Diagnose CI

Diagnostic executor for CI failures. ALWAYS invoke this skill when instructed to diagnose CI failures. Do not fetch CI logs directly — use this skill first to load the diagnosis workflow.

5 stars 1 forksProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TalonT-Org/AutoSkillit --skill diagnose-ci
Manual install
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/diagnose-ci ~/.claude/skills/diagnose-ci

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# diagnose-ci Skill

Fetch CI logs for a failing branch, classify the failure type, and write a structured
diagnosis report to `{{AUTOSKILLIT_TEMP}}/diagnose-ci/`. Called by the orchestrator on `ci_watch` failure
before routing to `resolve-failures`.

## Invocation

```
/autoskillit:diagnose-ci {branch} [run_id] [ci_failed_jobs] [workflow] [event]
```

**Positional args:**
- `branch` — the git branch whose CI run to investigate
- `run_id` (optional) — specific workflow run ID; if absent, discover from `gh run list`
- `ci_failed_jobs` (optional) — JSON array of failed job names from `wait_for_ci`, used to scope log fetching
- `workflow` (optional) — workflow filename (e.g. `tests.yml`); if provided, scopes `gh run list` to that workflow only; use `-` to skip
- `event` (optional) — GitHub Actions trigger event (e.g. `push`, `pull_request`); if provided, scopes `gh run list` to that event only; use `-` to skip

## Critical Constraints

**NEVER:**
- Modify any source code files
- Run the test suite
- Write files outside `{{AUTOSKILLIT_TEMP}}/diagnose-ci/`
- Block on missing `gh` CLI — write a minimal `failure_type=unknown` diagnosis instead

**ALWAYS:**
- Write the diagnosis file before emitting output tokens
- Emit the four output tokens (`diagnosis_path`, `failure_type`, `failure_subtype`, `is_fixable`) at the end of the response on their own lines

## Context Limit Behavior

When context is exhausted mid-execution, the diagnosis file may be partially written
Read the full skill on GitHub

Details

Skill name
diagnose-ci
Path
src/autoskillit/skills_extended/diagnose-ci/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Diagnose CI skill do?

Diagnostic executor for CI failures. ALWAYS invoke this skill when instructed to diagnose CI failures. Do not fetch CI logs directly — use this skill first to load the diagnosis workflow.

How do I install the Diagnose CI skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill diagnose-ci. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Diagnose CI popular?

It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.

Related skills

Analyze Prs

5

TalonT-Org/AutoSkillit

Analyze all open PRs targeting a base branch — determine merge order, identify file overlaps, and tag each PR as simple or needs_check for complexity. Use at the start of a PR consolidation workflow.

Git & Code Review

Arch Lens C4 Container

5

TalonT-Org/AutoSkillit

Create C4 Container architecture diagram showing static structure, building blocks, and technology choices. Anatomical lens answering "How is it built?

Software Development

Arch Lens Concurrency

5

TalonT-Org/AutoSkillit

Create Concurrency architecture diagram showing parallel execution patterns, thread pools, synchronization, and barriers. Physiological lens answering "How does parallelism work?

Software Development

Dry Walkthrough

5

TalonT-Org/AutoSkillit

Plan validation executor. ALWAYS invoke this skill when instructed to validate or dry-walkthrough a plan. Do not read the plan or trace changes directly — use this skill first to load the validation workflow.

Productivity & Notes

Audit Friction

5

TalonT-Org/AutoSkillit

Scan Claude Code project logs for friction patterns — repeated failures, approach loops, tool errors, misunderstanding cycles, and stuck workflows. Categorizes and counts friction events to surface what causes the most resistance. Use when user says "audit friction", "find friction", "friction audit", or "what keeps going wrong".

Productivity & Notes

Make Plan

5

TalonT-Org/AutoSkillit

Planning executor. ALWAYS invoke this skill when instructed to create, devise, or write an implementation plan. Do not explore the codebase or draft a plan directly — use this skill first to load the planning workflow.

Productivity & Notes

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.