AC pm-workbench
A comprehensive product manager workbench that provides document generation (PRD, competitive analysis), decision coaching, end-to-end workflow guidance, interview coaching, and growth strategy design. Covers data products, back-office systems, and edtech growth domains. Use when the user asks about product management, needs a PRD, wants competitor analysis, is designing experiments, planning roadmaps, doing retrospectives, preparing for interviews, designing growth strategies, or seeking PM advice.
A comprehensive product manager workbench that provides document generation (PRD, competitive analysis), decision coaching, end-to-end workflow guidance…
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "trigger_keywords"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (pm-workbench) differs from the folder (pm-workbench-2)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 69 steps
- 100Execution cost. Instruction body is 1073 tokens
- 100Running it twice. No mutating operations
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 504: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.