fix-ci-failures SKILL.md skillA

fix-ci-failures from leek/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add leek/agent-skills/fix-ci-failures@git:20261020.99d744d

Pins git:20261020.99d744d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
leek/agent-skills
Path
skills/fix-ci-failures/SKILL.md
Versions recorded
8
Latest version
git:20261020.99d744d, committed Oct 20, 2026
First version recorded
Sep 27, 2026
Size
5,793 bytes
Repository stars
4
License
MIT

Read a branch's latest failed CI runs, triage each failure from its existing logs, and fix the real ones.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Fix CI Failures

Take the branch named in the input, or `main` when none is given. Find its most recent
CI failures, triage each one from the logs that **already exist**, and fix what is
real. The logs are the whole evidence: CI is a record you read, never a thing you
trigger. Your own proof that a fix works is the failing command run green locally.
Text after the branch name is overriding guidance.

**Project context.** Follow the repo's `AGENTS.md` / `CLAUDE.md` rules for tests, lint,
cache clears, and a dirty tree.

## 1. Find the latest failures

Run `git fetch origin`. For each workflow, take only its newest **completed** run on the
branch that was not cancelled, looking back at most 10 runs. An older failure whose
workflow has passed since is already fixed, and a run still in progress or cancelled is
not evidence: skip them. A workflow whose last 10 completed runs were all cancelled
comes back as `all_cancelled`: report it with no verdict, since it has no log to triage.

```bash
gh run list --branch B --status completed --limit 100 \
  --json databaseId,workflowName,conclusion,headSha,createdAt,url \
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add leek/agent-skills/fix-ci-failures@sha256:d8a8cb8eb63e4063

The line at the top of this page pins the label git:20261020.99d744d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_aaqruytl7xe2xmgn.svg)](https://markdownregistry.com/a/art_aaqruytl7xe2xmgn)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 8 versions of this file, between Sep 27, 2026 and Oct 20, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20261020.99d744d latest2026-10-20 99d744d 5,793 BA view · diff
git:20261020.7c18a102026-10-20 7c18a10 5,428 BA view · diff
git:20261019.0f2f3852026-10-19 0f2f385 5,359 BA view · diff
git:20261017.6acb87d2026-10-17 6acb87d 5,268 BA view · diff
git:20261004.e735c0a2026-10-04 e735c0a 4,294 BA view · diff
git:20261002.c185c742026-10-02 c185c74 4,172 BA view · diff
git:20261002.64f505f2026-10-02 64f505f 3,969 BA view · diff
git:20260927.4b0fe7c2026-09-27 4b0fe7c 3,881 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5793 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

leek/agent-skills · 4 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_aaqruytl7xe2xmgn
GET https://markdownregistry.com/api/v1/resolve?ref=leek/agent-skills/fix-ci-failures
GET https://markdownregistry.com/api/v1/blob/d8a8cb8eb63e40637ca9e816b96710d3c088c90d724ee1ea3a9eab1969ac09e3

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from leek/agent-skills

AGENTS.md AGENTS.md file
leek/agent-skills · AGENTS.md
git:20261020.7c18a10 · audit A · 4 stars
CLAUDE.md CLAUDE.md file
leek/agent-skills · CLAUDE.md
git:20260506.52cef56 · audit B · 4 stars
architecture-satisfaction SKILL.md skill
leek/agent-skills · skills/architecture-satisfaction/SKILL.md · Run a bounded architectural refactor loop toward a stated design.
git:20261019.0f2f385 · audit A · 4 stars
autopilot SKILL.md skill
leek/agent-skills · skills/autopilot/SKILL.md · Drive an existing wayfinder map, spec, or set of tickets to completion through fresh top-level Claude Code, Codex, or…
git:20261006.cae3ac3 · audit A · 4 stars
browser-test SKILL.md skill
leek/agent-skills · skills/browser-test/SKILL.md · Test a web app from a start URL and a plain-language prompt. A planner splits the prompt into cases, cheap parallel…
git:20261011.ab699a5 · audit A · 4 stars
chatter-scout SKILL.md skill
leek/agent-skills · skills/chatter-scout/SKILL.md · Sweep the web for new chatter on a topic, skip what earlier runs already saw, verify what is left, and write one…
git:20261011.024ee5c · audit A · 4 stars
closeout SKILL.md skill
leek/agent-skills · skills/closeout/SKILL.md · Check whether this session is safe to close: unsaved work, running jobs, open PRs, unanswered questions, and steps…
git:20261020.609a4bb · audit A · 4 stars
code-review SKILL.md skill
leek/agent-skills · skills/code-review/SKILL.md · Three-axis review of the diff since a fixed point: Correctness (bugs, failure modes, security), Standards (repo…
git:20261012.631a831 · audit A · 4 stars
code-smells-audit SKILL.md skill
leek/agent-skills · skills/code-smells-audit/SKILL.md · Audit a codebase, path, or branch diff for classic code smells against the 56-smell Luzkan catalog (PHP/Laravel and…
git:20261006.cae3ac3 · audit A · 4 stars
codebase-design SKILL.md skill
leek/agent-skills · skills/codebase-design/SKILL.md · Shared vocabulary for designing deep modules in any codebase. Use when the user wants to design or improve a class or…
git:20261006.192f5aa · audit A · 4 stars
commit SKILL.md skill
leek/agent-skills · skills/commit/SKILL.md · Commit the work done in this session, skipping files a parallel session also touched.
git:20261006.cae3ac3 · audit A · 4 stars
dependency-audit SKILL.md skill
leek/agent-skills · skills/dependency-audit/SKILL.md · Run a dependency audit for Composer or npm projects and propose a safe upgrade plan.
git:20261006.cae3ac3 · audit A · 4 stars

Every file in leek/agent-skills

Browse by kind, by grade A, or by owner.