ci-fix
Diagnose and fix GitHub Actions CI failures. Inspects workflow runs and logs, identifies root causes, implements minimal fixes, and pushes to a fix branch. Use when CI is failing, red, broken, or needs diagnosis.
97
96%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does (diagnose and fix CI failures via inspecting logs, identifying root causes, implementing fixes) and when to use it (CI failing/red/broken). It uses natural trigger terms and is well-scoped to a distinct niche of GitHub Actions CI troubleshooting.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Inspects workflow runs and logs, identifies root causes, implements minimal fixes, and pushes to a fix branch.' These are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers both what ('Diagnose and fix GitHub Actions CI failures. Inspects workflow runs and logs, identifies root causes, implements minimal fixes, and pushes to a fix branch') and when ('Use when CI is failing, red, broken, or needs diagnosis'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'GitHub Actions', 'CI failures', 'CI is failing', 'red', 'broken', 'diagnosis', 'workflow runs'. These cover natural variations of how users would describe CI problems. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to GitHub Actions CI failures specifically, with distinct triggers like 'workflow runs', 'CI', 'fix branch'. Unlikely to conflict with general coding or git skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that provides a clear, actionable workflow for diagnosing and fixing CI failures. It excels at conciseness and actionability with concrete gh/git commands at every step, and the workflow includes proper validation checkpoints. The only minor weakness is that all content is inline, though for a skill of this size it's largely appropriate.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. Every section serves a purpose, commands are concrete without unnecessary explanation, and it doesn't explain concepts Claude already knows (like what CI is or how git works). The common failure patterns list is appropriately brief. | 3 / 3 |
Actionability | Every step includes specific, copy-paste-ready `gh` and `git` commands. The workflow covers the full lifecycle from diagnosis to verification with concrete command examples, branch naming conventions, and commit message formats. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit validation in step 6 (verify the fix via `gh run watch --exit-status`). It includes a feedback loop for rerunning failed jobs and handles both new and existing fix branches. The prerequisite auth check is a good upfront validation gate. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but everything is inline in a single file. At ~100 lines it's borderline—the safety notes and deliverable template could arguably stay inline, but the common failure patterns section could benefit from linking to a more detailed troubleshooting reference for complex cases. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- warpdotdev/oz-skills
- Commit
6c08c49
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.