CI Debug

What it does

When your agent uses it

• A specific PR check
• GitHub Actions run failed and you want a diagnosis instead of speculation
• Org-wide CI sweeps (thats /status)
• For app-level test failures (the playbook is CI-infra-specific)

Example prompts

• “t use for org-wide CI sweeps (that”
• “/ci-debug”

Requirements

• Python 3
• Compatibility (from SKILL.md): Claude Code 2.1.277+ — uses `gh` CLI for GitHub Actions log inspection. Works in interactive sessions and headless `claude -p --bare` invocations (e.g. /ork:ci-sentinel).
• Pre-approved tools (allowed-tools): Bash, Read, Grep, Glob

Workflow steps

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

1. 1Resolve the failing job
2. 2Fetch the failing log
3. 3Classify against the playbook
4. 4Report

What it can do on your machine

Read from SKILL.md and the folder at commit 1f8d8f3. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Grep
  • Glob

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • gh
  • git
  • python
  • claude
  • pnpm
  • uv
  • node
  • python3

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

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • github.com

  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.

• Compatibility

  Claude Code 2.1.277+ — uses `gh` CLI for GitHub Actions log inspection. Works in interactive sessions and headless `claude -p --bare` invocations (e.g. /ork:ci-sentinel).

  From compatibility in the SKILL.md frontmatter.

Context cost

CI Debug loads about 2.7k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 1,006 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~108

When it runs · the whole SKILL.md, loaded when a task matches

~2.7k

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

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Grep, Glob

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 yonatangross/orchestkit at commit 1f8d8f3, republished under its MIT licence (© yonatangross). 1,006 words, ~2,718 tokens.

name

ci-debug

description

Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for org-wide CI sweeps (that's /status) or for app-level test failures (the playbook is CI-infra-specific).

allowed-tools

Bash, Read, Grep, Glob

compatibility

Claude Code 2.1.277+ — uses `gh` CLI for GitHub Actions log inspection. Works in interactive sessions and headless `claude -p --bare` invocations (e.g. /ork:ci-sentinel).

license

MIT

argument-hint

<PR-number | run-URL | job-URL>

context

fork

background

false

disable-model-invocation

false

user-invocable

true

skills

github-operations, memory

model

sonnet

metadata.category

workflow-automation

metadata.origin

/insights audit 2026-05-11 — recurring CI-debug pattern across 12 sessions in 3 weeks

# From PR number:
gh pr checks <n> --repo <owner>/<repo> --json bucket,link,name \
  --jq '.[] | select(.bucket=="fail") | "\(.name)|\(.link)"'

# From run URL:
gh api repos/<owner>/<repo>/actions/runs/<run-id>/jobs \
  --jq '.jobs[] | select(.conclusion=="failure")
                | {id, name, runner_name, started_at, completed_at,
                   steps: [.steps[] | select(.conclusion=="failure") | {name, number}]}'

gh api repos/<owner>/<repo>/actions/jobs/<job_id>/logs 2>&1 \
  | grep -iE '(error|fail|ERR_|CONFLICT|Process completed with exit code)' \
  | head -30

## CI Debug: <repo> · <pr-or-run-ref>

**Failing job:** `<job name>` (<duration>s) on runner `<runner_name>`
**Failing step:** <step name> (#<step number>)
**Error excerpt:**
\`\`\`
<first 3 lines of grep'd error>
\`\`\`

**Classification:** Pattern #<n> — <pattern name>
**Reference:** memory `<memory-file.md>`

**Proposed fix:**
<exact commands, one per line>

**Will I apply this?** No — awaiting your approval. Reply "go" to ship.

## CI Debug: <repo> · <pr-or-run-ref> · NOVEL

**Failing step:** <step name>
**Unique log lines:**
\`\`\`
<top 10 distinct error lines>
\`\`\`

This doesn't match any of the 11 playbook patterns. Surfacing the raw
evidence for your read. Once you identify the root cause, consider
adding it to the playbook (in this SKILL.md) so the next run catches
it automatically.

© yonatangross, 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 src/skills/ci-debug of yonatangross/orchestkit.

Open the folder on GitHubat commit 1f8d8f3