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

Fixing CI

by ReviewStage in ReviewStage/stage-cli

A skill your agent uses when CI is failing on a branch and you need to diagnose failures from GitHub, fix them locally with iterative verification, and re-push clean commits.

MITAuto-check passedDevelopment

Install Fixing CI

skills CLI
$ npx skills add ReviewStage/stage-cli --skill fixing-ci -a claude-code

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

GitHub CLI
$ gh skill install ReviewStage/stage-cli fixing-ci --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/ReviewStage/stage-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/fixing-ci .claude/skills/fixing-ci && 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
fixing-ci
GitHub stars
274
Token cost
~977 tokens
SKILL.md length
409 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when CI is failing on a branch and you need to diagnose failures from GitHub, fix them locally with iterative verification, and re-push clean commits.

  • Works in 4 steps: Diagnose → Fix Loop (repeat per failure) → Verify All Checks (gate before push) → …
  • CI is failing on a branch and you need to diagnose failures from GitHub
  • SKILL.md covers Overview, Workflow, Step 1: Diagnose and Step 2: Fix Loop (repeat per…, plus 3 more sections
  • Calls pnpm, git and gh

What it does

Fixing CI is an agent skill from ReviewStage/stage-cli. Use when CI is failing on a branch and you need to diagnose failures from GitHub, fix them locally with iterative verification, and re-push clean commits.

Its SKILL.md is about 980 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 Development. It works with GitHub and pnpm. The repository describes itself as: A viewer for reviewing local code changes in small individual chapters. Works with any AI agent. The licence is MIT.

When your agent uses it

  • CI is failing on a branch and you need to diagnose failures from GitHub
  • Fix them locally with iterative verification
  • Re-push clean commits

Example prompts

  • “/fixing-ci”

Workflow steps

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

  1. Diagnose
  2. Fix Loop (repeat per failure)
  3. Verify All Checks (gate before push)
  4. Push

What it can do on your machine

Read from SKILL.md and the folder at commit 59b977b. 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

    Shell commands in SKILL.md call:

    • pnpm
    • git
    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, git and gh, which can reach the network depending on how they are called.

    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

Fixing CI loads about 977 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 409 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~977

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 ReviewStage/stage-cli at commit 59b977b, republished under its MIT licence (© ReviewStage). 409 words, ~977 tokens.

Download SKILL.mdSave it as .claude/skills/fixing-ci/SKILL.md (or your agent's skills folder).
name
fixing-ci
description
Use when CI is failing on a branch and you need to diagnose failures from GitHub, fix them locally with iterative verification, and re-push clean commits.
metadata.internal
true

Fixing CI

Overview

Diagnose failing CI from GitHub logs, fix each issue with an atomic commit, and iterate locally until the full suite is green — then push once.

Principle: One fix, one commit. Never push until all checks pass locally.

Workflow

1. DIAGNOSE      → Pull failure logs from GitHub, list all failures
2. For each failure:
   a. REPRODUCE  → Run the failing check locally to confirm you see it
   b. FIX        → Fix root cause (not downstream symptoms)
   c. VERIFY FIX → Re-run the check to confirm it passes
   d. COMMIT     → Atomic commit for this fix
3. VERIFY ALL    → Run the full suite locally
   ↳ If anything fails → go back to step 2
   ↳ All green → proceed
4. PUSH          → Push all commits

Step 1: Diagnose

bash
# See recent CI runs on current branch
gh run list --branch $(git branch --show-current) --limit 5

# View failing run (find run-id from above)
gh run view <run-id>

# Stream logs from only the failed steps
gh run view <run-id> --log-failed

Read top-to-bottom and list all distinct failures before fixing any of them. Find the first error in each job — not symptoms that cascade from it.

