AB band-agreement
Write the band agreement before the money or the breakup arrives — who owns the songs, how money splits (writing vs performing distinguished), who owns the name, what happens when someone quits, and the decision rules for offers — decided while everyone still shares a van. Use when a band asks 'how should we split money', 'who owns our songs', 'our drummer quit, what happens', or is about to record/release/sign anything. Produces a plain-language band agreement and the meeting script to agree it. Not legal advice — it's the conversation that makes the lawyer cheap later.
Write the band agreement before the money or the breakup arrives — who owns the songs, how money splits (writing vs performing distinguished), who owns the…
As a process B 67/100 · Nearly there — weak spots: when it triggers, failures and branches, running it twice
The same skill appears in 1 more place: pm-claude-skills
How to improve
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 67/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1553 tokens
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)
- +1No license
- +2Single-language instructions
- +3Description length 577: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 25 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.