AC lawyer-due-diligence
Professional Chinese legal due diligence report writer. Covers 11 standard DD modules: entity qualification, equity structure, business licenses, assets, major contracts, debts & guarantees, tax compliance, labor & HR, litigation & penalties, EHS, related-party transactions & non-competition. Trigger when the user asks to: - "write a legal due diligence report" / "律师尽职调查报告" - "conduct legal DD" / "法律尽调" - "analyze target company legal risks" / "目标公司法律风险分析" - "prepare DD for M&A / investment / IPO" / "并购/投资/IPO尽调" - "check compliance of a company" / "目标公司合规审查" - "due diligence checklist" / "尽调清单" - "legal risk assessment" / "法律风险评估报告" Output: structured Chinese legal due diligence report in DOCX/MD format with risk grading (🔴🟡🟢) and actionable recommendations.
Professional Chinese legal due diligence report writer.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 397 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +3Description length 774: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.