fix
Skill0 starsChanged 46 days agoMITView on GitHub
The bounded fast lane for trivial, reversible fixes — check-trivial.sh decides eligibility (≤15 lines, ≤3 files, no new deps, off the critical surface); regression test, gate, and single machine-checked review are never skipped. Anything bigger routes to the full loop.
- Commits and pushes
90 other projects use a version of this.
Adopted by
Most recently taken up by
- Akirakii/harness-doctortheir own version, first seen Nov 16, 2026
- krystaleicher/claude-skillstheir own version, first seen Nov 16, 2026
- david33137/claude-skillstheir own version, first seen Nov 16, 2026
- cloudflare/vinexttheir own version, first seen Nov 15, 2026
- stericishere/skillstheir own version, first seen Nov 15, 2026
- RemiPelloux/kill-my-ideatheir own version, first seen Nov 15, 2026
Used with
Projects with it also use feature, frontend-code-review 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.
bradtraversySkillfeature
Manage current feature workflow - start, review, explain or complete
Also in 10 projects that use this
chendongqiSkillfrontend-code-review
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.
Also in 4 projects that use this
GoogleSkillpr-creator
Also in 4 projects that use this
PJuniszewskiSkillcook
Feature development with guardrails. Plan → Review → Code → Ship.
Also in 3 projects that use this
vbrevikSkillwork
Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.
Also in 4 projects that use this
MetaSkillroadmap
Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint. Use for source research, repository-wide inventories of existing and planned mathematics, scope, coverage, milestones, and roadmap articles; do not create repository infrastructure or prove Lean declarations.
Also in 4 projects that use this
Other versions90 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 90
- react/react★ 253ksame name
- facebook/react★ 253ksame name
- motiondivision/motion★ 35ksame name
- cloudflare/vinext★ 9.4ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- crbnos/carbon★ 2.8ksame name
- Akylas/OSS-DocumentScanner★ 2.7ksame name
- kdlbs/kandev★ 1.1ksame name
80 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 repository29 other files it gives its agents.
- hosts/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adrSkill
- api-designSkill
- auditSkill
- code-reviewSkill
- concurrency-performanceSkill
- coverageSkill
- debuggingSkill
- debugSkill
- fast-laneSkill
- implementSkill
- intakeSkill
- leanSkill
- migration-safetySkill
- nonnaSkill
- observabilitySkill
- planSkill
- refactoringSkill
- releaseSkill
- reviewSkill
- rollbackSkill
- security-reviewSkill
- shipSkill
- supply-chainSkill
- syncSkill
- tddSkill
- tdd-workflowSkill
- testSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 83 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Branch check: Never on main/master/develop — branch as fix/<id>-<slug> first.
- Very specific: line 25
Eligibility — the script decides: Run bash "${CLAUDE_SKILL_DIR}/../fast-lane/scripts/check-trivial.sh".
“Common” is measured: kept by at least 6 in 10 of the 83 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
!git branch --show-current !git status --short
Fix: $ARGUMENTS
The autonomy dial, bounded (see the fast-lane skill): the leash length is set by a deterministic
script, not by self-assessment. If at any step this looks bigger than trivial, stop and take the
full loop.
Steps
- Branch check. Never on
main/master/develop— branch asfix/<id>-<slug>first. - Regression test first. Pin the fixed behavior with a test that fails before the change (RED). Behavior changes are never exempt; only a docs/comment-only diff — nothing to pin — skips this.
- Implement the minimal fix (GREEN). No drive-by improvements — surgical changes only.
- Eligibility — the script decides. Run
bash "${CLAUDE_SKILL_DIR}/../fast-lane/scripts/check-trivial.sh". Non-zero means this is not a trivial change: stop and route through the full loop (/plan→/tdd→/review→/ship). Do not argue with the classifier. - Full local gate (
/test): lint + type-check + tests + coverage. Never skipped, never reported green unless observed green. - Single review — machine-checked. Dispatch
code-reviewerwithmodel: sonnet(a fast-lane diff does not need the deep tier); write its fenced JSON verdict verbatim to.claude/reviews/<sha>-code.json(git rev-parse --short HEAD) and runbash "${CLAUDE_SKILL_DIR}/../code-review/scripts/check-review.sh"on it. Non-zero blocks the ship. - Ship. One-line
docs/STATUS.mdentry, conventional commit,git push -u origin <branch>, PR todeveloplinked to the tracked issue.
Output
Report as Assumptions / Changed / Verified / Remaining risk — include the classifier's line count, the observed gate result, and the review verdict.
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.

