gh-pr-inline
Post inline comments on GitHub PRs and respond to review feedback via gh api
83
75%
Does it follow best practices?
Impact
96%
1.29xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./dot_config/opencode/skill/gh-pr-inline/SKILL.mdQuality
Discovery
50%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 about what it does (posting inline comments and responding to review feedback on GitHub PRs via gh api) and occupies a clear niche. However, it critically lacks a 'Use when...' clause, which makes it harder for Claude to know when to select this skill. It also misses common trigger term variations like 'pull request', 'code review', or 'reply to reviewer'.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to post inline comments on a PR, reply to code review feedback, or respond to reviewer comments.'
Include common trigger term variations such as 'pull request', 'code review', 'PR comment', 'reply to reviewer', and 'review thread'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Post inline comments on GitHub PRs' and 'respond to review feedback'. Also specifies the tool used ('gh api'), which adds technical specificity. | 3 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes good natural keywords like 'inline comments', 'GitHub PRs', 'review feedback', and 'gh api'. However, it misses common variations users might say such as 'pull request', 'code review', 'PR comment', 'reply to review', or 'review comment'. | 2 / 3 |
Distinctiveness Conflict Risk | The description targets a clear niche: inline PR comments and review feedback via gh api. This is distinct from general GitHub skills, code review skills, or PR creation skills, making conflicts unlikely. | 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 an excellent skill that solves a real pain point (gh pr review's lack of inline comment support) with precise, executable commands. It covers the full lifecycle—posting, resolving, replying, and error recovery—while remaining concise and well-organized. The safety note about waiting for approval before posting and the inclusion of the delete command for misplaced comments show thoughtful workflow design.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The opening immediately explains why the non-obvious approach is needed, code examples are minimal but complete, and there's no explanation of concepts Claude already knows. The 'Line Number Gotchas' section is tight and practical. | 3 / 3 |
Actionability | All code examples are fully executable with real gh api commands, proper JSON payloads, and correct API endpoints. The skill covers posting, resolving, replying, and deleting with copy-paste ready commands including the heredoc pattern and GraphQL queries. | 3 / 3 |
Workflow Clarity | The 'Responding to PR Feedback' section provides a clear decision workflow (fixed → resolve, not fixing → reply). The posting workflow includes a safety checkpoint ('show proposed comments and wait for approval before posting'). The line number gotchas section includes verification and error recovery (delete misplaced comment). | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear headers that progress from basic posting to event types to multi-line comments to responding to feedback. For a skill of this size (~80 lines), everything is appropriately inline with logical section organization that enables quick scanning. | 3 / 3 |
Total | 12 / 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
- athal7/dotfiles
- Commit
07d79b6
- 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.