New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

CI Fixer

by hex in hex/claude-council

A CI job fails on a named revision and the fix belongs in code, config or tests, not in the CI provider.

MITAuto-check passed

Install CI Fixer

skills CLI
$ npx skills add hex/claude-council --skill ci-fixer -a claude-code

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

GitHub CLI
$ gh skill install hex/claude-council ci-fixer --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/hex/claude-council.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mods/council-pane/specialists/ci-fixer .claude/skills/ci-fixer && 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
ci-fixer
GitHub stars
848
Token cost
~941 tokens
SKILL.md length
602 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

A CI job fails on a named revision and the fix belongs in code, config or tests, not in the CI provider.

  • Works in 4 steps: Work from the exact revision SHA, run ID… → Check that the run is still relevant. A… → Fetch the failed job's log once and keep… → …
  • SKILL.md covers Pin the failure, Classify before changing…, Reproduce and Fix, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

CI Fixer is an agent skill from hex/claude-council. A CI job fails on a named revision and the fix belongs in code, config or tests, not in the CI provider.

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Claude Code plugin that asks several AI coding agents the same question and shows their answers side by side. Gemini, OpenAI, Grok, Perplexity, Kimi and any model OpenRouter… The licence is MIT.

Example prompts

  • “/ci-fixer”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Work from the exact revision SHA, run ID and job named in the task. If the
  2. Check that the run is still relevant. A cancelled run is often superseded
  3. Fetch the failed job's log once and keep it. Work from that copy. Prefer
  4. Find the first real error, not the last line. Later errors are often

What it can do on your machine

Read from SKILL.md and the folder at commit 23867e1. 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

CI Fixer loads about 941 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 602 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~941

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 hex/claude-council at commit 23867e1, republished under its MIT licence (© hex). 602 words, ~941 tokens.

Download SKILL.mdSave it as .claude/skills/ci-fixer/SKILL.md (or your agent's skills folder).
name
ci-fixer
description
A CI job fails on a named revision and the fix belongs in code, config or tests, not in the CI provider.

CI Fixer

Make one failing CI job pass for the right reason. A green run earned by retrying, skipping or loosening a check is a failure of this task, not a success.

Pin the failure

  1. Work from the exact revision SHA, run ID and job named in the task. If the task names only a pull request or a branch, ask for them in the report rather than guessing which run is current.
  2. Check that the run is still relevant. A cancelled run is often superseded by a newer run on the same revision or branch. If the newest run passes, stop and report that.
  3. Fetch the failed job's log once and keep it. Work from that copy. Prefer the job's own status over a summary or rollup view.
  4. Find the first real error, not the last line. Later errors are often consequences.

Classify before changing anything

Put the failure in exactly one class and record the evidence for it:

  • product: the code under test is wrong. The same failure should reproduce locally or in CI's environment.
  • test harness: the test, fixture, helper or setup is wrong, flaky or order-dependent, and the product is fine.
  • environment: runtime version, OS difference, missing tool, dependency resolution, disk, network, cache. The code and test are fine on another environment.
  • credential: a secret, token, quota or permission is missing or expired. This is never fixable in code. Stop and report which credential and where the log shows it.

If the evidence does not settle the class, say so and report what would.

Reproduce

  • Run the failing command locally with the same arguments the job used.
  • If it passes locally, do not conclude the CI is wrong. Match CI's OS, runtime version, locale, timezone and environment variables, as far as you can, and try again. A local pass does not override a CI failure.
  • For a suspected flake, run the single test repeatedly and record the pass and fail count. Flaky means you saw it fail and pass on the same code.
Show full SKILL.md (261 more words)Show less

Fix

  • Fix the class you identified:
    • product: fix the code at the root cause, as a bug fix;
    • harness: fix the test or fixture so it is deterministic, keeping what it asserts;
    • environment: pin or update the version, cache key, or setup step in the repo's CI config.
  • Never skip, disable, mark as expected-failure, raise a timeout without a measured reason, loosen an assertion, or add a retry loop to make the job pass.
  • Keep changes to the job's failure. Record unrelated failures you notice in the report rather than fixing them.

Prove it

  • Run the reproduction again and show it passing.
  • For a flake fix, repeat the run enough times that the previous failure rate would have shown at least one failure, and record the count.
  • State plainly that the CI run itself has not re-run on your change. The tool records your work; CI results come afterwards.

Evidence to record

  • Revision, run ID, job name, and the first real error line.
  • The class and why.
  • Local reproduction command and its output, before and after.
  • For flakes: repeat counts before and after.

Stop conditions

Stop and report when the failure is a credential or provider-side problem, when the newest run already passes, when you cannot reproduce and cannot match CI's environment, or when the fix needs a change outside the repo.

Handoff

Report the class, the root cause, the change, the proof commands with results, and what still needs a real CI run to confirm.

CI triage steps adapted from openclaw's openclaw-testing and release-openclaw-ci skills (MIT, OpenClaw Foundation); see ../LICENSE-openclaw.

© hex, 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 mods/council-pane/specialists/ci-fixer of hex/claude-council.

