Content
71%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable with copy-paste CLI commands and a well-sequenced connection workflow including state-based feedback loops, but it carries some marketing padding and inlines reference-grade material that would benefit from separation into bundled files.
Suggestions
Trim the marketing overview of HeySummit's audience and the vague agent-types note; assume Claude knows the CLI tooling context and keep only task-relevant detail.
Move the clientAction state schema and the proxy-flag reference table into a references/ file (e.g. references/connection-states.md) and link to it from SKILL.md so the main file stays an overview.
Label the workflow steps explicitly (e.g. '## Step 2: Find and run actions') so the 'skip to Step 2' reference resolves to a real heading.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean command references, but the marketing-style overview ("used by marketers, entrepreneurs, and educators to share knowledge, generate leads, and build community") and the awkward agent-types note pad sections Claude does not need, fitting the score-3 anchor of mostly efficient with some unnecessary explanation. | 3 / 5 |
Actionability | It provides copy-paste-ready commands for every common case (install, login, connection ensure/get, action list/run, request proxy) with flags documented and a popular-actions table, matching the score-5 anchor of fully executable examples covering common cases. | 5 / 5 |
Workflow Clarity | There is a clear install→authenticate→connect→poll/state-machine→search→run sequence with explicit polling feedback loops and per-state handling, but the "skip to Step 2" reference points to no labeled Step 2, a minor sequencing gap keeping it at 4. | 4 / 5 |
Progressive Disclosure | Section headers are clear and logically ordered, but the skill is monolithic: the detailed clientAction state schema, proxy-flag reference table, and popular-actions table are all inlined with no one-level-deep reference files, matching the score-3 anchor of content that should be separate being inline. | 3 / 5 |
Total | 15 / 20 Passed |