odyssey4me/github
Create and manage GitHub issues, pull requests, workflows, and repositories using the gh CLI. Use when asked to open a PR, merge a pull request, check repo actions, list issues, create a branch, or manage GitHub projects.
90
90%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 skill description that clearly defines its scope (GitHub operations via gh CLI), lists concrete actions, and provides explicit trigger guidance with natural user language. It follows the recommended pattern of 'what it does' followed by 'Use when...' with specific trigger phrases. No significant weaknesses identified.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create/manage issues, pull requests, workflows, repositories, and explicitly mentions using the gh CLI tool. | 3 / 3 |
Completeness | Clearly answers both what ('Create and manage GitHub issues, pull requests, workflows, and repositories using the gh CLI') and when ('Use when asked to open a PR, merge a pull request, check repo actions, list issues, create a branch, or manage GitHub projects'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'open a PR', 'merge a pull request', 'check repo actions', 'list issues', 'create a branch', 'manage GitHub projects' — these are all phrases users naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to GitHub operations via the gh CLI, with distinct triggers like 'PR', 'pull request', 'GitHub projects', 'repo actions' that are unlikely to conflict with non-GitHub skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%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 concrete, executable commands throughout, but suffers significantly from verbosity - it essentially reproduces the gh CLI documentation that Claude already knows. The workflow examples are decent but lack explicit error recovery loops. The content would benefit greatly from aggressive trimming to focus only on the wrapper script usage and the read/write distinction, which are the genuinely novel pieces of information.
Suggestions
Remove or drastically reduce the 'Commands (Direct gh Usage)' section - Claude already knows gh CLI commands. Keep only the wrapper script commands and the read vs write distinction.
Move the Advanced Usage, Configuration, and Troubleshooting sections to a reference file, keeping only a one-line pointer from the main skill.
Add explicit error handling to workflows, e.g., 'If gh auth status fails, run gh auth login before proceeding' with clear conditional logic rather than informal comments.
Remove the Summary section which largely repeats the top of the document - the quick start content could replace the Prerequisites/Authentication sections at the top.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose, essentially duplicating the gh CLI's own help documentation. Claude already knows gh CLI commands - listing every subcommand with basic descriptions (e.g., 'gh issue list # List issues') adds no value. The configuration section, troubleshooting, and official documentation links are all things Claude already knows. The content could be cut by 60%+ while preserving all useful information. | 1 / 3 |
Actionability | All commands are concrete, copy-paste ready bash commands with specific examples. The script usage section provides exact invocation patterns, and the examples section shows complete multi-step workflows with real command sequences. | 3 / 3 |
Workflow Clarity | The examples section shows multi-step workflows (Daily PR Review, Create Issue and Link PR, Monitor CI Pipeline) with some verification steps ('Verify approval was recorded', 'Verify PR was created'). However, these verification steps are informal comments rather than explicit validation checkpoints with error recovery paths. The distinction between read (wrapper script) vs write (direct gh) operations is clear but could be more prominently structured. | 2 / 3 |
Progressive Disclosure | There are references to external files (references/permissions.md, references/common-workflows.md) which is good, but the main file contains far too much inline content that could be split out - the full command reference sections, advanced usage, configuration, and troubleshooting could all be in reference files. The structure exists but the balance is wrong. | 2 / 3 |
Total | 8 / 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.
Reviewed
Table of Contents