Content
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a well-organized, token-efficient pointer to an upstream bundle with clear navigation, but it is light on actionable instruction: the actual install/run steps are deferred to an external README without concrete commands.
Suggestions
Add a concrete, executable install step (e.g., a `git clone` or skills-directory copy command) instead of deferring entirely to 'Inspect the upstream README for exact paths'.
Replace the non-agent-actionable `open https://...` command with a step that actually advances the task (e.g., `gh repo clone figma/skills` or a curl of the README).
Spell out the expected outcome of each step (where the bundle lands, how to confirm it is installed) so the workflow has explicit checkpoints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~25-line body is lean, assumes Claude's competence, and avoids explaining concepts Claude already knows; every section earns its place, matching the 'lean and efficient' anchor. | 3 / 3 |
Actionability | It offers some concrete guidance (a bash command and a named-invocation instruction) but the core action — "install the upstream bundle into your active agent's skills directory" — has no executable command, and the only code (`open https://...`) merely opens a browser, so key details are missing. | 2 / 3 |
Workflow Clarity | A sequence is implied (inspect upstream README → install bundle → invoke by name) but the install step is vague with no concrete mechanism, fitting 'sequence present but checkpoints missing or implicit' rather than a fully clear workflow. | 2 / 3 |
Progressive Disclosure | For a catalogue/pointer skill the body is a clean overview with clearly signaled sections (What it does, Source, How to use) and a single one-level-deep reference to the upstream repository, providing easy navigation to the detailed materials. | 3 / 3 |
Total | 10 / 12 Passed |