Content
82%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 strong, actionable connector skill body with executable examples and a real backing script, well-structured into clear sections. Main weaknesses are a duplicated .env line, no explicit validation checkpoint in the workflow, and a large inline skill-id table that could live in a reference file.
Suggestions
Fix the duplicated '仓库根目录 .env' entry in the env-loading list (lines 59-60) — it appears twice with no distinction.
Add an explicit numbered workflow with a validation checkpoint (e.g. '1. set TTFUND_APIKEY; 2. verify with `list`; 3. invoke; 4. confirm response has source/asOf') so the sequence and its verification are unambiguous.
Consider moving the Skill IDs table into a references/ file (e.g. SKILL_IDS.md) and linking to it from the body to keep SKILL.md a leaner overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly lean and assumes Claude's competence (no explanation of what funds/net value are), but the env-loading list duplicates '仓库根目录 .env' on consecutive lines and the repeated full script path is slightly verbose. | 4 / 5 |
Actionability | Quick Reference gives copy-paste-ready bash commands backed by a real verified script (scripts/ttfund-call.mjs), and the Skill IDs table maps each id to a concrete version and purpose covering the common cases. | 5 / 5 |
Workflow Clarity | Clear usage path (set TTFUND_APIKEY → `list` → invoke with payload) with the Common Mistakes table acting as guardrails, but there is no explicit numbered sequence or validation checkpoint confirming the key loaded or the response parsed. | 4 / 5 |
Progressive Disclosure | Well-organized sections (When to Use, Quick Reference, Skill IDs, Common Mistakes, 下一步) with one-level-deep references to a real script, though the sizable Skill IDs table is inlined rather than split into a reference file. | 4 / 5 |
Total | 17 / 20 Passed |