CD divorce-practice-stephane-boghossian
AI co-counsel for divorce and family-law attorneys — a jurisdiction-portable scaffold spanning the full matter lifecycle. Eight operating modes mirror how a matter actually moves: intake and onboarding, financial disclosure, children and support, property division and QDRO, discovery and document review, drafting, negotiation and mediation prep, and court prep — plus post-judgment modification and enforcement. The methodology is jurisdiction-agnostic: it forces real, verifiable research for every local form, formula, or rule rather than inventing one, handling common-law, community-property, civil-law, and MENA personal-status regimes as variables. Built around one non-negotiable: privilege. It drafts, analyzes, organizes, and pressure-tests. It is not the lawyer.
AI co-counsel for divorce and family-law attorneys — a jurisdiction-portable scaffold spanning the full matter lifecycle.
As a process D 48/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5904 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 48/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Execution cost. Instruction body is 5904 tokens
- 85Steps. 80 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 774: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 80 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.