BA local-counsel-manager-scott-margetts
End-to-end external local counsel lifecycle management for multi-jurisdiction legal matters. LC selection criteria and capability assessment, engagement setup and instruction design, performance monitoring and check-in cadence, scope enforcement, and relationship escalation. Use when selecting local counsel for a jurisdiction, designing LC instructions, managing the LC check-in rhythm, enforcing scope boundaries when LC signals overreach, or escalating a performance or relationship issue beyond the matter team. Trigger on: 'which LC should we use', 'LC instruction', 'brief the local counsel', 'LC hasn't responded', 'LC is going off scope', 'LC scope dispute', 'confirm scope with LC', 'LC check-in', 'LC is slow', 'monitor the LC network', 'LC engagement letter', 'LC selection', 'what should we tell the local counsel', 'LC onboarding', 'LC performance issue', 'LC relationship problem'.
End-to-end external local counsel lifecycle management for multi-jurisdiction legal matters.
As a process A 87/100 · Runs to the end — weak spots: execution cost, 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8280 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 87/100
- 30Running it twice. 13 mutating operations with no state check
- 40Execution cost. Instruction body is 8280 tokens: crowds the task out of the window
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 5 branches
- 100Tools and files. No external tools needed
- 100Steps. 72 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 10 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 896: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 18 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.