kkkirito-123/zlagent/systematic-debugging
Claude Code and agent skill by kkkirito-123/zlagent
- community
Checking that the SKILL.md file is still in the repository.
Root-cause-first debugging loop for code or runtime errors: understand the failure before proposing a fix. Adapted from Hermes' systematic- debugging — same iron law, smaller surface, ZLAgent-tool-aware.
Install
npx vskill@latest install kkkirito-123/zlagent/systematic-debuggingSKILL.md
systematic-debugging
Trigger
Use this skill when the user reports a bug, a failing test, an unexplained runtime exception, a flaky job, or pastes a traceback.
Do NOT use this when:
- The user only wants a code review of working code.
- The error is obviously environmental (missing env var) and the fix
is one line.
- The user explicitly says "just patch it, don't investigate".
The Iron Law
No fix without a root cause. A symptom fix is failure. If you haven't completed Phase 1, you cannot propose a fix.
Inputs
symptom: the user-visible failure (error message, wrong output,
hang, ...). Capture verbatim.
repro: how to reproduce. Ask if missing.recent_changes: what changed since it last worked.scope: file paths / functions / cron jobs / channels involved.
Steps
Phase 1 — Understand:
- Restate the symptom in your own words. If you can't, ask.
- Reproduce or get the user to reproduce. No repro = no fix.
- Read the smallest necessary code with
read_file. Avoid wide grep. - State the hypothesis as: "Failure happens because X, evidenced by Y".
Phase 2 — Localise:
- Add minimal logging or a targeted test that would prove / disprove
the hypothesis.
- Run it (or have the user run it) and read the new evidence.
Phase 3 — Fix:
- Propose the smallest change that addresses the root cause. Show the
diff. State which assumption it corrects.
- Verify with the same repro / test you used in Phase 2.
Phase 4 — Land:
- State what regression test was added (or why none was needed).
- Note any related-but-not-fixed issues; do not silently widen scope.
Verification
- The fix reverts a specific named cause, not a generic "improvement".
- The repro that failed before the fix passes after.
- Tests that already passed still pass.
- Changes are minimal — no drive-by edits, no comment churn.
Failure Signals
- "Try this and see if it works" without a hypothesis.
- Multiple unrelated changes in one fix.
- The user has to debug your fix.
- Same bug class re-fires within a week.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingworkspace/skills/coding/systematic-debugging/SKILL.md
Popularity
- Repository stars
- 32
- Repository forks
- 5
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kkkirito-123/zlagent/systematic-debugging)