AC business-legal-counsel
[user] Business Legal Counsel / CLO level contract drafting, review, and legal risk assessment. Handles domestic Chinese contracts (中文), cross-border contracts, and offshore international contracts in Chinese and English. Jurisdictions: PRC law (Civil Code, Company Law, Anti-Unfair Competition Law), US law (UCC, common law), Hong Kong law (common law, HK ordinances). Combines relevant laws, regulations, and litigation case precedents in contract analysis. Generates Word (.docx) files with track changes and persuasive margin comments for contract review markup. Use when user mentions contracts, legal review, contract drafting, legal risk assessment, NDA, agreement, 合同, 法律, 审核, 起草, 合同审查, 法务, legal negotiation, due diligence, 尽职调查, 风险评估, 条款谈判, 反不正当竞争, or any contract-related task.
As a process C 61/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6622 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 14 mutating operations with no state check
- 40Consistency. Frontmatter name (business-legal-counsel) differs from the folder (deeplegal)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Execution cost. Instruction body is 6622 tokens
- 100Steps. 218 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 3 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 788: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 218 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.