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

83%

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

100%

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, actionable, well-sequenced guide that fully leverages the simple-skill profile: executable commands, an explicit retry-until-green feedback loop, and clean section organization with no unnecessary padding.

Dimension	Reasoning	Score
Conciseness	The body is lean and every section earns its place; the 'gh pr checks' vs 'gh run list' distinction is useful tool-selection guidance rather than basic-concept padding Claude already knows.	3 / 3
Actionability	Provides concrete, executable commands such as 'gh pr view --json number,url,headRefName' and 'gh pr checks --watch --fail-fast' that are copy-paste ready.	3 / 3
Workflow Clarity	A clear numbered sequence pairs with an explicit feedback loop (step 5 re-checks and repeats until green) and error-recovery guardrails for flakes and unrelated failures.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references, the skill is well-organized into Trigger/Workflow/Commands/Guardrails/Output sections, meeting the simple-skill exception for a 3.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 occupies a distinct niche, but it omits an explicit 'Use when…' trigger clause and is missing common natural keywords like 'CI' and 'tests', which cap completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when CI checks on a PR are failing or pending and you need to iterate until they pass.'

Broaden trigger terms to include natural phrasings users say, such as 'CI', 'tests', 'build', and 'make checks green'.

Keep the concrete action list but pair it with the when-trigger so the description answers both 'what' and 'when' explicitly.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Monitor PR checks', 'fix failures', 'until green') and a specific tool ('gh pr checks'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers 'what' but lacks any explicit 'Use when…' trigger clause for when to invoke the skill, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Includes natural terms like 'PR checks' and 'failures', but omits common variations users would say such as 'CI', 'tests', or 'build', fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (PR-attached check monitoring) and distinguishes itself via the 'gh pr checks as the source of truth' framing, making it unlikely to trigger for unrelated skills.	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/loop-on-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.