agentleFS
Sign inStart free
avibebuilderavibebuilder/claude-prime/.claude/skills/fix/SKILL.md

fix

Skill119 starsChanged 6 months agoMITView on GitHub

Fix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, or a prior diagnosis to implement. Do NOT use for new features, pure explanation, architecture discussion, broad research, or bug reports where the main need is figuring out why the behavior happens — use diagnose for that.

82 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use feature, frontend-code-review and 8 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.
  • bradtraversySkill

    feature

    Manage current feature workflow - start, review, explain or complete

    Also in 10 projects that use this

  • chendongqiSkill

    frontend-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

  • GoogleSkill

    pr-creator

    Also in 4 projects that use this

  • vbrevikSkill

    work

    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

  • MetaSkill

    roadmap

    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

  • PydanticSkill

    coverage

    Fetch coverage diff from Codecov for the current branch or a specific PR. Shows uncovered lines, patch coverage, and overall coverage change.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 75 edited versions we read keep these.

  • 8

    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
  1. Distinctive:

    Remove the cause with the change that genuinely restores the intended behavior.

    line 8
  2. Distinctive:

    Check conversation context and skip completed steps.

    line 12
  3. Distinctive:

    Read the symptom, expected behavior, errors, logs, failing tests, and any prior diagnosis.

    line 16
  4. Very specific:

    If you're about to add a speculative guard or workaround because the cause is still fuzzy, you're in the wrong lane.

    line 25
  5. Distinctive:

    GATE: If a plan was requested or produced, wait for user approval before implementation.

    line 27
  6. Distinctive:

    Follow existing code patterns and keep scope tight

    line 38
  7. Distinctive:

    Keep temporary instrumentation that helps prove the repair until verification is complete, then remove it

    line 39
  8. Very specific:

    Add or update a durable test in /fix when covering the bug clearly belongs in the codebase.

    line 47
  9. Distinctive:

    Remove temporary debugging artifacts once verification passes: throwaway scripts, temp logs, or ad hoc instrumentation.

    line 51
  10. Distinctive:

    GATE: Do not call the bug fixed until the evidence directly addresses the reported failure.

    line 53

“Common” is measured: kept by at least 6 in 10 of the 75 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Think harder. Remove the cause with the change that genuinely restores the intended behavior. Making the symptom disappear without explaining the evidence is not a fix.

Process

Check conversation context and skip completed steps.

1. Read the bug, then choose the lane

Read the symptom, expected behavior, errors, logs, failing tests, and any prior diagnosis. Separate confirmed facts from guesses. Then route:

SituationAction
Clear root cause or one strongly evidenced failing areaStay in /fix
One narrow check would remove the last uncertaintyDo that check inside /fix, then commit to a lane
Multiple plausible causes, unclear failing area, or needs runtime instrumentationSwitch to /diagnose first
Bug is understood but multiple defensible fixes with real tradeoffsSwitch to /discuss

If you're about to add a speculative guard or workaround because the cause is still fuzzy, you're in the wrong lane. If evidence is insufficient, switch to /diagnose instead of guessing.

GATE: If a plan was requested or produced, wait for user approval before implementation.

1.5 Reboot after repeated misses

After 3 substantive fix attempts that haven't resolved the bug, stop thrashing. Write a handoff note covering: bug context, confirmed evidence, files checked, each failed approach and why it failed, open questions, and most likely next diagnostic branch. Start a fresh Claude session with the handoff note (or give it to the user to paste). Repeated failures signal contaminated context or narrowed reasoning — a clean window gets fresh judgment. Let stop and enjoy the world, you just did the best thing bro!

2. Repair the cause

  • Apply the smallest change that removes the root cause
  • Correct the bad state transition, condition, query, or data flow rather than masking the symptom at the crash site
  • Call-stack upstream rule: when a function crashes on bad data (undefined, null, wrong type), trace back to where that data was produced or passed. Fix the producer or caller, not the victim. Example: applyDiscount(cart, coupon) crashes because coupon is undefined → fix the lookup or call site that passed bad data, not applyDiscount
  • Follow existing code patterns and keep scope tight
  • Keep temporary instrumentation that helps prove the repair until verification is complete, then remove it

3. Verify with matching evidence

A repair is only done when the evidence matches the report. Prove three things: (1) the original failure is gone, (2) the repaired path was actually exercised, and (3) nearby behavior did not regress.

Hand off to a tester — an isolated teammate that verifies the repair independently. See .claude/skills/test/teammate.md for how to spawn one.

Add or update a durable test in /fix when covering the bug clearly belongs in the codebase. Otherwise the tester owns verification.

4. Clean up

Remove temporary debugging artifacts once verification passes: throwaway scripts, temp logs, or ad hoc instrumentation. Keep durable tests and intentional logging.

GATE: Do not call the bug fixed until the evidence directly addresses the reported failure.

Issue

<issue>$ARGUMENTS</issue>

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free