Content
86%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 a model of token-efficient routing-skill authoring: tight sections, exact commands, a crisp command table, explicit cross-skill boundaries, and a sensible untrusted-data security note, with no filler. The only gaps are the absence of worked API/usage examples and error-recovery steps, which keep actionability and workflow clarity at 4 rather than 5.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~40-line body is lean: every section carries skill-specific facts Claude could not know (the Profound-vs-SE-Ranking polling distinction, the routing table, citation format "Profound (live, confidence 0.90)", delegation rules) with zero padding or explanation of concepts Claude already knows. It matches anchor 5 — every token earns its place — and is clearly above anchor 4's 'minor instances of over-explanation'. | 5 / 5 |
Actionability | Concrete, runnable guidance dominates: "Run `extensions/profound/install.sh` or `install.ps1`", "check `~/.claude/settings.json` has `env.PROFOUND_API_KEY`", and four exact routing commands like "/seo profound citations <brand>" with defined outputs. It stops short of anchor 5 because there are no API-call examples, parameter details, or sample output shapes — the actual data-fetching mechanics are left to the extension. | 4 / 5 |
Workflow Clarity | The flow is clearly sequenced: install → verify the API key ("Before any tool call, check `~/.claude/settings.json` has `env.PROFOUND_API_KEY`" is an explicit pre-flight checkpoint) → route via the command table → apply citation conventions → delegate. It misses anchor 5 because there is no error-recovery guidance (e.g., what to do when the key is missing or an API call fails), but checkpoints are present, keeping it above anchor 3. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ exist) and no need for external references, so per the rubric's simple-skill guideline well-organized sections alone qualify for 5. Sections (Prerequisites, Routing, Output conventions, Cross-skill delegation, Security) are clear, flat, and easy to navigate. | 5 / 5 |
Total | 18 / 20 Passed |