deanpeters/

Product-Manager-Skills

GitHub

Product Manager Skills provides a library of 70 PM frameworks and 3 skill types, with multiple downloadable packs and a Streamlit beta for local testing. It targets Claude, Codex, and other agents, and is actively updated with recent releases.

6.3kstars

760forks

10issues

2026since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

thedotmack/

claude-mem

▲ 660/wk

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

90k7.8kJavaScript

code-yeongyu/

oh-my-openagent

▲ 483/wk

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

67k5.5kTypeScript

nanocoai/

nanoclaw

▲ 37/wk

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

30k13kTypeScriptgiant

VoltAgent/

awesome-agent-skills

▲ 426/wk

A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

30k3.2k

OthmanAdi/

planning-with-files

▲ 158/wk

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Claude Code, Codex, Cursor, Kiro, OpenCode and 60+ agents via the Agent Skills standard.

26k2.2kShell

Egonex-AI/

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

77k6.5kTypeScriptgiant

CompareProduct-Manager-Skills vs claude-mem Product-Manager-Skills vs oh-my-openagent Product-Manager-Skills vs nanoclaw

Reviewgenerated from repository data · Aug 5, 2026

What it is

Product Manager Skills is a framework library of 70 battle-tested PM skills organized into three tiers (WORKFLOW SKILLS, INTERACTIVE SKILLS, COMPONENT SKILLS) designed for use with Claude Code, Claude Desktop/Web, Codex, and other agents that read structured knowledge. It includes 70 skills plus 6 command workflows and provides both downloadable skill ZIPs and themed packs (Starter, Discovery, Strategy, Delivery, AI PM, Market Intel, All skills).

How it works

Skills are grouped into three tiers and are designed to be executed via agent workflows. The library emphasizes interactive skills that use an Adaptive Decision Ladder, asking 3-5 targeted questions to tailor recommendations, then executing a chosen path with rationale. Each skill follows a consistent SKILL.md structure with frontmatter, purpose, input, concepts, application, examples, pitfalls, and references.

Getting started

Get started options include:

Claude Desktop or Claude Web: pm-skills-starter-pack.zip and related skill ZIPs for upload to Claude Skills
Claude Code: Plugin marketplace path
Codex: pm-skills-codex.zip with .agents/skills and AGENTS.md
Not sure: pm-skills-starter-pack.zip

All downloads: GitHub Releases

Try It First — Streamlit (beta):

pip install -r app/requirements.txt
streamlit run app/main.py

Multi-provider support: Anthropic, OpenAI, Ollama. API keys via environment variables only.

Getting started details in README

The project documents the available packs and how to install for Claude, Codex, and non-technical PMs, including a Streamlit beta playground and a catalog of the 70 skills across three tiers. It lists the latest version as v0.83 (July 17, 2026) and prior releases that introduce new skills like stakeholder-identification and organic-growth-advisor.

Recent releases

Latest releases include:

v0.83 (2026-07-17)
v0.82 (2026-07-08)
v0.81 (2026-07-04)
v0.80 (2026-06-25) with 5 new skills (54 total)
v0.79 (2026-05-20) introducing new skill: organic-growth-advisor

Traction

Stars: 6255; Forks: 760; Open issues: 10. Language: Shell. Created: 2026-02-05; Last push: 2026-07-17. License: none listed.

Caveats

License not listed. Age indicates initial creation in 2026-02-05 and ongoing activity through 2026-07-17. No explicit security or license details are provided in the facts.

Agent skills inside · 70

All skills →

tam-sam-som-calculatorCalculate TAM, SAM, and SOM with explicit assumptions, methods, and caveats. Use when sizing a market for a product idea, business case, or executive review.Code Review & Qualityscripts user-storyCreate user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions.Otherscripts autonomous-investigationThe protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs.Workflow & Productivity competitive-research-snapshotResearch a competitive landscape with cited snapshots, a comparison matrix, and so-what implications. Use when a product decision needs competitive grounding, not a market report.Other customer-journey-mapCreate a customer journey map across stages, touchpoints, actions, emotions, and metrics. Use when diagnosing a broken experience or aligning a team on the full customer flow.Other competitive-intel-watchScheduled delta monitoring against a prior competitive snapshot. Use when tracking competitors on a cadence: material shifts only, cited evidence, battle-card update flags, runs unattended.Design & Presentation

SharePost on X LinkedIn