debug
Skill0 starsChanged 6 months agoMITView on GitHub
Use this skill when diagnosing bugs, errors, test failures, or unexpected behavior. Triggers: 'debug', 'fix bug', 'not working', 'error', 'failing test', 'broken', 'unexpected behavior', 'investigate issue', 'stack trace', 'crash'. Provides a systematic debugging methodology to find root causes efficiently.
192 other projects use a version of this.
Adopted by
Most recently taken up by
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- Firzus/agent-skillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
- microsoft/veronatheir own version, first seen Nov 8, 2026
Used with
Projects 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
Other versions192 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 192
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- anthropics/knowledge-work-plugins★ 35ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- openai/symphony★ 27ksame name
- FalkorDB/FalkorDB★ 10ksame name
- NVIDIA/TensorRT-Model-Optimizer★ 5.6ksame name
- NVIDIA/Model-Optimizer★ 5.6ksame name
182 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 repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-developmentSkill
- agent-teamsSkill
- ai-sdkSkill
- analyzing-financial-statementsSkill
- cache-componentsSkill
- chrome-devtoolsSkill
- Codex-automation-recommenderSkill
- Codex-md-improverSkill
- code-reviewSkill
- Command DevelopmentSkill
- creating-financial-modelsSkill
- data-visualizationSkill
- develop-ai-functions-exampleSkill
- evolve-ai-layerSkill
- excalidraw-diagramSkill
- find-skillsSkill
- frontend-designSkill
- Hook DevelopmentSkill
- make-skill-templateSkill
- markdown-to-htmlSkill
- mcp-builderSkill
- MCP IntegrationSkill
- pdfSkill
- playwrightSkill
- Plugin SettingsSkill
- Plugin StructureSkill
- refactorSkill
- researchSkill
- security-best-practicesSkill
- skill-creatorSkill
- Skill DevelopmentSkill
- smithery-ai-cliSkill
- source-command-commit-and-deploySkill
- source-command-commitSkill
- source-command-create-prdSkill
- source-command-create-rulesSkill
- source-command-empty-redeploySkill
- source-command-evaluateSkill
- source-command-executeSkill
- source-command-handoffSkill
- source-command-plan-featureSkill
- source-command-primeSkill
- source-command-reviewSkill
- source-command-self-healSkill
- source-command-validateSkill
- sql-queriesSkill
- statistical-analysisSkill
- vscode-ext-localizationSkill
- webapp-testingSkill
- web-artifacts-builderSkill
- web-design-guidelinesSkill
- Writing Hookify RulesSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 175 edited versions we read keep these.
9
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 14
Before fixing anything, confirm you can see the problem:
- Distinctive: line 28
If you can't reproduce it, you don't understand it yet.
- Distinctive: line 56
Use binary search — don't change 10 things at once:
- Distinctive: line 75
Don't add a try/catch to hide an error — understand why it happens
- Distinctive: line 76
If the fix is in one place but the same pattern exists elsewhere, check those too
- Distinctive: line 77
If the bug came from a missing guard, consider if other callers have the same gap
- Distinctive: line 83
Add a test that would have caught this bug
- Distinctive: line 84
Check if AGENTS.md or rules should be updated to prevent this pattern
- Distinctive: line 85
Run full validation to ensure no regressions
“Common” is measured: kept by at least 6 in 10 of the 175 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
Debug Skill
When to Use
The agent should read this skill when troubleshooting any bug, error, or unexpected behavior.
Debugging Methodology
Step 1: Reproduce
Before fixing anything, confirm you can see the problem:
# Run the failing test
{test command} -- --grep "test name"
# Start the app and trigger the error
{dev command}
# Then reproduce the exact steps
# Check logs
tail -f logs/*.log 2>/dev/nullIf you can't reproduce it, you don't understand it yet. Gather more information.
Step 2: Read the Error
Actually read the full error:
- Error message: What does it literally say?
- Stack trace: Which file and line threw? Trace the call chain.
- Error type: TypeError? NetworkError? ValidationError? Each means something different.
- Context: What was the input? What state was the app in?
Step 3: Form a Hypothesis
Based on the error, hypothesize the root cause. Common patterns:
| Symptom | Likely Cause |
undefined is not a function | Wrong import, missing method, typo |
null reference | Async timing, optional field not checked |
connection refused | Service not running, wrong port/host |
401/403 | Auth token expired, wrong credentials, missing header |
404 | Wrong URL, route not registered, typo in path |
500 | Unhandled exception in handler, DB query failure |
| Test passes alone, fails in suite | Shared state, mock pollution, test ordering |
| Works locally, fails in CI | Environment difference, missing env var, different DB state |
| Intermittent failure | Race condition, timing dependency, flaky external service |
Step 4: Narrow Down
Use binary search — don't change 10 things at once:
# Check if the issue is in a specific file
git stash # Remove your changes
# Test — does the bug exist in clean state?
git stash pop # Bring changes back
# Check when it broke
git log --oneline -20
git bisect start
git bisect bad # Current commit is broken
git bisect good abc123 # This commit was working
# Git walks you to the breaking commitStep 5: Fix the Root Cause
- Fix the actual problem, not the symptom
- Don't add a try/catch to hide an error — understand why it happens
- If the fix is in one place but the same pattern exists elsewhere, check those too
- If the bug came from a missing guard, consider if other callers have the same gap
Step 6: Verify and Prevent
After fixing:
- Confirm the original reproduction case now passes
- Add a test that would have caught this bug
- Check if AGENTS.md or rules should be updated to prevent this pattern
- Run full validation to ensure no regressions
Anti-Patterns
- ❌ Changing random things until it works (shotgun debugging)
- ❌ Adding
console.logeverywhere without a hypothesis - ❌ Fixing the symptom without understanding the cause
- ❌ Disabling a test that fails instead of fixing the code
- ❌ Catching and swallowing exceptions to make errors disappear
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.

