AF prd-for-agents
Generate machine-actionable Product Requirements Documents optimized for AI coding agents (Claude Code, Codex, Cursor, Gemini CLI). Enforces a Discovery Interview before writing, so the PRD reflects user intent rather than agent assumptions. Output is a phased, dependency-ordered spec with testable acceptance criteria, file structures, API contracts, and a sequenced build order agents can execute without clarification. Use whenever the user asks to create a PRD, write product requirements, spec a feature, generate a tech spec, or says "spec this out", "write requirements for", "I need a PRD", "turn this idea into a spec", "create a build plan", "document this feature for Claude Code / Cursor". Also trigger when the user shares a raw idea dump and wants something an agent can build from.
As a process F 46/100 · Will not run — References files that are not bundled: references/discovery-questions.md, references/prd-template.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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
- warning
missing-refreference to a missing file: references/discovery-questions.md - warning
missing-refreference to a missing file: references/prd-template.md
Process rating: all ten parameters 46/100
- 0Tools and files. 2 referenced file(s) missing: references/discovery-questions.md, references/prd-template.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (prd-for-agents) differs from the folder (prd-for-ai-agents)
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 24 steps
- 100Execution cost. Instruction body is 1474 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 797: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 24 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.