Content
92%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 skill body is concise, well-structured, and presents a clear validated workflow with concrete credential and CLI guidance. The only notable gap is the absence of executable API/token code examples that would lift actionability to fully copy-paste ready.
Suggestions
Add a short executable snippet for a common operation, e.g. obtaining a tenant access token via curl against open.feishu.cn/openapis/auth/v3/tenant_access_token/internal.
Show one minimal webhook send example using the FEISHU_WEBHOOK_URL and FEISHU_WEBHOOK_SECRET env vars so the credential pattern is demonstrated end-to-end.
Optionally note the Feishu-vs-Lark host split inside the workflow step that issues API calls, anchoring the endpoint choice to the clarified target.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence — it explains no concepts and every line (ground rules, use cases, workflow) earns its place with no padding. | 5 / 5 |
Actionability | Provides concrete env var names and executable CLI commands ('codewhale mcp add', 'codewhale mcp validate', 'codewhale mcp tools'), but lacks actual API-call or token-request code examples, leaving minor gaps in executable detail. | 4 / 5 |
Workflow Clarity | A clear six-step sequence includes an explicit validation checkpoint (step 6: dry run / sandbox / read-back) and a feedback loop before externally visible actions, plus a confirmation gate for destructive operations. | 5 / 5 |
Progressive Disclosure | Under 50 lines, single-purpose, and organized into well-signaled sections (Ground Rules, Common Use Cases, Workflow) with no need for external bundle files — meeting the simple-skill exception for a top score. | 5 / 5 |
Total | 19 / 20 Passed |