fix-ci

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

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./cursor-team-kit/skills/fix-ci/SKILL.md

Quality

Content

86%Weight 40%Scale 1-5

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

The content is lean, well-structured, and gives a concrete entry-point command plus an explicit re-check feedback loop. The main gap is that the actual fix step is abstract with no example fix patterns, which limits actionability and workflow validation granularity.

Suggestions

Add one or two concrete example fix patterns (e.g., a flaky-test retry, a config typo correction) to make the fix step more actionable.

Insert an explicit validation checkpoint before re-push (e.g., confirm the fix addresses the extracted root error) to push workflow clarity toward 5.

Optionally note the "repeat until green" loop should stop or escalate after N failed iterations to bound the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean (~30 lines), assumes Claude's competence, and never pads with explanations of what CI or GitHub Actions is; every line earns its place, matching the lean-and-efficient anchor.	5 / 5
Actionability	Provides a copy-paste-ready command ("gh pr checks --json name,bucket,state,workflow,link") and concrete inspection steps, but "Apply the smallest safe fix" stays abstract with no example fix pattern; matches mostly-executable guidance with minor gaps, not a 5 because specific examples don't cover common cases.	4 / 5
Workflow Clarity	A clear 4-step sequence with an explicit feedback loop in step 4 ("Push, re-check the PR check set, and repeat until green"), but it lacks a granular validation checkpoint confirming the fix targets the root error before re-push; not a 5 because validation is a single loop rather than per-step checkpoints.	4 / 5
Progressive Disclosure	A simple single-purpose skill under 50 lines with no need for external references and well-organized sections (Trigger, Workflow, Guardrails, Output); per the scoring notes this qualifies for a 5 on well-organized structure alone.	5 / 5
	Total	18 / 20 Passed

Description

66%Weight 40%Scale 1-5

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 concise and names concrete actions in a distinct niche, but it omits an explicit "Use when..." trigger clause, which caps completeness. Adding trigger phrasing (e.g., "Use when PR/branch CI checks are failing") would raise both completeness and distinctiveness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when CI checks, PR checks, or the build are failing') to lift completeness above 3.

Include common synonyms users say ('CI', 'build', 'tests', 'red checks') to improve trigger-term coverage toward 5.

Tighten the fix-action wording with a concrete example fix pattern to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the CI/PR-check domain and three concrete actions ("Find failing PR checks", "inspect logs or external check links", "apply focused fixes"), matching the anchor for several specific actions with minor gaps; not a 5 because coverage of fix types is not comprehensive.	4 / 5
Completeness	Has a clear "what" but no explicit "Use when..." trigger clause, so per the judging guideline completeness is capped at 3; not a 4 because the "when" is only weakly implied, not stated.	3 / 5
Trigger Term Quality	Includes natural terms users say ("PR checks", "failing", "logs", "fixes") but misses common variations like "CI", "build", or "tests", fitting good-but-not-comprehensive keyword coverage; not a 3 because the present terms are clearly natural, not a 5 because key synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear CI-fixing niche with distinct triggers (PR checks, failing checks), mostly distinct from other skills with only minor overlap risk against general debugging; not a 5 because "apply focused fixes" is generic and no explicit trigger phrasing reinforces the niche.	4 / 5
	Total	15 / 20 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: 51a96e0

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.