loop-on-ci

Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

Quality

75%

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/loop-on-ci/SKILL.md

Quality

Content

85%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 a tight, well-structured operational guide with executable commands and a clear validation-rich feedback loop. Minor trimming of the repeated check command and a note on non-GHA diagnosis would push it to full marks.

Suggestions

Replace the verbatim repeat in Guardrails with a short reference (e.g. "Re-run `gh pr checks --json ...` after every push") to remove the duplicated token cost.

Add a brief pointer for diagnosing failures from non-GitHub-Actions checks (e.g. following the check's `link`), since the only diagnosis command targets GHA runs.

Consider noting where to find required-checks vs informational-checks (e.g. `gh pr checks --json name,bucket` plus required status context) so the "until green" target is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no concept over-explanation, but the full command "gh pr checks --json name,bucket,state,workflow,link" is repeated verbatim in both Commands and Guardrails and could be trimmed.	4 / 5
Actionability	The Commands section provides concrete, executable gh commands with real flags and the workflow maps to them, but diagnosis guidance only covers GitHub Actions logs (gh run view --log-failed), leaving a minor gap for non-GHA failing checks.	4 / 5
Workflow Clarity	The 5-step workflow has a clear sequence with explicit validation checkpoints (inspect before waiting, re-check after every push) and a feedback loop (repeat until green, retry flaky once), matching the anchor for explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	This is a simple, under-50-line skill with no need for external references, and it is organized into well-signaled sections (Trigger, Workflow, Commands, Guardrails, Output), which per the guidelines earns a 5.	5 / 5
	Total	18 / 20 Passed

Description

65%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, specific, and clearly distinct, but it omits an explicit trigger/"Use when" clause, which caps its completeness. It reads in third person with no over-claims.

Suggestions

Add an explicit trigger clause, e.g. "Use when a PR's checks are failing or pending and you need to iterate until all required checks are green."

Include common synonyms users say ("CI", "tests") alongside "PR checks" to broaden natural trigger coverage.

Consider enumerating one more concrete action (e.g. "re-run failed checks") to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Monitor PR checks and fix failures until green" names the domain and two concrete actions (monitor, fix failures), but the action set is not comprehensive — it stops at two rather than listing several specific actions.	3 / 5
Completeness	There is a clear "what" (monitor PR checks and fix failures until green) but no explicit "Use when..." trigger clause, so per the judging guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural user-facing phrases like "PR checks", "failures", and "until green" are present and would be said by a user needing this skill, though common synonyms like "CI" or "tests" are absent.	4 / 5
Distinctiveness Conflict Risk	The PR-checks monitoring loop with a specific source-of-truth tool (gh pr checks) is a clear, narrow niche with minimal overlap risk against other skills.	5 / 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/loop-on-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.