BB scope-change-controller-scott-margetts
Scope management for legal matters — baseline capture, in-flight change control, OOS documentation, and scope retrospective. Use when asked to review scoping assumptions, assess whether work is in or out of scope, draft a scope change notice, track scope changes, prepare an OOS justification, run an OOS report, prepare a scope call agenda, or review what changed on a matter. Trigger on: 'scope change', 'out of scope', 'OOS', 'scope creep', 'is this in scope', 'the client wants us to also', 'additional work', 'scope review', 'what changed from the original scope', 'we need to revisit the quote', 'the budget assumed', 'OOS report', 'scope call with the client', 'run a scope report'.
Scope management for legal matters — baseline capture, in-flight change control, OOS documentation, and scope retrospective.
As a process B 72/100 · Nearly there — weak spots: result and completion, 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 ≈ 6468 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 72/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 12 mutating operations with no state check
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6468 tokens
- 85Steps. 70 steps, 3 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 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
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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 689: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 70 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.