debug
Skill1 starsChanged 3 months agoMITView on GitHub
Debug a failing command, bug, flake, runtime error, wrong output, or performance regression with evidence: reproduce, minimize, hypothesize, instrument, fix, and regression-test. Use when the user asks to debug, diagnose, fix a failure, or use debug-loop.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- mannobeats/hyper-tastetheir own version, first seen Nov 16, 2026
- champ18ion/claud18codetheir own version, first seen Nov 16, 2026
- jestermaxdelta/roblox-building-skilltheir own version, first seen Nov 16, 2026
- chuckplayer/claude-agent-packtheir own version, first seen Nov 16, 2026
- automagik-dev/omnitheir own version, first seen Nov 15, 2026
- patrickjaja/claude-desktop-extratheir 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
MicrosoftSkilladd-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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architecture-reviewSkill
- domain-modelingSkill
- handoffSkill
- implementation-planSkill
- requirements-reviewSkill
- test-and-verifySkill
- webgl-scroll-siteSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 176 edited versions we read keep these.
10
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 12
Do one job: turn a symptom into root cause, fix, and regression proof.
- Distinctive: line 14
Keep output bounded: inspect high-signal tails, focused files, and direct repros.
- Distinctive: line 15
Use shell and repo-native tools first.
- Distinctive: line 16
After two identical failures, change hypothesis or instrumentation.
- Distinctive: line 20
Use for failing tests, CI failures, crashes, hangs, flakes, broken UI flows, bad output, slow paths, and environment drift.
- Distinctive: line 28
Add temporary instrumentation only when observation is otherwise impossible.
- Distinctive: line 30
Add or identify a regression proof and rerun the original repro.
- Distinctive: line 34
Do not guess from logs alone when a repro is available.
- Distinctive: line 35
Do not widen the fix until the local cause is understood.
- Distinctive: line 36
Treat hangs and concurrency failures as first-class symptoms.
“Common” is measured: kept by at least 6 in 10 of the 176 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
Find root cause before changing code.
Unix/Pi Contract
- Do one job: turn a symptom into root cause, fix, and regression proof.
- Consume an exact repro, logs, runtime state, and code path; emit cause, patch, and proof.
- Keep output bounded: inspect high-signal tails, focused files, and direct repros.
- Use shell and repo-native tools first; use heavier tooling only when it improves observation.
- After two identical failures, change hypothesis or instrumentation.
Use
Use for failing tests, CI failures, crashes, hangs, flakes, broken UI flows, bad output, slow paths, and environment drift.
Workflow
- Reproduce the symptom with the exact command, URL, or workflow.
- Minimize to the smallest failing surface.
- State one current hypothesis and the evidence that would disprove it.
- Inspect the code path and runtime state that can affect the symptom.
- Add temporary instrumentation only when observation is otherwise impossible; remove it before finishing.
- Fix the root cause, not just the observed error string.
- Add or identify a regression proof and rerun the original repro.
Guardrails
- Do not guess from logs alone when a repro is available.
- Do not widen the fix until the local cause is understood.
- Treat hangs and concurrency failures as first-class symptoms; use timeouts, logs, and serialized repros.
- Separate pre-existing unrelated failures from failures caused by the edit.
Output
Return:
- Symptom and repro.
- Root cause.
- Fix.
- Regression proof.
- Commands and results.
- Remaining risks or external blockers.
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.

