fix-ci

Find failing PR checks, inspect logs or external check links, and apply focused fixes

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise, well-structured, and has a clear iterative feedback loop, but the fix-application step is abstract and would benefit from concrete examples.

Suggestions

Add one or two concrete fix examples in the workflow (e.g., retrying a flaky job, fixing a lint/type error) to lift actionability.

Optionally note how to get job logs specifically (e.g. 'gh run view --log') to make log inspection more executable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence; it gives a concrete gh command and minimal prose with no padding or explanation of concepts Claude already knows, matching the 3-anchor 'every token earns its place'.	3 / 3
Actionability	Provides one executable command ('gh pr checks --json name,bucket,state,workflow,link') but the fix step is generic ('Apply the smallest safe fix') with no concrete examples of common fixes, fitting the 2-anchor 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	The four-step workflow is clearly sequenced with an explicit feedback loop — push, re-check, 'repeat until green' — which is a validation checkpoint for an iterative CI operation, matching the 3-anchor.	3 / 3
Progressive Disclosure	A simple under-50-line skill with well-organized sections (Trigger, Workflow, Guardrails, Output) and no external references needed; per the rubric's simple-skills note this can score 3 with just well-organized sections.	3 / 3
	Total	11 / 12 Passed

Description

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.

The description is specific and clearly distinct, but lacks an explicit 'Use when...' trigger clause and broad natural trigger-term coverage, which cap completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a PR's CI is failing or checks are red and you need to get them green.'

Broaden natural trigger terms to include 'CI', 'red checks', 'build failures', and 'broken tests' that users commonly say.

Keep the concrete action list but tie it to the trigger so both 'what' and 'when' are explicit.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — 'Find failing PR checks', 'inspect logs or external check links', 'apply focused fixes' — comparable to the 3-anchor example that lists multiple specific actions.	3 / 3
Completeness	Clearly states what the skill does but provides no 'Use when...' clause; the trigger is only implied by the phrase 'failing PR checks', which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes relevant natural terms like 'failing PR checks', 'logs', and 'check links', but lacks common variations users would say such as 'CI', 'red checks', 'broken tests', or 'build failure', so it is not full coverage.	2 / 3
Distinctiveness Conflict Risk	The CI-fix niche is narrow and unlikely to overlap with unrelated skills; the trigger ('failing PR checks') is distinct, matching the 3-anchor 'clear niche' example.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cursor/plugins
Path: cursor-team-kit/skills/fix-ci/SKILL.md
Commit: fe77e77

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.