AB prd-creator
Creates production-grade, internationally-standardized Product Requirements Documents (PRDs) for full-stack web/mobile projects, plus an execution-ready task breakdown so a coding agent (Claude Code, opencode CLI, etc.) can implement directly from it. Synthesizes ISO/IEC/IEEE 29148:2018, IEEE 830, Amazon's Working Backwards PR/FAQ, and Big Tech PRD conventions into one rigorous English .md deliverable. Use whenever the user asks to write/draft a PRD, product spec, SRS, feature spec, implementation plan, or "dokumen requirement/spesifikasi produk" — for any web, mobile, or full-stack system, even from a one-sentence idea. Also trigger to formalize an existing idea/backlog item into a proper requirements document, for a PRD "standar internasional"/"lengkap"/"seperti dibuat expert", or to prepare a project brief before handing off to Claude Code/opencode. Do NOT trigger for quick one-off feature descriptions the user wants kept short and informal.
As a process B 65/100 · Nearly there — weak spots: result and completion, 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: 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 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Steps. 39 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2531 tokens
- 100Running it twice. Mutating operations check current state
- 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)
- +3Description length 958: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 39 items
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.