Content
64%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 reference-style skill with excellent actionability—every section provides real, executable gh CLI commands. Its main weaknesses are moderate verbosity (duplicate quick reference section, redundant resource descriptions, unnecessary 'When to Use' section) and lack of multi-step workflow sequences with validation checkpoints. The progressive disclosure structure is well-intentioned but redundant in its reference descriptions.
Suggestions
Remove the 'When to Use This Skill' section entirely—this duplicates the YAML description and is metadata, not instruction.
Eliminate the 'Quick Reference' section which duplicates commands already shown in the Core Operations sections, or consolidate by removing the inline examples and keeping only the quick reference.
Add at least one multi-step workflow with validation (e.g., 'Create PR → verify checks pass → request review → merge' with explicit checkpoint steps like `gh pr checks 123 --watch`).
Consolidate the 'Resources' section to just the reference links without re-describing contents—the inline 📚 links already provide sufficient context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary sections like 'When to Use This Skill' (which repeats the description) and the 'Resources' section that re-describes what each reference file contains after already linking to them inline. The 'Quick Reference' section also largely duplicates commands already shown above. However, the core content is reasonably efficient with executable examples. | 2 / 3 |
Actionability | All guidance is concrete with copy-paste ready bash commands. PR creation, issue management, API calls, authentication, and output formatting all have executable examples with real flags and arguments. The PR title convention is specific and actionable. | 3 / 3 |
Workflow Clarity | Individual commands are clear, but there are no multi-step workflows with validation checkpoints. For example, the PR creation flow doesn't include verifying the PR was created, checking CI status, then merging. Operations are presented as isolated commands rather than sequenced workflows with feedback loops. | 2 / 3 |
Progressive Disclosure | The skill references five separate reference files with clear signaling (📚 icons and a detailed Resources section), which is good structure. However, since no bundle files are provided, we cannot verify these references exist. Additionally, the Resources section at the bottom redundantly describes each reference file's contents in detail after already linking them inline, and the main body itself is somewhat long with content that could be pushed to references. | 2 / 3 |
Total | 9 / 12 Passed |