prcheckloop

Iterate on a GitHub PR until latest-head checks are green or a precise blocker is named. Use when a PR still has failing or pending checks after review fixes, including after greploop.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

96%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.

An exceptionally actionable and concise repair-loop skill with a clearly sequenced workflow and explicit feedback/escalation checkpoints. The only soft spot is progressive disclosure: the entire skill is inline with no reference files, which is reasonable but not ideal for its length.

Suggestions

Consider moving the GraphQL rollup payload and/or the failure-classification table into a references/ file and linking from SKILL.md to nudge progressive disclosure toward 5.

If keeping everything inline, add a one-line 'Quick start' or overview section at the top so the body reads as an overview plus detail rather than a single wall.

Dimension	Reasoning	Score
Conciseness	Lean and dense throughout: assumes Claude knows what GitHub Actions and check runs are, leads with executable gh/git/jq commands, and every enumerated terminal-state list is reference data that earns its place rather than padding.	5 / 5
Actionability	Fully executable, copy-paste-ready guidance including check-runs/status API calls, a GraphQL rollup query, `gh run view --log-failed`, and a failure-type-to-action classification table covering the common cases.	5 / 5
Workflow Clarity	An explicitly sequenced 8-step loop with feedback checkpoints: poll-until-terminal, fix -> push -> refresh HEAD_SHA -> restart at Step 3, clear exit conditions, and a precise escalation checklist, satisfying the validation requirement for batch/push operations.	5 / 5
Progressive Disclosure	Well-organized inline with clear section headers and no nested references, but all ~200 lines live in a single SKILL.md with no overview-pointing-to-details split or bundle files, leaving it just short of the one-level-deep reference ideal.	4 / 5
	Total	19 / 20 Passed

Description

82%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.

A tight, third-person description that answers both what and when with concrete trigger phrasing and a clearly distinct niche. Specificity is the weakest dimension because only one core capability is named rather than several.

Suggestions

Add one or two more concrete actions (e.g., 'inspect failed GitHub Actions logs and rerun flakes once') to lift specificity from 3 to 4-5.

Include common synonyms users say, such as 'CI is red', 'build failing', or 'status checks', to broaden trigger term coverage toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain (GitHub PR checks) and one concrete core action ("Iterate on a GitHub PR until latest-head checks are green"), with the "precise blocker is named" being an exit condition rather than a distinct capability, so coverage is not comprehensive enough for 4.	3 / 5
Completeness	Explicitly answers both what ("Iterate on a GitHub PR until latest-head checks are green or a precise blocker is named") and when ("Use when a PR still has failing or pending checks after review fixes, including after greploop") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage with a natural user phrasing ("failing or pending checks after review fixes") plus GitHub PR/checks/greploop terms, but missing common synonyms like "CI is red", "build failing", or ".github".	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (GitHub PR check repair loop) and explicitly distinguishes itself from sibling skills check-pr and greploop, giving it minimal conflict risk.	5 / 5
	Total	17 / 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: paperclipai/paperclip
Path: .agents/skills/prcheckloop/SKILL.md
Commit: 890ab9a

Reviewed: about 16 hours 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.