github-pr-workflow

Working with GitHub Pull Requests using the gh CLI. Use for fetching PR details, review comments, CI status, and understanding the difference between PR-level comments vs inline code review comments.

1.06x

Quality

93%

Does it follow best practices?

Impact

85%

1.06x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

87%

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

A concise, highly actionable reference of executable gh/API commands with sensible progressive disclosure via a real script. Its main weakness is the truncated 'Addressing Review Comments' workflow, which lacks the validation/verification checkpoints expected for a fix-making process.

Suggestions

Complete the 'Workflow: Addressing Review Comments' section beyond step 2 — add explicit steps for committing/pushing fixes and re-running 'gh-pr-info <PR>' to verify the comments are resolved.

Add a validation checkpoint in the workflow (e.g., 'Confirm no unresolved comments remain before requesting re-review') to satisfy the feedback-loop expectation for a fix-making process.

Resolve the minor redundancy where the command caption ('Everything you need: summary, checks, reviews, unresolved comments') repeats the script table's purpose line, to tighten conciseness further.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes competence — no padding about what a PR is — and keeps genuinely non-obvious knowledge (PR-level vs inline comments); a small redundancy in the script caption keeps it from padding territory but it remains efficient enough for the score-3 anchor rather than 'could be tightened' (score 2).	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout — 'gh pr view <PR> --comments', 'gh pr review <PR> --approve', 'gh api repos/OWNER/REPO/pulls/PR/comments', and 'gh-pr-info <PR> [REPO]' — matching the score-3 anchor rather than pseudocode or vague direction (score 2).	3 / 3
Workflow Clarity	The 'Workflow: Addressing Review Comments' section lists a sequence but is truncated at two steps ('Get unresolved comments', 'Make fixes') with no validation/verification checkpoint for a fix-making workflow; per the rubric this caps at 2, and it is not 1 because a sequence is present.	2 / 3
Progressive Disclosure	Well-organized sections with a single one-level-deep reference (scripts/gh-pr-info) clearly signaled via a table; the referenced bundle file exists, matching the score-3 anchor for a compact skill, rather than inline content that should be split (score 2).	3 / 3
	Total	11 / 12 Passed

Description

100%

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 strong, concise description that names concrete actions, includes natural trigger terms, and provides an explicit 'Use for' clause covering both what and when. It is highly specific to the gh-CLI PR niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'fetching PR details, review comments, CI status, and understanding the difference between PR-level comments vs inline code review comments' — matching the score-3 anchor of multiple specific concrete actions, not merely naming a domain (score 2).	3 / 3
Completeness	Explicitly answers both 'what' ('Working with GitHub Pull Requests using the gh CLI') and 'when' via an explicit 'Use for' trigger clause, matching the score-3 anchor; it is not 2 because the when is explicit rather than implied.	3 / 3
Trigger Term Quality	Includes natural terms users would say — 'Pull Requests', 'PR details', 'review comments', 'CI status' — giving good coverage rather than only some relevant keywords (score 2).	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (GitHub PR workflow via gh CLI) with distinct triggers unlikely to overlap with other skills; not 2 because it is not merely 'somewhat specific'.	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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: YPares/agent-skills
Commit: ac633fa

Reviewed: 5 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.