Fix bugs and broken behavior when there is enough evidence to act on a repair path.

MITAuto-check passedTesting & QA

Install Fix

skills CLI
$ npx skills add avibebuilder/claude-prime --skill fix -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install avibebuilder/claude-prime fix --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/avibebuilder/claude-prime.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/fix .claude/skills/fix && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fix
GitHub stars
120
Token cost
~1k tokens
SKILL.md length
482 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
MIT

At a glance

Fix bugs and broken behavior when there is enough evidence to act on a repair path.

  • Works in 4 steps: Read the bug, then choose the lane → Repair the cause → Verify with matching evidence → …
  • Incorrect results
  • SKILL.md covers Process and Issue
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Fix is an agent skill from avibebuilder/claude-prime. 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…

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Failing and flaky tests, Debugging and QA and bug reports. The repository describes itself as: You've heard Claude Code can do amazing things. Skills, hooks, agents, memory systems — but who has time to figure all that out? Claude Prime sets it up for you in one command. The licence is MIT.

When your agent uses it

  • Incorrect results
  • API failures (500
  • Database exceptions
  • Broken rendering

Example prompts

  • “/fix”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Read the bug, then choose the lane
  2. Repair the cause
  3. Verify with matching evidence
  4. Clean up

What it can do on your machine

Read from SKILL.md and the folder at commit 80bcfa4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fix loads about 1k tokens when it runs. Until then it costs about 182 tokens; SKILL.md has 482 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~182
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from avibebuilder/claude-prime at commit 80bcfa4, republished under its MIT licence (© avibebuilder). 482 words, ~1,007 tokens.

Download SKILL.mdSave it as .claude/skills/fix/SKILL.md (or your agent's skills folder).
name
fix
description
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.
argument-hint
issue

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!

Show full SKILL.md (229 more words)Show less
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>

© avibebuilder, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/fix of avibebuilder/claude-prime.

Open the folder on GitHubat commit 80bcfa4

Compare with similar skills

Fix next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fix this skillavibebuilder/claude-prime120—~1kAutomated safety check: PassMIT
Bug Reproduction Test GeneratorArabelaTso/Skills-4-SE253—~1.8kAutomated safety check: PassApache-2.0
Bug FixEmeaAppGbb/spec2cloud100—~2kAutomated safety check: PassMIT
Bug To Patch GeneratorArabelaTso/Skills-4-SE253—~4.4kAutomated safety check: PassApache-2.0
Fix The Classjoetawil7/first-pass112—~1.5kAutomated safety check: PassMIT
Dynamo Jira TicketDynamoDS/Dynamo2k—~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • Bug Reproduction Test Generator

    ArabelaTso/Skills-4-SE

    Automatically generates executable tests that reproduce reported bugs from issue reports and code repositories.

    253 GitHub stars~1.8k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Bug Fix

    EmeaAppGbb/spec2cloud

    Lightweight entry point for fixing bugs with full traceability.

    100 GitHub stars~2k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed
  • Bug To Patch Generator

    ArabelaTso/Skills-4-SE

    Generate code fixes and patches from bug reports, failing test cases, error messages, and stack traces.

    253 GitHub stars~4.4k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Fix The Class

    joetawil7/first-pass

    Bug-fix routine that fixes the whole class of bug, not just the reported instance.

    112 GitHub stars~1.5k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Dynamo Jira Ticket

    DynamoDS/Dynamo

    Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.

    2k GitHub stars~1.1k tokensUpdated today
    Testing & QAAuto-check passed
  • Offload

    imbue-ai/offload

    Activate when you see offload.toml in a repo, offload referenced in build targets (justfile, Makefile, scripts), or when you need to run a large test suite in parallel.

    125 GitHub stars~3.1k tokensUpdated 12 days ago
    Testing & QAAuto-check passed

More from avibebuilder/claude-prime

All 19 skills in this repo
  • Diagnose

    avibebuilder/claude-prime

    Investigate unexpected behavior and mysterious bugs. An agent skill from avibebuilder/claude-prime.

    120 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Frontend Design

    avibebuilder/claude-prime

    Builds distinctive, production-grade UIs that avoid generic AI aesthetics.

    120 GitHub stars~2.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Media Processor

    avibebuilder/claude-prime

    Specialized visual and multimedia processing tools. An agent skill from avibebuilder/claude-prime.

    120 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check: notes
  • Skill Creator

    avibebuilder/claude-prime

    A skill your agent uses when the user wants to work on a Claude Code skill file (SKILL.md): writing one from scratch, testing whether an existing one works well, running evals or benchmarks…

    120 GitHub stars~8.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Self Evolve

    avibebuilder/claude-prime

    The single config quality skill. An agent skill from avibebuilder/claude-prime.

    120 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed
  • Cook

    avibebuilder/claude-prime

    Implement, build, create, or add any feature, endpoint, page, component, or functionality.

    120 GitHub stars~970 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Fix

What does Fix do?

Fix bugs and broken behavior when there is enough evidence to act on a repair path. Fix is an agent skill from avibebuilder/claude-prime. Fix bugs and broken behavior when there is enough evidence to act on a repair path.

When should I use Fix?

Fix fits situations like: incorrect results; API failures (500; database exceptions; broken rendering.

How do I install Fix in Claude Code?

Run `npx skills add avibebuilder/claude-prime --skill fix -a claude-code`. Or copy the skill folder (.claude/skills/fix in avibebuilder/claude-prime) into .claude/skills/fix in your project. Claude Code loads it when a task matches its description.

How do I install Fix in Codex?

Run `npx skills add avibebuilder/claude-prime --skill fix -a codex`. Or copy the skill folder (.claude/skills/fix in avibebuilder/claude-prime) into .agents/skills/fix in your project. Codex loads it when a task matches its description.

Can I use Fix in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add avibebuilder/claude-prime --skill fix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fix, .gemini/skills/fix, .github/skills/fix and .opencode/skills/fix in your project.

What does Fix need to run?

SKILL.md names no scripts, command-line tools or credentials: Fix is instructions for the agent only.

Does Fix access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fix safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Fix use?

Fix is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fix use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fix?

Skills that share tags, products or a category with Fix: Bug Reproduction Test Generator (ArabelaTso/Skills-4-SE, 253 stars), Bug Fix (EmeaAppGbb/spec2cloud, 100 stars), Bug To Patch Generator (ArabelaTso/Skills-4-SE, 253 stars) and Fix The Class (joetawil7/first-pass, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fix?

avibebuilder (a GitHub organization) maintains it in avibebuilder/claude-prime, which has 120 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on May 16, 2026.

Source: avibebuilder/claude-prime on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.