diagnose
Skill0 starsChanged 5 months agoMITView on GitHub
Disciplined diagnosis loop for hard bugs and performance regressions — reproduce → hypothesise → instrument → fix → regression-test. Use when asked to diagnose/debug, something is broken or failing, or a perf regression is reported.
193 other projects use a version of this, 98 of them edited.
Adopted by
Most recently taken up by
- GravionLabs/skillstheir own version, first seen Nov 15, 2026
- matasarei/mac-bottlertheir own version, first seen Nov 15, 2026
- ekirton/Pouletheir own version, first seen Nov 15, 2026
- fx-studio/fx-sdlc-labtheir own version, first seen Nov 15, 2026
- agent-services-at/pluginstheir own version, first seen Nov 8, 2026
- skillberry-ai/cap-evolvetheir own version, first seen Nov 8, 2026
Used with
Projects with it also use zoom-out, to-prd 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.
victorgarciaesgiSkillzoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
Also in 61 projects that use this
GoogleSkillto-prd
Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
Also in 56 projects that use this
GoogleSkillto-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
Also in 53 projects that use this
simo97Skilledit-article
The user will invoke this skill to help them edit an article.
Also in 17 projects that use this
simo97Skillwrite-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Also in 44 projects that use this
AnasX7Skillsetup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Also in 27 projects that use this
- +4 more from simo97
Other versions193 projects use a version of this.
Word for word · 0
None found.
Edited · 98
- epicenter-md/epicenter★ 4.8k57% same
- EpicenterHQ/epicenter★ 4.8k57% same
- formancehq/ledger★ 1.5k57% same
- victorgarciaesgi/regle★ 50861% same
- amazingloft999-droid/mattpocock-skills★ 42261% same
- openvetta/open-vetta★ 29961% same
- InditexTech/weavejs★ 26661% same
- letehaha/moneymatter★ 24361% same
- yamcodes/arkenv★ 15161% same
- alex-on-ai/WebReaper★ 14961% same
88 more not listed
Wrote their own version · 95
- github/awesome-copilot★ 41ksame name
- CherryHQ/cherry-studio-app★ 4.1ksame name
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- getagentseal/founder-playbook★ 745same name
- microsoft/AutoSaddler★ 231same name
- avibebuilder/claude-prime★ 119same name
- KerberosClaw/kc_ai_skills★ 79same name
- tranhieutt/software_development_department★ 71same name
- skillberry-ai/cap-evolve★ 70same name
- TserenTserenov/FMT-exocortex-template★ 64same name
85 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 repository63 other files it gives its agents.
- .claude/skills/nestjs-best-practices/AGENTS.mdAGENTS.md
- accessibility-a11ySkill
- architecture-blueprint-generatorSkill
- backend-delivery-loopSkill
- backend-designSkill
- backend-dev-guidelinesSkill
- backend-testingSkill
- backend-to-frontend-handoff-docsSkill
- building-componentsSkill
- bullmq-specialistSkill
- canvas-designSkill
- code-patternsSkill
- components-composition-patternsSkill
- conventional-commitSkill
- core-web-vitalsSkill
- create-svgSkill
- css-architectureSkill
- cypress-authorSkill
- cypress-docsSkill
- cypress-explainSkill
- delivery-loop-retroSkill
- fastify-best-practicesSkill
- figma-code-connectSkill
- frontend-delivery-loopSkill
- frontend-fundamentalsSkill
- fullstack-delivery-loopSkill
- grill-meSkill
- hunt-race-conditionSkill
- impeccableSkill
- mermaid-diagramsSkill
- nestjs-best-practicesSkill
- nextjs-best-practicesSkill
- nextjs-performanceSkill
- nodejs-backend-patternsSkill
- owasp-security-reviewSkill
- performance-hunterSkill
- playwright-best-practicesSkill
- postgresql-code-reviewSkill
- postgresql-optimizationSkill
- postmanSkill
- prisma-postgresSkill
- pro-state-machineSkill
- race-conditionSkill
- react-best-practicesSkill
- react-performanceSkill
- react-querySkill
- redis-coreSkill
- redis-query-engineSkill
- redis-securitySkill
- refactorSkill
- review-panelSkill
- run-delivery-chainSkill
- spec-drivenSkill
- sql-optimizationSkill
- system-designSkill
- testing-strategySkill
- tune-skills-and-agentsSkill
- ui-ux-pro-maxSkill
- vercel-react-view-transitionsSkill
- viteSkill
- The first 60 shown.
