Add line-specific review comments to pull requests using GitHub CLI API
51
42%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/git/skills/attach-review-to-pr/SKILL.mdQuality
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent, executable code examples and thorough error handling documentation, but it is severely over-engineered for a SKILL.md file. At 350+ lines, it wastes significant token budget on redundant explanations, duplicate API references, and content that should be split into separate files. The document would benefit enormously from being condensed to a concise overview with references to supporting files.
Suggestions
Reduce the SKILL.md to ~80 lines covering: preferred MCP approach, single comment syntax with one example, batch review syntax with one example, and how to get the commit SHA. Move troubleshooting, helper scripts, API reference, and best practices to separate referenced files.
Remove explanatory sections like 'Understanding GitHub's Review Comment System' and 'Prerequisites' — Claude already knows what PR review comments are and can check gh auth status without being told.
Eliminate the duplicate API Reference section at the bottom, as the parameter tables earlier in the document already cover the same information.
Add a brief validation step after posting comments (e.g., check response status code or parse the returned JSON for the comment URL) to confirm success.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Explains concepts Claude already knows (what review comments are, parameter flag differences, what Markdown is). The API reference section at the bottom duplicates information already covered in the parameters table. Multiple redundant examples, helper scripts, and best practices sections that could be drastically condensed. The 'Understanding GitHub's Review Comment System' section is unnecessary preamble. | 1 / 3 |
Actionability | Provides fully executable, copy-paste ready bash commands with concrete examples. Parameter tables are clear, complete examples include real commit SHAs and file paths, and the heredoc JSON input pattern is immediately usable. Error messages and their solutions are specific and actionable. | 3 / 3 |
Workflow Clarity | The workflow examples at the end show clear sequences (get commit SHA → add comment), and the preferred approach section provides a decision tree (MCP tool → single comment → batch review). However, there's no explicit validation step after posting comments (e.g., verify the comment was created successfully by checking the response), and the overall document structure makes it hard to follow a single clear workflow path. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files to offload content to. The API reference, helper scripts, common issues, best practices, and workflow examples are all inline when they could be split into separate files. The document tries to be both a quick reference and a comprehensive guide, resulting in poor organization for either use case. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (512 lines); consider splitting into references/ and linking | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
dedca19
Table of Contents
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.