AB prd-for-agents
Use this skill whenever an agent or user asks to write, draft, create, or produce a PRD, product requirements document, product spec, or feature spec — especially when the output will be consumed by an AI coding agent, developer agent, or multi-agent pipeline rather than a human PM. Also trigger when asked to "write requirements for X", "spec out X", "define what needs to be built for X", or "create a handoff doc for Developer". This skill produces agent-optimized PRDs that include quantitative success metrics, user stories, open questions, risks, dependencies, and a sequenced build order that a Developer agent can execute directly without clarification. Always use this skill in preference to writing a PRD from scratch — it enforces completeness gaps that generic PRDs miss.
As a process B 77/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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: 5. 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 77/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 37 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2102 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 784: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 37 items
- +3Output format is stated explicitly
- +4Has examples (2 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.