Step 2: Fix Loop (repeat per failure)

a. Reproduce

Check the project's AGENTS.md for exact commands. Common mappings:

CI JobTypical Local Command
Lintpnpm lint
Typecheckpnpm typecheck
Testspnpm test
Buildpnpm build

Run the failing check and confirm you see the same error locally before touching code.

b. Fix
  • Fix the root cause — lint errors often cascade from a single type error upstream
  • Don't fix just to silence the error; understand why it's wrong
  • If the fix is unclear, read the relevant library docs or AGENTS.md before guessing
c. Verify the Fix

Re-run the specific check to confirm it passes before committing.

d. Commit
bash
git add -p                          # Review every hunk before staging
git commit -m "fix: <what broke>"   # Specific message, not "fix CI"

Use git add -p to catch accidental debug code or unrelated changes. Then loop back to the next failure.

Step 3: Verify All Checks (gate before push)

After all individual fixes are committed, run the full suite:

bash
# Run all checks (adapt to project — check AGENTS.md)
pnpm lint && pnpm typecheck && pnpm test && pnpm build

If anything fails here, go back to step 2. A fix in one area can break another. Do not push until this full pass is clean.

Show full SKILL.md (170 more words)Show less

Step 4: Push

Only push once the full suite is green locally:

bash
git push

STOP here. Do not poll GitHub to check if CI passed remotely. Local verification is sufficient — if all checks pass locally, the push is done. Only revisit if the user explicitly reports CI is still failing, then start from Step 1 with the new run ID.

Common Mistakes

  • Polling GitHub after pushing — do NOT run gh run list, gh run watch, or any GitHub polling after pushing. Local green = done.
  • Pushing before the full suite passes — the verify-all step is a hard gate, not optional
  • One giant commit — commit after each fix; atomic history is easier to bisect
  • Pushing without reproducing locally — if you can't reproduce it, you can't verify the fix
  • Fixing symptoms not root cause — a cascade of 10 lint errors is often one bad import
  • Vague commit messages — "fix CI" is useless; "fix: remove unused import breaking typecheck" is not
  • Staging with git add . — use git add -p to review and avoid committing debug code

© ReviewStage, 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 .agents/skills/fixing-ci of ReviewStage/stage-cli.

Open the folder on GitHubat commit 59b977b

Compare with similar skills

Fixing CI 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.

Fixing CI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fixing CI this skillReviewStage/stage-cli274—~977Automated safety check: PassMIT
Verdaccio Pull Request Workflowverdaccio/verdaccio18k—~1.9kAutomated safety check: PassMIT
Verdaccio PR Reviewverdaccio/verdaccio18k—~1.7kAutomated safety check: PassMIT
Difit Reviewyoshiko-pg/difit3.2k—~764Automated safety check: PassMIT
ZCF Release AutomationUfoMiao/zcf6.1k—~3.4kAutomated safety check: PassMIT
Linea Dependency MaintenanceConsensys-Incorporated/linea-attestation-registry1771 repos~3.7kAutomated safety check: WarnMIT

Similar skills

  • Verdaccio Pull Request Workflow

    verdaccio/verdaccio

    Takes a change through a verdaccio pull request: branch, local checks, changeset, title and body, labels, CI and review rounds, and ports to other release lines.

    18k GitHub stars~1.9k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Verdaccio PR Review

    verdaccio/verdaccio

    Reviews an existing verdaccio/verdaccio pull request end to end, verifies each finding and reports whether it is mergeable, optionally fixing it on the PR branch.

    18k GitHub stars~1.7k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Difit Review

    yoshiko-pg/difit

    A skill for reviewing a specific diff and showing the findings as comments inside difit (the diff viewer).

    3.2k GitHub stars~764 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • ZCF Release Automation

    UfoMiao/zcf

    Automates a version release with changesets: analyzes code changes, writes a bilingual CHANGELOG, bumps the version and commits through a release branch and pull request.

