Content
65%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 well-organized, token-efficient overview with concrete routing commands and sensible guardrails, and its single-file structure suits its size. Its main weakness is execution detail: no actual SE Ranking API call example or end-to-end query workflow, leaving Claude to infer how to invoke the vendor API and validate responses.
Suggestions
Add a minimal executable example of the SE Ranking API call (endpoint URL, auth header using SERANKING_API_KEY, and a sample request/response for an AI visibility query) so the core operation is copy-paste runnable.
Spell out the run workflow with checkpoints: query the API, validate the response (HTTP status, sample size fields), then report each *_sov percentage with a confidence note; include what to do on API error or empty samples.
Trim the Profound/Peec AI comparison sentence, which adds vendor context without operational value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and operational — routing table, API key check, unit costs, delegation rules — with almost no explanation of concepts Claude already knows. One tangential sentence ("The scorer is the same logic used by Profound / Peec AI but bundled into one MCP/API") could be trimmed, keeping it at anchor 4 rather than 5. | 4 / 5 |
Actionability | Concrete elements exist (routing commands like "/seo seranking ai-visibility <brand>", the env-var verification step, and the logging command "${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo run dataforseo_costs.py"), but for a skill whose entire purpose is driving the SE Ranking REST API there is no executable API example — no endpoint, auth header format, or sample request/response. This lands at anchor 3 (some concrete guidance but missing key details) rather than 4. | 3 / 5 |
Workflow Clarity | Prerequisites are sequenced with one explicit validation checkpoint ("Before any call, verify SERANKING_API_KEY is present... If absent, tell the user to run the installer"), but the main operation — issue query, parse the *_sov fields, report with confidence note — is described only loosely with no checkpoints for API errors or empty samples. Matches anchor 3 (sequence present, checkpoints missing or implicit) rather than 4. | 3 / 5 |
Progressive Disclosure | This is a short (~50-line) single-file skill with no bundle directories, organized into clear sections (Prerequisites, Routing, scoring fields, Cost guardrails, delegation, Security) and a routing table. Per the rubric's simple-skill guideline, content under 50 lines with no need for external references scores 5 with well-organized sections; nothing inlined here belongs in a separate file. | 5 / 5 |
Total | 15 / 20 Passed |