AB pm-agent
AI-powered product management workflow agent. Use when the user wants to do product discovery, write PRDs, prioritize features, design experiments, plan launches, or run any PM workflow. Triggers on phrases like "product discovery", "write PRD", "user research", "prioritize features", "design sprint", "product launch", "opportunity mapping", "JTBD", "jobs to be done", "working backwards", "PM workflow", "product planning", "feature prioritization", "competitor analysis", "user persona", "GTM plan", "product strategy". Covers the full PM lifecycle from research to launch using proven frameworks (JTBD, Opportunity Solution Tree, RICE, Kano, Amazon Working Backwards, Google Design Sprint, Lean BML).
As a process B 74/100 · Nearly there — weak spots: failures and branches, consistency, running it twice
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: 4. 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 74/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (pm-agent) differs from the folder (ai-pm-agent)
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 39 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 1312 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 16 example trigger phrases
- +3Description length 705: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.