메뉴
Hypothesis-driven debugging loop. Forces explicit hypothesis formation before any fix attempt. Prevents guess-and-check debugging. Use when investigating or fixing an observed bug, failing test, runtime error, broken behavior, or performance regression.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | systematic-debugging |
| description | Hypothesis-driven debugging loop. Forces explicit hypothesis formation before any fix attempt. Prevents guess-and-check debugging. Use when investigating or fixing an observed bug, failing test, runtime error, broken behavior, or performance regression. |
| allowed-tools | Read Write Bash |
Never guess-and-check. Always hypothesize first, then design a test for the hypothesis.
Create a fast, deterministic, agent-runnable pass/fail signal for the bug. Prefer, in order: failing test, curl/CLI script, browser script, replayed trace, throwaway harness, or stress loop for flakes.
If you cannot build a loop, stop and report what artifact or environment access is missing. Do not patch from code reading alone.
Run the loop and confirm it matches the user's bug.
Write 3 hypotheses, ordered by likelihood (most likely first):
H1: IF [condition] THEN [expected] BUT we see [actual]
Evidence for: [why this is likely]
Evidence against: [why this might be wrong]
H2: [same format]
H3: [same format]
Design a targeted test that confirms OR rules out H1. A good test is:
Use targeted instrumentation only. Tag temporary logs with a unique prefix like
[DEBUG-a4f2] so cleanup is mechanical.
H1: [confirmed | ruled out]
Evidence: [what you observed]
If confirmed: root cause found → go to Step 6. If ruled out: move to H2. Repeat. If all 3 ruled out: write 3 new hypotheses based on what you learned.
Symptom: API returns 500 Root cause: DB connection pool exhausted Wrong fix: retry API call → symptom addressed, root cause remains
Always trace back to WHY, not just WHAT.
See references/debug-hypotheses.md for hypothesis templates by error type. See references/feedback-loops.md for ways to construct a reliable debug loop.
Enforces use of Context7 MCP for all external library documentation. Prevents API hallucination by requiring real-time doc fetching before any external library call. Auto-triggered when external library usage is detected in code context.
Reading coach: guides users through books systematically with knowledge compilation, mastery testing, spaced repetition, and knowledge querying. Triggers on "read this book", "book study", "start studying", "/book-study".
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. For AI search optimization, see ai-seo.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.