Learn-skills.dev debug-tools
install
source · Clone the upstream repo
git clone https://github.com/NeverSight/learn-skills.dev
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/NeverSight/learn-skills.dev "$T" && mkdir -p ~/.claude/skills && cp -r "$T/data/skills-md/adeonir/agents-skills/debug-tools" ~/.claude/skills/neversight-learn-skills-dev-debug-tools-85326a && rm -rf "$T"
manifest:
data/skills-md/adeonir/agents-skills/debug-tools/SKILL.mdsource content
Debug Tools
Iterative debugging workflow with targeted log injection and cleanup.
Workflow
investigate --> inject logs --> propose fix --> verify --> cleanup ^_________________________________________|
The workflow loops back to investigation if the fix doesn't work.
Context Loading Strategy
Load only the reference matching the current trigger. Multiple references may be loaded during a full debugging session (investigation often leads to log injection).
Triggers
| Trigger Pattern | Reference |
|---|---|
| Debug issue, investigate bug, fix bug | investigation.md |
| Add debug logs, inject logs, trace with logs | log-injection.md |
| Remove debug logs, cleanup logs | log-cleanup.md |
| Debug patterns, log format, common bugs | debugging-patterns.md |
Cross-References
investigation.md <---> log-injection.md (investigation may request logs) investigation.md <---> log-cleanup.md (after fix verified) log-injection.md ----> log-cleanup.md (cleanup removes injected logs)
Guidelines
DO:
- Use confidence scoring: >= 70 report as probable cause, 50-69 suggest logs
- Always use
prefix for injected logs (enables cleanup)[DEBUG] - Apply minimal fix: smallest change that resolves the issue
- Clean up debug logs automatically after fix is verified
- Use whatever debugging tools are available in the environment
DON'T:
- Report findings with confidence < 50
- Log sensitive data (passwords, tokens, PII)
- Apply large refactors as part of a bug fix
- Leave debug logs in production code
Error Handling
- No bug description provided: ask user to describe the issue
- Cannot reproduce: suggest adding debug logs
- Fix doesn't work: return to investigation phase
- Logs left behind: user can request cleanup anytime