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.
A tight, well-organized instruction skill with concrete tool selection and solid validation rules for risky write and authentication operations. Minor gaps are the absence of tool argument shapes and a fully numbered workflow sequence.
Suggestions
Add a brief example invocation or argument shape for one read and one write tool to make guidance copy-paste ready.
Consider presenting the browser/authentication flow as a short numbered sequence to make the retry-once checkpoint explicit.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and operational throughout; assumes Claude's knowledge of LinkedIn, MCP, and browsers, with every line earning its place and no concept over-explanation. | 5 / 5 |
Actionability | Maps each task category to concrete tool names (e.g., get_person_profile, send_message) with explicit authorization rules, but provides no argument shapes or example invocations. | 4 / 5 |
Workflow Clarity | Clear auth progression with checkpoints (captcha/2FA -> stop and ask) and write-action feedback loops ('do not retry unless the result proves it was not sent'), though guidance is rule-based rather than a numbered sequence. | 4 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references, organized into clear sections (Operating rules, Browser and authentication, Tool selection); the simple-skill exception applies. | 5 / 5 |
Total | 18 / 20 Passed |