Content
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent workflow examples that include verification steps, but it suffers significantly from verbosity. It essentially duplicates gh CLI documentation that Claude already knows, inflating the token cost substantially. The progressive disclosure structure is partially implemented with references to supporting files, but too much reference-level content remains inline.
Suggestions
Move the entire 'Commands (Direct gh Usage)' section to a reference file (e.g., references/gh-commands.md) and replace with a brief note that gh commands are available for all action operations, with a link to the reference.
Remove the Configuration, Troubleshooting, Official Documentation, and Summary sections entirely — Claude knows how to use gh --help, check auth status, and find documentation. The Summary restates the skill's own content.
Consolidate the Advanced Usage section into the reference files or trim to only the gh api examples, which are the most non-obvious content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is very verbose, essentially duplicating the gh CLI's own help documentation. The direct gh usage sections (Issues, PRs, Workflows, Repositories, Search) largely repeat what the wrapper script section already covers, and Claude already knows gh CLI commands. The Configuration, Troubleshooting, Official Documentation, and Summary sections add significant token bloat with information Claude can easily infer or look up. The summary at the end restates what was already said. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready commands throughout. Both the wrapper script usage and direct gh commands are concrete with specific examples, flags, and real command patterns including jq processing and JSON output. | 3 / 3 |
Workflow Clarity | The Examples section provides clear multi-step workflows (Daily PR Review, Create Issue and Link PR, Monitor CI Pipeline) with explicit verification steps after actions (e.g., 'Verify approval was recorded', 'Verify PR was created and linked', 'Verify rerun started'). The read/write distinction between wrapper script and direct gh is clearly articulated. | 3 / 3 |
Progressive Disclosure | References to permissions.md and common-workflows.md are well-signaled and one level deep, which is good. However, the main SKILL.md contains far too much inline content that could be split into reference files (the entire direct gh usage section is essentially a command reference). The bundle files aren't provided, so we can't verify the referenced files exist. | 2 / 3 |
Total | 9 / 12 Passed |