AB pm-workbench
Use when product work needs clearer framing, prioritization, or communication: clarifying a vague request, evaluating whether a feature is worth doing, comparing options, prioritizing requests, drafting a lightweight spec, building a roadmap, defining metrics, preparing an executive summary, reviewing outcomes, or making product-leadership/founder trade-offs. Best when the user needs a practical recommendation or reusable output, not just frameworks. Do not use for raw data crunching, deep project tracking, legal/compliance review, generic marketing copy, or pure UI copy.
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
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: 80. 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 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 14 branches
- 100Steps. 183 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3611 tokens
- 100Running it twice. Mutating operations check current state
- low 18 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
- +4No input/output examples
- -48 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 578: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 183 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.