bug-fix
Skill16 starsChanged 2 days agoMITView on GitHub
Fix a bug test first - reproduce it in a failing test, fix, watch the test pass, and stop after three failed attempts to rethink. Use for any reported bug or failing behaviour.
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
1
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 18
Measure before theorising: Read the actual values, logs and inputs.
- Very specific: line 22
Three strikes: After three fixes that did not work, stop changing code.
“Common” is measured: kept by at least 6 in 10 of the 16 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
<!-- Generated by tools/sync_adapters.py from skills/bug-fix/SKILL.md. Edit the source, not this file. -->Bug fix
- Find the row. Which requirement does the bug break? If none, the bug is a missing
requirement: write the row first. Then write three lines in the fix's
status.md: what happens now, what should happen, and what must not change. The third names the rows next to the bug, and their tests run before and after the fix (TPL-126). From Kiro's bugfix specs, which record current, expected and unchanged behaviour (https://kiro.dev/docs/specs/, read 2026-10-30). - Reproduce in a test that fails for the reason the user saw. Watch it fail. A fix without a failing test first is a guess.
- Measure before theorising. Read the actual values, logs and inputs. The plausible cause is often not the cause.
- Fix the smallest thing that makes the test pass without weakening any other test.
- Watch it pass, then run the sweep.
- Three strikes. After three fixes that did not work, stop changing code. Write down what you
know, what you tried and what each attempt showed, and hand it to the orchestrator, which
brings in
debugger. The fourth blind attempt is the one that breaks something else. - Grep for siblings. The same mistake usually lives in more than one place.
When you catch yourself saying
| The excuse | The answer |
| "It's obvious what's wrong, I'll just fix it." | The obvious cause is the first hypothesis, not the last. Reproduce it in a test first; if you are right, that costs two minutes. |
| "I'll add the test after the fix." | A test written after passes at once and proves nothing. It fails first, for the reason the user saw. |
| "Let me try this and see if it goes away." | A change that tests no stated idea is a guess. Say the idea, then change one thing. |
| "One more attempt and I'll have it." | The fourth blind attempt is the one that breaks something else. Three strikes means stop and write up. |
| "It's probably the environment, or timing, or flaky." | Say what you checked that rules out your code. Most "no root cause" is an unfinished investigation. |
| "The founder is waiting; no time for the process." | Trial and error is slower than measurement. It only feels faster. |
Red flags: a fix bundled with other changes; "should work now"; a test whose failure you cannot explain; a retry or a wider catch added "for safety".
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- techygarg/lattice★ 209same name
- sd0xdev/sd0x-dev-flow★ 192same name
- sd0xdev/sd0x-harness★ 192same name
- EmeaAppGbb/spec2cloud★ 100same name
- nwiizo/claudelytics★ 88same name
- eugenelim/agent-ready-repo★ 27same name
- eugenelim/llm-wiki-kit★ 12same name
- mae616/ai-template★ 9same name
- ramboz/jig★ 7same name
- crgarcia12/Liliput★ 4same name
12 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.
Used alongsideProjects with it also use security-checklists, work-loop and 7 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.
eugenelimSkillsecurity-checklists
Progressive-disclosure security-depth modules for the security-reviewer. Holds ten boundary-keyed checklists (access-control, authn-session, injection, path-and-file, secrets-and-crypto, outbound-ssrf, supply-chain, config-misconfig, exceptional-conditions, llm-agent) as references/, each anchored on a current standard (OWASP Top 10:2025, ASVS 5.0, API Security Top 10:2023, Proactive Controls 2024, CWE Top 25, OWASP LLM Top 10:2025). The work-loop's orchestrator loads only the boundary-matching modules and inlines them into the security-reviewer's brief; the subagent never self-discovers this skill. Not a reviewer prompt itself — it is the depth library the reviewer reasons from.
Also in 3 projects that use this
- eugenelimSkill
work-loop
Use this skill whenever you're implementing a non-trivial change — a feature, a multi-file bug fix, a refactor, a migration, a framework or dependency upgrade, a schema or API change, performance work, an infrastructure or build-system edit, or anything spec-driven. It enforces the project's plan → execute → self-review → fix loop with mechanical gates (lint, typecheck, tests) and adversarial review. Default to this skill for any task larger than a one-line edit.
