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.
90
89%
Does it follow best practices?
Impact
85%
1.06xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a strong description that clearly identifies its domain (GitHub PRs via gh CLI), lists specific capabilities (fetching PR details, review comments, CI status), and includes a 'Use for...' clause with natural trigger terms. The distinction between PR-level comments and inline code review comments adds valuable specificity that helps differentiate it from other GitHub-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: fetching PR details, review comments, CI status, and distinguishes between PR-level comments vs inline code review comments. | 3 / 3 |
Completeness | Clearly answers both what ('fetching PR details, review comments, CI status, understanding comment types') and when ('Use for fetching PR details, review comments, CI status') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'GitHub', 'Pull Requests', 'PR', 'gh CLI', 'review comments', 'CI status', 'code review'. These cover common variations of how users refer to PR workflows. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to GitHub Pull Requests via the gh CLI, with specific mention of PR-level vs inline code review comments. This is a distinct niche unlikely to conflict with general git skills or other GitHub skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, practical skill that efficiently communicates the critical distinction between PR comment types and provides actionable commands. Its main weaknesses are the truncated workflow section (which appears cut off mid-content) and the lack of a complete feedback loop for the review-addressing workflow. The API reference is a useful addition but could be better organized via progressive disclosure.
Suggestions
Complete the 'Addressing Review Comments' workflow with remaining steps including validation (e.g., re-running gh-pr-info to verify all comments addressed, pushing and checking CI).
Add a feedback loop to the workflow: after making fixes, re-run gh-pr-info to confirm no unresolved comments remain before pushing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what PRs are or how GitHub works—it jumps straight into the distinction between comment types (which is genuinely non-obvious) and provides concrete commands. The table format for scripts is efficient. | 3 / 3 |
Actionability | Provides fully executable commands throughout: gh CLI commands, API endpoints with exact paths, and a custom script with clear usage syntax. Every section gives copy-paste ready commands with comments explaining their purpose. | 3 / 3 |
Workflow Clarity | The 'Addressing Review Comments' workflow at the end is truncated/incomplete—it only shows steps 1-2 and cuts off. There's no validation checkpoint (e.g., verifying fixes address the comments, re-running checks). The common commands section is well-organized but the actual workflow is unfinished. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a table, but the API endpoints reference section could be split to a separate file since it's supplementary detail. The skill references a script `gh-pr-info` but doesn't link to its source or documentation file. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%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
- YPares/agent-skills
- Commit
aed1afb
- Reviewed
Table of Contents
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.