Open the folder on GitHubat commit 23867e1

Compare with similar skills

CI Fixer 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.

CI Fixer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CI Fixer this skillhex/claude-council848—~941Automated safety check: PassMIT
Technical Job Searchgithub/awesome-copilot40k—~1.2kAutomated safety check: PassMIT
Job Application AssistantMadsLorentzen/ai-job-search45k1 repos~1.2kAutomated safety check: NotesMIT
Debug Failed Runactivepieces/activepieces25k—~3.7kAutomated safety check: WarnCustom licence
Python Background Jobswshobson/agents40k—~1.8kAutomated safety check: PassMIT
Fixer AutomationComposioHQ/awesome-claude-skills77k3 repos~723Automated safety check: PassNone

Similar skills

  • Technical Job Search

    github/awesome-copilot

    Official

    A skill your agent uses when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer…

    40k GitHub stars~1.2k tokensUpdated today
    Business, Finance & HRAuto-check passed

  • Job Application Assistant

    MadsLorentzen/ai-job-search

    Evaluates job postings against your profile, then tailors a LaTeX CV and cover letter and prepares interview answers for the roles you pursue.

    45k GitHub starsUsed in 1 repo~1.2k tokens
    Business, Finance & HRAuto-check: notes

  • Debug Failed Run

    activepieces/activepieces

    Debug a failed Activepieces flow run end-to-end: given a flow run id (or BullMQ job id), find why it failed, cross-referencing the live BullMQ job + Postgres rows (SSH script on the DevOps box), the…

    25k GitHub stars~3.7k tokensUpdated today
    DatabasesAuto-check: warnings

  • Python Background Jobs

    wshobson/agents

    Python background job patterns including task queues, workers, and event-driven architecture.

    40k GitHub stars~1.8k tokensUpdated 3 days ago
    Backend & APIsAuto-check passed

  • Fixer Automation

    ComposioHQ/awesome-claude-skills

    Automate Fixer tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~723 tokens
    Productivity & AutomationAuto-check passed

  • Git Branch Naming

    makeplane/plane

    Names a new Git branch with a type prefix, the lowercased work item ID and a short kebab-case description, so the ID can be extracted later from the branch name.

    61k GitHub stars~594 tokensUpdated today
    DevelopmentAuto-check passed

More from hex/claude-council

All 10 skills in this repo

  • Local Council Execution

    hex/claude-council

    Runs a local council when no external AI providers are configured.

    848 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Council Execution

    hex/claude-council

    Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of…

    848 GitHub stars~824 tokensUpdated yesterday
    Auto-check passed

  • Deep Execution

    hex/claude-council

    Executes agent-enhanced council queries as one Workflow of parallel Claude analyst agents that each query a provider, evaluate response quality, ask follow-up questions, and return a schema-enforced…

    848 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

  • Provider Integration

    hex/claude-council

    Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface.

    848 GitHub stars~635 tokensUpdated yesterday
    Auto-check passed

  • Bug Fixer

    hex/claude-council

    A bug reproduces, the expected behaviour is clear, and the fix stands apart from the current work.

    848 GitHub stars~991 tokensUpdated yesterday
    Auto-check passed

  • Docs Updater

    hex/claude-council

    Docs must be updated or restructured to match code that already changed: README, reference pages, CLI help or config docs.

    848 GitHub stars~930 tokensUpdated yesterday
    Auto-check passed

Questions about CI Fixer

What does CI Fixer do?

A CI job fails on a named revision and the fix belongs in code, config or tests, not in the CI provider. CI Fixer is an agent skill from hex/claude-council. A CI job fails on a named revision and the fix belongs in code, config or tests, not in the CI provider.

How do I install CI Fixer in Claude Code?

Run `npx skills add hex/claude-council --skill ci-fixer -a claude-code`. Or copy the skill folder (mods/council-pane/specialists/ci-fixer in hex/claude-council) into .claude/skills/ci-fixer in your project. Claude Code loads it when a task matches its description.

How do I install CI Fixer in Codex?

Run `npx skills add hex/claude-council --skill ci-fixer -a codex`. Or copy the skill folder (mods/council-pane/specialists/ci-fixer in hex/claude-council) into .agents/skills/ci-fixer in your project. Codex loads it when a task matches its description.

Can I use CI Fixer 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 hex/claude-council --skill ci-fixer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ci-fixer, .gemini/skills/ci-fixer, .github/skills/ci-fixer and .opencode/skills/ci-fixer in your project.

What does CI Fixer need to run?

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

Does CI Fixer 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 CI Fixer 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 CI Fixer use?

CI Fixer 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 CI Fixer use?

About 941 tokens (SKILL.md is roughly 3.8k 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 CI Fixer?

Skills that share tags, products or a category with CI Fixer: Technical Job Search (github/awesome-copilot, 40k stars), Job Application Assistant (MadsLorentzen/ai-job-search, 45k stars), Debug Failed Run (activepieces/activepieces, 25k stars) and Python Background Jobs (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CI Fixer?

hex (a GitHub user) maintains it in hex/claude-council, which has 848 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 6, 2026.

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