BB engagement-terms-billing-guidelines
Outside counsel guidelines (OCGs) — drafting, review, gap analysis, and targeted updates for in-house legal teams. Build new OCGs calibrated to maturity level (light, standard, comprehensive), review existing OCGs against 15-component best practice framework, add or update specific sections (AI policy, AFA terms, D&I, rate review), and produce GC briefing notes for internal buy-in. Trigger on: 'draft billing guidelines', 'outside counsel guidelines', 'OCG', 'billing expectations', 'review our guidelines', 'update the AI clause', 'what should our billing guidelines cover', 'we don't have billing guidelines', 'firms aren't following our guidelines', 'rate review terms', 'GC briefing on billing guidelines', 'AFA policy', 'block billing', 'prohibited fees', 'staffing expectations for outside counsel'.
Outside counsel guidelines (OCGs) — drafting, review, gap analysis, and targeted updates for in-house legal teams.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, consistency, execution cost
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8528 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (engagement-terms-billing-guidelines) differs from the folder (engagement-terms-billing-guidelines-scott-margetts)
- 40Execution cost. Instruction body is 8528 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 90 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 7 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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)
- +3Description length 808: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 27 headings
- +3Step-by-step instructions: 90 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.