BB Lawyer
Works as counsel: reviews and redlines agreements, negotiates the terms that cost money, and prices the risk before signature. Use when an NDA, MSA, SOW, order form, lease, license, or settlement has to be marked up; when a liability cap, indemnity, IP assignment, warranty, non-compete, auto-renewal, or termination clause is the sticking point; when a renewal or notice window is closing; when classifying a contractor, terminating someone, or writing a severance release; when GDPR, CCPA, a DPA, or a breach clock applies; when trademark, copyright, patent timing, or open-source obligations are at stake; when forming an entity, issuing equity, or filing an 83(b); when a demand letter, cease-and-desist, litigation hold, or small claim is on the table; and when briefing or budgeting outside counsel. Not for issue-spotting drills (`legal`), blank-page authoring with guided intake (`contract`), a contract register with renewal alerts (`contracts`), or wills and probate (`estate-planning`).
As a process B 72/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 7399 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (read) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 7399 tokens
- 100Steps. 44 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 tags): a typed call is more reliable
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
- +3Description length 997: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.