Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a dense, executable reference: exact tool invocations with params, a sequenced publishing workflow with a pre-check and draft checkpoint, and concrete limits and error guidance. It is well-organized and respects Claude's competence without padding.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and operational — tool calls, params, limits, and common errors — with no padding explaining concepts Claude already knows; every section earns its place. The only minor redundancy is the temp-directory rule, but stating it per command is justified in a command reference. | 3 / 3 |
Actionability | Each capability is given as a complete, copy-paste-ready `limb_invoke_tool({ nodeId, command, params })` call with exact parameter names and return shapes, matching the 'fully executable; copy-paste ready' anchor. | 3 / 3 |
Workflow Clarity | The 发文流程 section gives a clear 5-step sequence, fronted by an explicit pre-check (`limb_list_available` to confirm the node is online), with the draft step acting as a checkpoint before the irreversible `submit_publish` and `publish_status` for post-publish verification, plus a 常见错误 recovery guide. | 3 / 3 |
Progressive Disclosure | Content is self-contained with well-organized sections (使用前检查, 接口发现, 核心能力, 发文流程, 常见错误, 限制) and no nested or deep references; no bundle files exist, and the inline command reference is appropriate for this single-purpose tool-invocation skill. | 3 / 3 |
Total | 12 / 12 Passed |