debug
Skill1 starsChanged 13 days agoApache-2.0View on GitHub
Root-cause a bug, test failure, or unexpected behavior before proposing a fix. Use whenever something is broken — instead of guessing at patches.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- automagik-dev/omnitheir own version, first seen Nov 15, 2026
- patrickjaja/claude-desktop-extratheir own version, first seen Nov 15, 2026
- NVIDIA/Model-Optimizertheir own version, first seen Nov 15, 2026
- drosam/agentstheir own version, first seen Nov 15, 2026
- shivasaini04/nanocrewtheir own version, first seen Nov 15, 2026
- markmhendrickson/neotomatheir own version, first seen Nov 15, 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
- MicrosoftSkill
add-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
- +10 more from microsoft
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- anthropics/knowledge-work-plugins★ 36ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- openai/symphony★ 27ksame name
- FalkorDB/FalkorDB★ 11ksame name
- NVIDIA/Model-Optimizer★ 5.6ksame name
- NVIDIA/TensorRT-Model-Optimizer★ 5.6ksame name
181 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 repository15 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- checkSkill
- commit-msgSkill
- consolidate-lessonsSkill
- coordinateSkill
- db-resetSkill
- implementSkill
- ingestSkill
- migrateSkill
- planSkill
- reviewSkill
- sync-graphSkill
- testSkill
- validateSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 175 edited versions we read keep these.
3
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 9
Root cause: Read the error / stack trace fully (line, file, code).
- Distinctive: line 10
Check recent changes (git diff, recent commits).
- Distinctive: line 17
Fix: Write a failing test that reproduces the bug first (TDD), then fix the root cause only — no "while I'm here" changes.
“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
Systematic debugging. No fix without a root cause first — symptom patches waste time and add bugs. Work the phases in order; don't jump to a fix.
- Root cause. Read the error / stack trace fully (line, file, code). Reproduce reliably.
Check recent changes (
git diff, recent commits). For a multi-layer path, add diagnostic logging at each boundary and run once to see where it breaks. Use the codegraph MCP (codegraph_explore/ callers / references) to trace the bad value back to its source. - Pattern. Find a working example of the same thing in the repo; list every difference between working and broken. Don't assume "that can't matter".
- Hypothesis. State one specific cause ("X because Y"). Test it with the smallest possible change, one variable at a time. Wrong? Form a new hypothesis — don't stack fixes.
- Fix. Write a failing test that reproduces the bug first (TDD), then fix the root cause only — no "while I'm here" changes. Verify the test passes and nothing else broke.
If 3+ fixes have failed, stop fixing and question the architecture/assumptions with the user — that pattern means the design is wrong, not the latest hypothesis.
Hand the verified fix to /implement conventions (one focused commit, test included) and /validate (gates green + behavior confirmed). Never claim fixed without fresh evidence.
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.