Skip to content
Agentmart
Submit a tool

fix-ci

Fetch the CI status for the current PR or branch, pull the failing run logs via the GitHub API, diagnose the failure, reproduce it locally, fix it, and push.

Skill by ding113

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ding113-fix-ci

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Fetch the CI status for the current PR or branch, pull the failing run logs via the GitHub API, diagnose the failure, reproduce it locally, fix it, and push. Use when the user says CI is red, checks are failing, the build is broken, or asks to fix CI.

Use cases: backend, devops

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/fix-ci

What's inside

Skill name
fix-ci
Description
Fetch the CI status for the current PR or branch, pull the failing run logs via the GitHub API, diagnose the failure, reproduce it locally, fix it, and push. Use when the user says CI is red, checks are failing, the build is broken, or asks to fix CI.
License
MIT
Instructions
11 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

> **Draft** — scope agreed, behavior not yet written. Do not rely on this skill yet.

The planned loop:

1. **Status** — `gh pr checks` / `gh run list` for the current PR or branch; pick the failing runs.
2. **Logs** — pull the failing job logs via `gh api`, and extract the first real error rather than the last.
3. **Diagnose** — separate root cause from cascade noise; classify it (code, test, config, flake, infra).
4. **Reproduce locally** — run the same command the workflow runs; a fix is only trusted once the failure has been seen locally.
5. **Fix and push** — the smallest fix that addresses the root cause; push; watch the new run until green. Flakes get re-run and reported, not papered over.

From ding113/skills, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 15, 2026 (3 months ago)
Last release
Jul 15, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ding113

Cite this page

fix-ci skill. Agent Mart. https://agentmart.dev/skills/ding113-fix-ci (last updated 2026-10-24)