BB panel-design-selection
Panel structure design, firm selection criteria, right-sourcing analysis, and coverage gap assessment for in-house legal teams. Build panel frameworks from scratch or formalise existing informal arrangements. Define weighted selection criteria for firm evaluation. Run right-sourcing analysis (ABC tiering) to identify work sent to expensive providers that doesn't require that level of resource. Assess existing panels for practice area, geographic, and capability gaps. Trigger on: 'design our panel', 'how many firms do we need', 'panel structure', 'firm selection criteria', 'which firms should we use', 'right-sourcing', 'are we sending work to the right firms', 'panel gaps', 'too many firms', 'consolidate our panel', 'we need a firm for', 'preferred provider', 'panel tiers', 'do we need BigLaw for this', 'convergence', 'D&I panel targets', 'how do we choose firms'.
Panel structure design, firm selection criteria, right-sourcing analysis, and coverage gap assessment for in-house legal teams.
As a process B 68/100 · 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 ≈ 8168 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 17 mutating operations with no state check
- 40Consistency. Frontmatter name (panel-design-selection) differs from the folder (panel-design-selection-scott-margetts)
- 40Execution cost. Instruction body is 8168 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 50 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 6 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 14 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 875: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 31 headings
- +3Step-by-step instructions: 50 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.