Content
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is well-organized and appropriately defers detail to an upstream bundle, but it offers no concrete executable guidance for installing or running the skill and duplicates information already present in the frontmatter.
Suggestions
Replace the bare `open <url>` redirect with concrete, copy-paste-ready commands for cloning or installing the upstream bundle and locating it in the agent's skills directory.
Remove the verbatim repetition of the description and the restated upstream URL/category from the body to avoid redundancy with the frontmatter.
Add a brief validation step confirming the skill is discoverable after install (e.g., a command to list installed skills) to clarify the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and avoids explaining concepts Claude already knows, but it duplicates the description verbatim and restates the upstream URL and category that already appear in the frontmatter, so it could be tightened. | 2 / 3 |
Actionability | Rather than giving concrete install or run commands, it redirects the user to "open https://github.com/garrytan/gstack" and "inspect the upstream README for exact paths", which is abstract direction with no executable guidance. | 1 / 3 |
Workflow Clarity | A loose sequence is present (install the upstream bundle, then invoke by name or trigger phrase), but the install step is itself vague with no concrete sub-steps or checkpoints. | 2 / 3 |
Progressive Disclosure | The body is cleanly sectioned (What it does, Source, How to use) and points one level deep to a clearly signaled upstream repository for the full assets, with no nested reference chain. | 3 / 3 |
Total | 8 / 12 Passed |