kelegele/oh-my-pm
Oh-My-PM - Product Manager AI Agent Workflow System via Claude Code Skills
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit kelegele/oh-my-pm/agents ./rig-oh-my-pm/agents $ npx degit kelegele/oh-my-pm/commands ./rig-oh-my-pm/commands $ npx degit kelegele/oh-my-pm/skills ./rig-oh-my-pm/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit kelegele/oh-my-pm/skills/clarify-requirements .claude/skills/clarify-requirements $ npx degit kelegele/oh-my-pm/skills/competitive-analysis .claude/skills/competitive-analysis $ npx degit kelegele/oh-my-pm/skills/feature-launch .claude/skills/feature-launch $ npx degit kelegele/oh-my-pm/skills/feedback-synthesis .claude/skills/feedback-synthesis $ npx degit kelegele/oh-my-pm/skills/full-pm-cycle .claude/skills/full-pm-cycle $ npx degit kelegele/oh-my-pm/skills/market-research .claude/skills/market-research $ npx degit kelegele/oh-my-pm/skills/ompm .claude/skills/ompm $ npx degit kelegele/oh-my-pm/skills/prd-gen .claude/skills/prd-gen $ npx degit kelegele/oh-my-pm/skills/product-strategy .claude/skills/product-strategy $ npx degit kelegele/oh-my-pm/skills/prototype-design .claude/skills/prototype-design $ npx degit kelegele/oh-my-pm/skills/quick-prd .claude/skills/quick-prd $ npx degit kelegele/oh-my-pm/skills/retrospective .claude/skills/retrospective
$ curl -fsSL --create-dirs -o .claude/agents/competitive-analyst.md https://raw.githubusercontent.com/kelegele/oh-my-pm/main/agents/perception/competitive-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/market-researcher.md https://raw.githubusercontent.com/kelegele/oh-my-pm/main/agents/perception/market-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/user-interviewer.md https://raw.githubusercontent.com/kelegele/oh-my-pm/main/agents/perception/user-interviewer.md $ curl -fsSL --create-dirs -o .claude/agents/feedback-collector.md https://raw.githubusercontent.com/kelegele/oh-my-pm/main/agents/validation/feedback-collector.md $ curl -fsSL --create-dirs -o .claude/agents/impact-analyst.md https://raw.githubusercontent.com/kelegele/oh-my-pm/main/agents/validation/impact-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/pm-orchestrator.md https://raw.githubusercontent.com/kelegele/oh-my-pm/main/agents/workflows/pm-orchestrator.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (12)
clarify-requirementscompetitive-analysisfeature-launchfeedback-synthesisfull-pm-cyclemarket-researchompmprd-genproduct-strategyprototype-designquick-prdretrospective
Subagents (6)
| competitive-analyst model: sonnet | 竞品分析专家，负责功能对比和定位。当用户说"分析竞品"、"对比 X 和 Y"、"竞品分析"、"竞品有什么"、"[产品] 有 [功能] 吗"时主动使用。 |
| market-researcher model: haiku | 市场研究专家，负责收集行业趋势、市场规模和机会分析。当用户需要市场情报，或说"分析 X 市场"、"市场研究"、"行业趋势"、"市场规模"、"Y 的市场有多大"时主动使用。 |
| user-interviewer model: sonnet | 用户研究专家，负责用户访谈、用户画像创建和用户行为分析。当用户需要了解用户需求、创建用户画像、分析用户反馈，或说"与用户交谈"、"用户想要什么"、"用户研究"、"创建用户画像"时主动使用。 |
| feedback-collector model: haiku | 用户反馈汇总专家，用于聚合多源反馈、识别主题和模式。当用户需要分析用户反馈、分类反馈主题、理解用户情绪，或说"分析反馈"、"用户在说什么"、"汇总反馈"时主动使用。 |
| impact-analyst model: sonnet | 上线效果分析专家，用于评估发布结果和衡量功能成功。当用户需要评估上线效果、衡量功能成功、分析上线后指标，或说"效果如何"、"衡量影响"、"上线复盘"时主动使用。 |
| pm-orchestrator model: inherit | 产品管理工作流编排器，协调感知、策略、设计、交付和验证层的完整工作流。用于"完整产品规划"、"完整 PM 周期"、"0-1 产品规划"。 |
Slash commands (4)
/feature-launch/full-pm-cycle/ompm/quick-prd
Similar rigs
Maudeunfledged834/startup-founder-skills
Automate founder tasks with AI skills for emails, decks, calls, contracts, hiring, sales, and finance across the startup stack
Skill Collector 3.0k tok ·
aakashg/pm-claude-code-setup
Ready-to-use CLAUDE.md and starter skill for product managers using Claude Code.
Pragmatist 818 tok ·
heyparsadev/claude-venture-plugin
Claude Code plugin and agent skills for founders — market research, competitor analysis, customer discovery, product-market fit, go-to-market and unit economics, chained through one shared workspace. Persian and English.
Pragmatist 759 tok ·
broomva/skills
Broomva agent-skills monorepo — 48 Tier-2 skills compatible with Claude Code, Codex, Cursor, Gemini CLI, Goose, Copilot. Layout follows anthropics/skills (agentskills.io spec). Install: npx skills add broomva/skills --skill <name>.
Orchestrator 1.2k tok ·