Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

PRD Creation — measured AI agent skill | DecimalAI

a5c-ai/prd-creation

NewSkillScoreMaintained

Create Product Requirements Documents through structured discovery using Jobs-to-be-Done framework.

by a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Product Management pack

decimalai skills pull a5c-ai-prd-creation

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-prd-creation/SKILL.md

Raw file: /s/a5c-ai-prd-creation/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-prd-creation.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9d ago

No measurable change+10% tokens0% turns13% of whole cases pass with skill (3/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-24%	0%
case-05	✗→✓	▲ Improved	11%	0%
case-07	✗→✓	▲ Improved	33%	0%
case-01	✗→✗	＝ Same ✗	-68%	0%
case-03	✗→✗	＝ Same ✗	64%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/methodologies/bmad-method/skills/prd-creation/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v2

Skill contents

SKILL.md

PRD Creation

Interactive PRD brainstorming and drafting with quality-gated refinement.

Agent

Product Planner - product-planner

Workflow

Brainstorm ideas, users, and pain points
Draft structured PRD with vision, user stories, success criteria
Validate PRD quality (completeness, clarity, testability, consistency)
Iteratively refine until quality threshold met
Finalize and write to .claude/prds/<featureName>.md

Inputs

projectName - Project name
featureName - Feature identifier
projectDescription - High-level description
targetAudience - Target user description (optional)
constraints - Known constraints (optional)

Outputs

PRD with vision, user stories, acceptance criteria, scope, constraints
Quality validation report with dimensional scores
Brainstorm artifacts

Process Files

ccpm-prd-workflow.js - Standalone PRD workflow
ccpm-orchestrator.js - Phase 1 of full lifecycle

Want to see if a5c-ai/prd-creation would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.