Content
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a thin catalogue entry that advertises an upstream bundle rather than providing usable skill instructions. It is concise and organized but not actionable — Claude cannot execute the skill from this body alone.
Suggestions
Provide concrete, executable guidance for running the skill (real install command or the key script invocation) instead of pointing at an external README.
Replace the `open https://...` pseudo-command with a genuine instruction (e.g. `git clone` + path to the skill entry script) or a numbered install sequence.
Either bundle the upstream references locally under references/scripts/assets and link them one level deep, or clearly document that this entry is a pointer and what the agent should do once the upstream bundle is installed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short (~25 lines) and avoids explaining concepts Claude already knows, but it repeats the frontmatter description verbatim and pads with a non-instructional `open https://...` line that could be tightened. | 2 / 3 |
Actionability | There is no executable code or command to run the skill; 'Inspect the upstream README' and `open https://github.com/...` describe rather than instruct, and `open` is a platform-ism rather than copy-paste guidance. | 1 / 3 |
Workflow Clarity | Steps are implied (install upstream bundle, then invoke by name or trigger), but there is no real sequence with checkpoints and the actual procedure is deferred entirely to an external README, leaving the single action ambiguous. | 2 / 3 |
Progressive Disclosure | Sections (What it does / Source / How to use) are organized, but there are no local bundle files (references/scripts/assets absent) and the only 'reference' is an external GitHub URL rather than a one-level-deep navigable local file. | 2 / 3 |
Total | 7 / 12 Passed |