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

78%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./cursor-team-kit/skills/loop-on-ci/SKILL.md

Quality

Discovery

57%

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 communicates a clear purpose—monitoring and fixing PR check failures—and identifies a specific tool (gh pr checks), giving it good distinctiveness. However, it lacks an explicit 'Use when...' clause and could benefit from more natural trigger terms users might say (e.g., 'CI failing', 'build broken', 'tests not passing'). The specificity of concrete actions is also somewhat limited.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to fix failing CI, get PR checks to pass, or debug build/test failures on a pull request.'

Include more natural trigger terms users would say: 'CI', 'pipeline', 'build failing', 'tests failing', 'GitHub Actions', 'checks not passing'.

List more specific concrete actions, e.g., 'Reads CI logs, identifies failing steps, applies code fixes, and pushes commits until all checks pass.'

Dimension	Reasoning	Score
Specificity	Names the domain (PR checks) and some actions (monitor, fix failures), but doesn't list specific concrete actions like 'analyze CI logs', 'push fixes', 'rerun flaky tests', etc.	2 / 3
Completeness	Clearly answers 'what' (monitor PR checks and fix failures) but lacks an explicit 'Use when...' clause. The when is only implied by the nature of the task.	2 / 3
Trigger Term Quality	Includes relevant terms like 'PR checks', 'gh pr checks', 'failures', and 'green', but misses common user variations like 'CI', 'pipeline', 'build failing', 'tests failing', 'GitHub Actions', 'check status'.	2 / 3
Distinctiveness Conflict Risk	The focus on PR checks specifically via 'gh pr checks' and the goal of getting checks to green creates a clear, distinct niche that is unlikely to conflict with other skills.	3 / 3
	Total	9 / 12 Passed

Implementation

100%

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

This is a well-crafted skill that is concise, actionable, and clearly structured. It provides executable commands, a clear iterative workflow with validation loops, and practical guardrails for edge cases (flaky tests, unrelated failures). The content respects Claude's intelligence while adding genuine value about the specific gh CLI patterns to use.

Dimension	Reasoning	Score
Conciseness	Every section is lean and purposeful. No unnecessary explanations of what gh CLI is or how CI works. The trigger, workflow, commands, guardrails, and output sections each earn their place without padding.	3 / 3
Actionability	Provides specific, copy-paste-ready gh CLI commands with JSON output flags. The workflow steps are concrete and the guardrails give specific decision rules (e.g., merge main for unrelated failures, retry once for flakes).	3 / 3
Workflow Clarity	Clear 5-step sequence with explicit feedback loop (re-check after every push, repeat until green). Includes fail-fast watching, pre-check before waiting, and guidance for different failure states (already failed, pending, flaky, unrelated).	3 / 3
Progressive Disclosure	For a focused, single-purpose skill under 50 lines with no need for external references, the content is well-organized into clearly labeled sections (Trigger, Workflow, Commands, Guardrails, Output) that are easy to scan.	3 / 3
	Total	12 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: cursor/plugins
Commit: b8f2564

Reviewed: 3 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.