johnainana GitHub avatar

product-manager-workflow

johnainana

A Codex Skill for product managers that transforms vague ideas into structured deliverables through interview-style clarification and evidence-based validation.

Stars

15

7-day growth

No data

Forks

1

Open issues

0

License

No data

Last updated

2026-07-28

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It enforces a disciplined workflow that prevents hallucination, requires evidence for claims, and produces ten distinct product artifacts—from PRDs to competitor analyses—all from a single conversational process.

Who it is for

  • Product managers seeking structured output generation
  • Teams using Codex or skill-compatible AI platforms
  • Startups or small teams wanting repeatable product discovery
  • Product coaches or educators teaching PM workflows

Use cases

  • Clarifying a vague product idea into a full PRD
  • Generating user stories with acceptance criteria for a new feature
  • Creating an A/B test plan with success metrics and validation criteria
  • Producing a product launch retrospective with evidence-based insights

Strengths

  • Step-by-step interview process avoids premature commitment to details
  • Explicit marking of missing or unverified information reduces risk
  • Supports 10 different output types covering the full product lifecycle
  • Works as a single file or full skill folder for easy integration

Considerations

  • Requires a platform that supports Codex Skill format (not standalone)
  • Quality of output depends heavily on user input and evidence provided
  • Default workflow may need tailoring for non-software or hardware products

README quick start

使用方式

Description

产品经理全流程 Codex Skill:访谈澄清、PRD、指标、Roadmap、验证、推进、评审、复盘和竞品分析。

Related repositories

Similar projects matched by category, topics, and programming language.

amitshekhariitbhu
Featured
amitshekhariitbhu GitHub avatar

ai-agents-tutorial

A comprehensive step-by-step tutorial series that teaches AI agents from scratch, covering function calling, agent loops, ReAct, reflection, plan-and-execute, multi-agent systems, orchestration, evaluation, and related concepts like RAG, GraphRAG, and LangChain.

AI & Machine LearningLarge Language Models
136
7-e1even
Featured
7-e1even GitHub avatar

learn-agent

A collection of notes on building coding agents, derived from the production development of the desktop agent Reina, with each mechanism simplified into a zero-dependency, single-file Node.js demo.

AI & Machine LearningLarge Language Models
218
zju3dv
Featured
zju3dv GitHub avatar

INTACT-JEPA

INTACT is an end-to-end JEPA world model that learns an isomorphic intent-to-action interface, enabling search-free direct control for goal-conditioned robot tasks with high success rates after just one epoch of training.

AI & Machine LearningEmbedded & IoT
14