debug
Skill0 starsChanged 16 days agoMITView on GitHub
Diagnose a failure with a tight red loop first, then hypothesise, fix the shared cause, and prove it. Use when something is broken, a test fails, a bug is reported, or the user asks to debug or find the root cause. Do not shotgun-edit.
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
- MicrosoftSkill
add-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 repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-passSkill
- assess-changeSkill
- build-regression-packSkill
- charter-exploratorySkill
- classify-dataSkill
- commitSkill
- cut-releaseSkill
- data-changeSkill
- design-experimentSkill
- diff-environmentsSkill
- draft-steercoSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- map-dependenciesSkill
- map-design-handoffSkill
- map-processSkill
- open-prSkill
- performanceSkill
- plan-data-migrationSkill
- plan-incrementSkill
- plan-rollbackSkill
- plan-uatSkill
- prioritize-backlogSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- revert-changeSkill
- review-architectureSkill
- review-changeSkill
- review-pipelineSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- spec-analyticsSkill
- spec-observabilitySkill
- start-projectSkill
- synthesize-discoverySkill
- triage-blockersSkill
- triage-defectSkill
- update-raidSkill
- verify-uiSkill
- write-api-examplesSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-integration-contractSkill
- write-nfrSkill
- write-opportunitySkill
- write-prdSkill
- write-requirementsSkill
- write-runbookSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 175 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
If you have neither a repro nor that evidence, stop.
- Very specific: line 40
Read AGENTS.md. Redact secrets (<REDACTED>).
- Distinctive: line 44
Write 3–5 falsifiable hypotheses, then test one at a time.
“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
Find the cause of a known failure. Do not start a feature while debugging. Do not theorise without a command that can go red on this bug.
Is this the right skill?
| Signal | Do this instead |
| Live prod impact | incident-triage first |
| No expected/actual | triage-defect then return |
| Add tests after the cause is known | write-tests |
Required inputs
- Expected, actual, and a repro command or the shortest UI/API steps
- Or captured production evidence from
incident-triage
If you have neither a repro nor that evidence, stop.
Human decisions (do not invent)
- Destructive data repairs
Procedure
- Read
AGENTS.md. Redact secrets (<REDACTED>). - Pin expected / actual / repro. Write them down.
- Build a tight red loop — one command you have already run that asserts the user’s symptom. Tests at a public seam first. If you cannot build a loop, list what you tried and stop.
- Confirm it is the user’s failure. Minimise inputs until every leftover piece is load-bearing.
- Write 3–5 falsifiable hypotheses, then test one at a time. Cap: five failed hypotheses → stop and report.
- Fix the shared cause (every caller). Do not delete the failing test. Load
engineering-bar. Prefer a failing test at the seam before the fix (write-tests). - Re-run the original loop. Remove tagged debug logs. Run focused tests and repo Test if cheap.
Output
- Path: reply (and a file only if asked)
- Template: references/debug-report.md
Quality bar
- Red-loop command and output exist
- Root cause names a file/symbol
- Tagged debug logs are gone
- Original loop is green or you stopped honestly
Done
Fill the report. Next: write-tests / ready-to-merge.
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.