debug
Skill4 starsChanged 33 days agoMITView on GitHub
Root-cause analysis for bugs, failing commands, broken behavior, and error logs. Use when the user encounters errors, crashes, or unexpected behavior. Triggers: debug, fix, bug, error, crash, lỗi, sửa lỗi, hỏng, fail.
We split this skill into the rules it gives an agent
14 rules. 0 are common, 6 are distinctive, and 8 are very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
START: Read .ai-memory.md from project root.
- Very specific: line 11
END: Update .ai-memory.md using Memory Compaction Rules with: bug, root cause, fix, files touched, lessons learned, and remaining risks.
- Very specific: line 17
If bug is in API/server/backend → read .kiro/skills/agents/agents/backend-specialist.md and apply its knowledge
- Very specific: line 18
If bug is in UI/rendering/CSS → read .kiro/skills/agents/agents/frontend-specialist.md and apply its knowledge
- Very specific: line 19
If bug is in database/queries → read .kiro/skills/agents/agents/database-architect.md and apply its knowledge
- Very specific: line 20
If bug may be a security issue → read .kiro/skills/agents/agents/security-auditor.md and apply its knowledge
- Very specific: line 21
Default → read .kiro/skills/agents/agents/debugger.md and apply its systematic analysis
- Distinctive: line 27
When did this start? (recent change, always broken, intermittent?)
- Distinctive: line 29
If any answer is missing, ASK before proceeding.
- Distinctive: line 69
Do not guess when evidence is missing.
- Distinctive: line 70
Prefer deterministic reproduction steps.
- Distinctive: line 72
Avoid changing unrelated files.
- Distinctive: line 73
Always read and update the memory file.
- Very specific: line 81
All code snippets and example files referenced or produced by this skill must be UTF-8 encoded.
“Common” is measured: kept by at least 6 in 10 of the 171 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
Memory Protocol
START: Read .ai-memory.md from project root. Check for known bugs, past fixes, tech stack details, common error patterns, and architecture notes.
END: Update .ai-memory.md using Memory Compaction Rules with: bug, root cause, fix, files touched, lessons learned, and remaining risks.
Goal
Find the real root cause, not just the first visible symptom.
Agent Routing
- If bug is in API/server/backend → read
.kiro/skills/agents/agents/backend-specialist.mdand apply its knowledge - If bug is in UI/rendering/CSS → read
.kiro/skills/agents/agents/frontend-specialist.mdand apply its knowledge - If bug is in database/queries → read
.kiro/skills/agents/agents/database-architect.mdand apply its knowledge - If bug may be a security issue → read
.kiro/skills/agents/agents/security-auditor.mdand apply its knowledge - Default → read
.kiro/skills/agents/agents/debugger.mdand apply its systematic analysis
Socratic Gate
Before debugging, verify:
- What is the expected behavior vs actual behavior?
- Is there a log, stacktrace, or error message?
- When did this start? (recent change, always broken, intermittent?)
- Have we tried this before? If any answer is missing, ASK before proceeding.
Workflow
- Read Memory — Load
.ai-memory.mdfor project context and past bug history. - Summarize the bug, expected behavior, and actual behavior.
- Gather evidence from logs, stack traces, code paths, config, and recent changes.
- List the top hypotheses ranked by likelihood. Eliminate previously failed hypotheses immediately.
- Eliminate hypotheses using direct evidence.
- Identify the root cause and confirm with evidence before attempting any code changes.
- Propose an effective solution that addresses the root cause definitively. Ensure clean code standards are met and fully update all related files.
- Suggest how to verify the fix and prevent regressions.
- Quality Gate — Read
.kiro/skills/_scripts/checklist.mdand run cross-cutting quality checks. - Update Memory — Save root cause, fix, and lessons to
.ai-memory.md.
Output format
- Symptom
- Evidence collected
- Failed Attempts (to avoid repetition)
- Hypotheses (ranked by likelihood)
- Root cause
- Fix (Clean code & complete file updates)
- Verification steps
- Regression prevention
Checklist
- Bug clearly described (expected vs actual)
- Past failed attempts reviewed to prevent loop
- Evidence gathered and root cause definitively confirmed
- Hypotheses listed and ranked
- Root cause confirmed with evidence
- Fix is effective and addresses root cause directly
- No side effects introduced
- Verification steps provided
- Regression prevention suggested
- Memory file updated
- Clean code chuẩn (Standard clean code applied)
- Cập nhật đầy đủ tất cả các file liên quan (All related files fully updated)
Rules
- Do not guess when evidence is missing; say what must be checked.
- Prefer deterministic reproduction steps.
- Mention any hidden risk or side effect of the fix.
- Avoid changing unrelated files; if a fix seems wide-impact, ASK before proceeding.
- Always read and update the memory file.
Related Skills
/test→ read.kiro/skills/test/SKILL.md— Write tests to prevent regression/enhance→ read.kiro/skills/enhance/SKILL.md— Improve code quality after fixing/status→ read.kiro/skills/status/SKILL.md— Check project health after fix
Encoding
All code snippets and example files referenced or produced by this skill must be UTF-8 encoded. When applicable, include encoding: "UTF-8" in SKILL.md front-matter and ensure saved files use UTF-8 (no BOM).
Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 194
- Yeachan-Heo/oh-my-claudecode★ 40ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 40ksame name
- anthropics/knowledge-work-plugins★ 34ksame name
- qwibitai/nanoclaw★ 31ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- openai/symphony★ 27ksame name
- FalkorDB/FalkorDB★ 11ksame name
- NVIDIA/Model-Optimizer★ 5.5ksame name
- NVIDIA/TensorRT-Model-Optimizer★ 5.3ksame name
184 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.
Used alongsideProjects with it also use add-discord, add-slack 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.
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
- +10 more from microsoft
In this repository96 other files it gives its agents.
- .cursor/rules/agents.mdcCursor rule
- .cursor/rules/brainstorm.mdcCursor rule
- .cursor/rules/clean.mdcCursor rule
- .cursor/rules/create.mdcCursor rule
- .cursor/rules/debug.mdcCursor rule
- .cursor/rules/deploy.mdcCursor rule
- .cursor/rules/enhance.mdcCursor rule
- .cursor/rules/explain.mdcCursor rule
- .cursor/rules/instructions.mdcCursor rule
- .cursor/rules/integrate.mdcCursor rule
- .cursor/rules/motion-ui.mdcCursor rule
- .cursor/rules/orchestrate.mdcCursor rule
- .cursor/rules/plan.mdcCursor rule
- .cursor/rules/preview.mdcCursor rule
- .cursor/rules/status.mdcCursor rule
- .cursor/rules/test.mdcCursor rule
- .cursor/rules/ui-ux-pro-max.mdcCursor rule
- agentsSkill
- brainstormSkill
- cleanSkill
- createSkill
- debugSkill
- deploySkill
- enhanceSkill
- explainSkill
- integrateSkill
- motion-uiSkill
- orchestrateSkill
- planSkill
- previewSkill
- statusSkill
- testSkill
- ui-ux-pro-maxSkill
- agentsSkill
- brainstormSkill
- cleanSkill
- createSkill
- debugSkill
- deploySkill
- enhanceSkill
- explainSkill
- integrateSkill
- motion-uiSkill
- orchestrateSkill
- planSkill
- previewSkill
- statusSkill
- testSkill
- ui-ux-pro-maxSkill
- agentsSkill
- brainstormSkill
- cleanSkill
- createSkill
- deploySkill
- enhanceSkill
- explainSkill
- integrateSkill
- motion-uiSkill
- orchestrateSkill
- planSkill
- The first 60 shown.
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.