Also in 3 projects that use this
dhzrxSkillprd-generator
Generate comprehensive Product Requirements Documents with AI PM best practices for new features and products
Also in 3 projects that use this
SvampenSkillinit-project
Generates a tailored .claude/project-config.md for the current project. Asks about project type, quality check commands, documentation paths, insight tags, and review strictness.
Also in 3 projects that use this
genomewalkerSkillresume
Resume a thread by loading its ~800-token context capsule
Also in 3 projects that use this
GitHubSkillrefactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Also in 4 projects that use this
- +1 more from eugenelim
In this repository120 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/agent-agentic-workflow.mdcCursor rule
- .cursor/rules/agent-android-dev.mdcCursor rule
- .cursor/rules/agent-architect.mdcCursor rule
- .cursor/rules/agent-backend-dev.mdcCursor rule
- .cursor/rules/agent-dashboard.mdcCursor rule
- .cursor/rules/agent-debugger.mdcCursor rule
- .cursor/rules/agent-desktop-dev.mdcCursor rule
- .cursor/rules/agent-devops.mdcCursor rule
- .cursor/rules/agent-explainer-writer.mdcCursor rule
- .cursor/rules/agent-feasibility.mdcCursor rule
- .cursor/rules/agent-growth.mdcCursor rule
- .cursor/rules/agent-ios-dev.mdcCursor rule
- .cursor/rules/agent-legal.mdcCursor rule
- .cursor/rules/agent-optimizer.mdcCursor rule
- .cursor/rules/agent-orchestrator.mdcCursor rule
- .cursor/rules/agent-platform-architect.mdcCursor rule
- .cursor/rules/agent-platform-designer.mdcCursor rule
- .cursor/rules/agent-product-designer.mdcCursor rule
- .cursor/rules/agent-qa.mdcCursor rule
- .cursor/rules/agent-researcher.mdcCursor rule
- .cursor/rules/agent-reviewer.mdcCursor rule
- .cursor/rules/agent-rollback.mdcCursor rule
- .cursor/rules/agent-security.mdcCursor rule
- .cursor/rules/agent-setup.mdcCursor rule
- .cursor/rules/agent-social-media.mdcCursor rule
- .cursor/rules/agent-web-dev.mdcCursor rule
- .cursor/rules/skill-bug-fix.mdcCursor rule
- .cursor/rules/skill-commit.mdcCursor rule
- .cursor/rules/skill-context-budget.mdcCursor rule
- .cursor/rules/skill-cost-audit.mdcCursor rule
- .cursor/rules/skill-decision-log.mdcCursor rule
- .cursor/rules/skill-experiment.mdcCursor rule
- .cursor/rules/skill-founder-voice.mdcCursor rule
- .cursor/rules/skill-frontend-design.mdcCursor rule
- .cursor/rules/skill-gates.mdcCursor rule
- .cursor/rules/skill-grilling.mdcCursor rule
- .cursor/rules/skill-handoff.mdcCursor rule
- .cursor/rules/skill-human-design.mdcCursor rule
- .cursor/rules/skill-human-steps.mdcCursor rule
- .cursor/rules/skill-karpathy-guidelines.mdcCursor rule
- .cursor/rules/skill-known-reds.mdcCursor rule
- .cursor/rules/skill-legal-review.mdcCursor rule
- .cursor/rules/skill-new-feature.mdcCursor rule
- .cursor/rules/skill-observability.mdcCursor rule
- .cursor/rules/skill-ordered-steps.mdcCursor rule
- .cursor/rules/skill-performance.mdcCursor rule
- .cursor/rules/skill-readiness-gate.mdcCursor rule
- .cursor/rules/skill-release.mdcCursor rule
- .cursor/rules/skill-requirement-first.mdcCursor rule
- .cursor/rules/skill-safe-data-write.mdcCursor rule
- .cursor/rules/skill-setup.mdcCursor rule
- .cursor/rules/skill-single-source.mdcCursor rule
- .cursor/rules/skill-spec-audit.mdcCursor rule
- .cursor/rules/skill-tailoring.mdcCursor rule
- .cursor/rules/skill-twin-check.mdcCursor rule
- .cursor/rules/skill-verified-claims.mdcCursor rule
- .cursor/rules/skill-verify-green.mdcCursor rule
- commitSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.