Nov 15, 2026
- KbWen/agent-virtual-officetheir own version, first seen Nov 15, 2026
- Wenaixi/dsh-superpowertheir own version, first seen Nov 15, 2026
Used with
Projects with it also use chinese-code-review, chinese-commit-conventions and 10 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.
Leodorareluctant259Skillchinese-code-review
中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈
Also in 8 projects that use this
Leodorareluctant259Skillchinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化
Also in 8 projects that use this
obraSkilldiagnosing-superpowers
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
Also in 20 projects that use this
SethGammonSkillascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
Also in 4 projects that use this
mjunaidcaSkillbuilding-chatgpt-apps
Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).
Also in 4 projects that use this
mjunaidcaSkillbuilding-chat-interfaces
Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.
Also in 4 projects that use this
- +2 more from Leodorareluctant259
- +4 more from mjunaidca
Other versions190 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 190
- obra/superpowers★ 314ksame name
- NousResearch/hermes-agent★ 264ksame name
- open-metadata/OpenMetadata★ 16ksame name
- jnMetaCode/superpowers-zh★ 8.5ksame name
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame name
- openai/plugins★ 7.8ksame name
- ChrisWiles/claude-code-showcase★ 6.1ksame name
- farm-fe/farm★ 5.6ksame name
- microsoft/FluidFramework★ 4.9ksame name
180 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
- code-auditSkill
- commitSkill
- create-prSkill
- governance-evalSkill
- governance-kurSkill
- migration-checklistSkill
- security-scanSkill
- stack-loaderSkill
- tddSkill
- test-scaffoldSkill
- yeni-projeSkill
The file
Files
Sistematik Debugging
Temel Kural
FIX ONERISINDEN ONCE ROOT CAUSE ARASTIRILIR. ISTISNASI YOK.Phase 1 tamamlanmadan fix onerisi YASAK.
Ne Zaman Kullanilir
- Test hatalari
- Production bug'lari
- Beklenmeyen davranis
- Performans sorunlari
- Build/integration hatalari
Ozellikle su durumlarda: Zaman baskisi varsa, "bariz fix" gorunuyorsa, birden fazla fix denemis ama cozemediysen.
4 Faz
Her faz tamamlanmadan bir sonrakine gecilmez.
Faz 1: Root Cause Arastirmasi
Fix denemeden ONCE:
- Hata mesajini OKU — stack trace, satir numarasi, hata kodu. Atlamak YASAK.
- Yeniden uret — Ayni hatayi guvenilir sekilde tetikleyebiliyor musun? Edemiyorsan daha fazla veri topla, tahmin etme.
- Son degisiklikleri kontrol et — git diff, son commit'ler, yeni dependency, config degisiklikleri.
- Cok katmanli sistemlerde kanit topla:
Her katman sinirinda: - Giren veriyi logla - Cikan veriyi logla - Ortam/config yayilimini dogrula Bir kez calistir → NEREDE kirildigini goster SONRA o katmani arastir - Veri akisini izle — Hatali deger nereden geliyor? Geriye dogru izle, kaynagi bul. Belirtide degil, kaynakta duzelt.
Faz 2: Pattern Analizi
- Calisan ornekleri bul — Ayni codebase'de benzer ama calisan kod var mi?
- Referansla karsilastir — Pattern uyguluyorsan referansi TAMAMEN oku, gozu kaydirmak YASAK.
- Farklari listele — Calisan ve kirilan arasindaki her fark, ne kadar kucuk olursa olsun.
- Bagimliliklari anla — Hangi bilesenler, ayarlar, ortam gereksinimleri var?
Faz 3: Hipotez ve Test
- Tek hipotez kur — "X root cause, cunku Y" — acik, net, yazili.
- Minimal test yap — Tek bir degisken degistir, birden fazla seyi ayni anda degistirme.
- Dogrula:
- Calisti? → Faz 4'e gec
- Calismadi? → YENI hipotez kur, ustune fix ekleme
Faz 4: Uygulama
- Failing test yaz — En basit yeniden uretim. Otomasyon mumkunse test framework'u ile.
- Tek fix uygula — Root cause'a yonelik, TEK degisiklik. "Buradayken su da duzelse" YASAK.
- Dogrula — Test geciyor mu? Diger testler kirilmadi mi?
- Fix calismadiysa:
- < 3 deneme: Faz 1'e don, yeni bilgiyle yeniden analiz et
= 3 deneme: DUR. Mimari sorun olabilir. Kullaniciya raporla, karar iste.
Kirmizi Bayraklar — DUR ve Faz 1'e Don
Su dusunceleri yakalarsan:
- "Simdilik hizli fix, sonra incelerim"
- "X'i degistirip deneyelim bakalim"
- "Birden fazla degisiklik yapip test calistirayim"
- "Test'i atlayip elle kontrol edeyim"
- "Tam anlamadim ama bu calisiabilir"
- "Bir fix daha deneyeyim" (zaten 2+ denemeden sonra)
Tumu = DUR. Faz 1'e don.
Yaygin Bahaneler
| Bahane | Gercek |
| "Basit sorun, surece gerek yok" | Basit sorunlarin da root cause'u var. Surec basit sorunlarda hizli. |
| "Acil, surece zaman yok" | Sistematik debugging, rastgele deneme-yanilmadan HIZLI. |
| "Once sunu deneyeyim, sonra arastiririm" | Ilk fix pattern'i belirler. Bastan dogru yap. |
| "Test'i fix'i dogruladiktan sonra yazarim" | Test edilmemis fix'ler tutmaz. Once test, sonra fix. |
| "Birden fazla fix ayni anda zaman kazandirir" | Hangisinin calistigini bilemezsin. Yeni bug'lar uretir. |
Hizli Referans
| Faz | Anahtar Aktiviteler | Basari Kriteri |
| 1. Root Cause | Hata oku, yeniden uret, degisiklikleri kontrol et | NE ve NEDEN'i anla |
| 2. Pattern | Calisan ornekleri bul, karsilastir | Farklari tespit et |
| 3. Hipotez | Teori kur, minimal test et | Dogrulandi veya yeni hipotez |
| 4. Uygulama | Test yaz, duzelt, dogrula | Bug cozuldu, testler geciyor |
Gercek Dunya Etkisi
- Sistematik yaklasim: 15-30 dk'da fix
- Rastgele fix denemesi: 2-3 saat bocalama
- Ilk seferde dogru fix orani: %95 vs %40
- Yeni bug uretme: Neredeyse sifir vs yaygin
Kaynak: obra/superpowers (uyarlanmis versiyon)
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.