    6.1k GitHub stars~3.4k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Linea Dependency Maintenance

    Consensys-Incorporated/linea-attestation-registry

    Safely plan and execute dependency maintenance for JavaScript/TypeScript (npm, pnpm) and GitHub Actions, including npm lockfiles, pnpm workspaces, catalogs, overrides, SHA-pinned action versions…

    177 GitHub starsUsed in 1 repo~3.7k tokens
    DevelopmentAuto-check: warnings

  • Release

    seasonedcc/remix-forms

    Release a new version of the remix-forms npm package. An agent skill from seasonedcc/remix-forms.

    514 GitHub stars~1.3k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed

More from ReviewStage/stage-cli

All 10 skills in this repo

  • Fixing PR Comments

    ReviewStage/stage-cli

    A skill your agent uses when a pull request has unresolved review comments that need to be addressed, or when asked to fix PR feedback

    274 GitHub stars~953 tokensUpdated 1 mo ago
    Auto-check passed

  • Iterate PR

    ReviewStage/stage-cli

    A skill your agent uses when a PR is open and the user wants to autonomously monitor and fix PR review comments, CI failures, and rebase conflicts on a recurring loop, or when asked to…

    274 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Linear Issue

    ReviewStage/stage-cli

    A skill your agent uses when creating a Linear issue from the current coding context, or when the user invokes /linear-issue.

    274 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

  • Quality Review

    ReviewStage/stage-cli

    A skill your agent uses when reviewing code changes against AGENTS.md implementation quality standards, or when asked to do an implementation quality review

    274 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Rebase Origin Main

    ReviewStage/stage-cli

    A skill your agent uses when rebasing the current branch onto origin/main, including resolving merge conflicts along the way

    274 GitHub stars~927 tokensUpdated 1 mo ago
    Auto-check passed

  • Trade Off

    ReviewStage/stage-cli

    Use at any stage — planning, before implementing, or reviewing code that's already written — to surface high-level trade-offs that could significantly simplify the work.

    274 GitHub stars~3k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Fixing CI

What does Fixing CI do?

A skill your agent uses when CI is failing on a branch and you need to diagnose failures from GitHub, fix them locally with iterative verification, and re-push clean commits. Fixing CI is an agent skill from ReviewStage/stage-cli. Use when CI is failing on a branch and you need to diagnose failures from GitHub, fix them locally with iterative verification, and re-push clean commits.

When should I use Fixing CI?

Fixing CI fits situations like: CI is failing on a branch and you need to diagnose failures from GitHub; fix them locally with iterative verification; re-push clean commits.

How do I install Fixing CI in Claude Code?

Run `npx skills add ReviewStage/stage-cli --skill fixing-ci -a claude-code`. Or copy the skill folder (.agents/skills/fixing-ci in ReviewStage/stage-cli) into .claude/skills/fixing-ci in your project. Claude Code loads it when a task matches its description.

How do I install Fixing CI in Codex?

Run `npx skills add ReviewStage/stage-cli --skill fixing-ci -a codex`. Or copy the skill folder (.agents/skills/fixing-ci in ReviewStage/stage-cli) into .agents/skills/fixing-ci in your project. Codex loads it when a task matches its description.

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

What does Fixing CI need to run?

Going by SKILL.md and its folder, Fixing CI needs the command-line tools its instructions call (pnpm, git and gh).

Does Fixing CI access the network?

SKILL.md contains no URLs. Its commands use git and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Fixing CI 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 Fixing CI use?

Fixing CI 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 Fixing CI use?

About 977 tokens (SKILL.md is roughly 3.9k 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 Fixing CI?

Skills that share tags, products or a category with Fixing CI: Verdaccio Pull Request Workflow (verdaccio/verdaccio, 18k stars), Verdaccio PR Review (verdaccio/verdaccio, 18k stars), Difit Review (yoshiko-pg/difit, 3.2k stars) and ZCF Release Automation (UfoMiao/zcf, 6.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fixing CI?

ReviewStage (a GitHub organization) maintains it in ReviewStage/stage-cli, which has 274 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 7, 2026.

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