BB continuous-improvement-engine-scott-margetts
Capture, structure, and recycle lessons from active and closed legal matters. Three modes: in-flight capture (triggered by scope changes, risk events, status updates — highest value), mid-matter review (phase gates or quarterly), and matter close retrospective (full structured findings). Lessons are formatted for immediate reuse, not filed and forgotten. Use when a risk materialises, a scope change lands, a phase completes, or a matter closes and you want to convert what happened into something useful for the next matter. Trigger on: 'capture a lesson', 'what did we learn', 'matter close', 'retrospective', 'lessons learned', 'what went wrong', 'what worked', 'phase gate review', 'debrief', 'extract the learning', 'close the matter', 'what should we do differently', 'pattern from this matter', 'improve the next one'.
Capture, structure, and recycle lessons from active and closed legal matters.
As a process B 71/100 · Nearly there — weak spots: 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6640 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6640 tokens
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 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 827: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.