AC self-improving-legal
Captures clause risks, compliance gaps, precedent shifts, contract deviations, regulatory changes, and litigation exposure to enable continuous legal operations improvement. Use when: (1) An unfavorable clause is accepted or slips through review, (2) A compliance deadline is missed or approaching, (3) A new regulation impacts the organization, (4) A contract remains unsigned past SLA, (5) An IP infringement notice is received, (6) New case law changes interpretation in a relevant jurisdiction, (7) A data subject access request reveals process gaps.
As a process C 57/100 · Has gaps — weak spots: result and completion, 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: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6885 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 15 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 6885 tokens
- 100Steps. 122 steps
- 100Failures and branches. 2 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 20 top-level sections: this looks like several domains in one skill
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
- +1No license
- +2Single-language instructions
- +3Description length 554: enough signal without eating the budget
- +4Structure: 50 headings
- +3Step-by-step instructions: 122 items
- +4Has examples (17 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.