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 10
When exploring the codebase, use the project's domain glossary to get a clear mental model of the relevant modules, and check ADRs in the …
- Distinctive: line 22
Do not proceed to Phase 2 until you have a loop you believe in.
- Distinctive: line 26
Run the loop. Watch the bug appear.
- Distinctive: line 34
Do not proceed until you reproduce the bug.
- Distinctive: line 44
If you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it.
- Distinctive: line 54
Debugger / REPL inspection: if the env supports it. One breakpoint beats ten logs.
- Distinctive: line 56
Never "log everything and grep".
- Distinctive: line 64
Write the regression test before the fix — but only if there is a correct seam for it.
- Distinctive: line 70
If a correct seam exists:
“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
Diagnose
A discipline for hard bugs. Skip phases only when explicitly justified.
When exploring the codebase, use the project's domain glossary to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
Phase 1 — Build a feedback loop
This is the skill. Everything else is mechanical. If you have a fast, deterministic, agent-runnable pass/fail signal for the bug, you will find the cause — bisection, hypothesis-testing, and instrumentation all just consume that signal. If you don't have one, no amount of staring at code will save you.
Spend disproportionate effort here. Be aggressive. Be creative. Refuse to give up.
Read references/feedback-loops.md now — it lists the ten ways to construct a loop (in preference order, from failing test to the HITL script at scripts/hitl-loop.template.sh), how to iterate the loop itself (faster, sharper, more deterministic), how to raise the reproduction rate of non-deterministic bugs, and what to do when no loop is possible.
Build the right feedback loop, and the bug is 90% fixed.
Do not proceed to Phase 2 until you have a loop you believe in.
Phase 2 — Reproduce
Run the loop. Watch the bug appear.
Confirm:
- The loop produces the failure mode the user described — not a different failure that happens to be nearby. Wrong bug = wrong fix.
- The failure is reproducible across multiple runs (or, for non-deterministic bugs, reproducible at a high enough rate to debug against).
- You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix actually addresses it.
Do not proceed until you reproduce the bug.
Phase 3 — Hypothesise
Generate 3–5 ranked hypotheses before testing any of them. Single-hypothesis generation anchors on the first plausible idea.
Each hypothesis must be falsifiable: state the prediction it makes.
Format: "If
<X>is the cause, then<changing Y>will make the bug disappear /<changing Z>will make it worse."
If you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it.
Show the ranked list to the user before testing. They often have domain knowledge that re-ranks instantly ("we just deployed a change to #3"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it — proceed with your ranking if the user is AFK.
Phase 4 — Instrument
Each probe must map to a specific prediction from Phase 3. Change one variable at a time.
Tool preference:
- Debugger / REPL inspection if the env supports it. One breakpoint beats ten logs.
- Targeted logs at the boundaries that distinguish hypotheses.
- Never "log everything and grep".
Tag every debug log with a unique prefix, e.g. [DEBUG-a4f2]. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die.
Perf branch. For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, performance.now(), profiler, query plan), then bisect. Measure first, fix second.
Phase 5 — Fix + regression test
Write the regression test before the fix — but only if there is a correct seam for it.
A correct seam is one where the test exercises the real bug pattern as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence.
If no correct seam exists, that itself is the finding. Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase.
If a correct seam exists:
- Turn the minimised repro into a failing test at that seam.
- Watch it fail.
- Apply the fix.
- Watch it pass.
- Re-run the Phase 1 feedback loop against the original (un-minimised) scenario.
Phase 6 — Cleanup + post-mortem
Required before declaring done:
- Original repro no longer reproduces (re-run the Phase 1 loop)
- Regression test passes (or absence of seam is documented)
- All
[DEBUG-...]instrumentation removed (grepthe prefix) - Throwaway prototypes deleted (or moved to a clearly-marked debug location)
- The hypothesis that turned out correct is stated in the commit / PR message — so the next debugger learns
Then ask: what would have prevented this bug? If the answer involves architectural change (no good test seam, tangled callers, hidden coupling), flag the specifics to the user as a follow-up recommendation. Make the recommendation after the fix is in, not before — you have more information now than when you started.
References
| Reference | Read when |
| references/feedback-loops.md | In Phase 1 — constructing, sharpening, or rescuing the pass/fail loop |
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.

