Product & Planning

Product & planning agent skills structure the thinking side of building: specs, PRDs, user stories, roadmaps, and prioritization frameworks. Install one and your AI agent produces planning documents with the same rigor and format every time.

wenjunduan Skill

Roadmap 3

PACE 可选 stage. 大需求 (跨 ≥3 模块) 拆成子 feature 序列. 产出 .ai_state/roadmap/{slug}/items.yaml + roadmap.md. 每个子 item 完成后回写 status, 主 agent 自动进入下一个 item 的 plan stage.

Sep 17
wenjunduan Skill

Roadmap 4

PACE 可选 stage. 大需求 (跨 ≥3 模块) 拆成子 feature 序列. 产出 .ai_state/roadmap/{slug}/items.yaml + roadmap.md. 每个子 item 完成后回写 status, 主 agent 自动进入下一个 item 的 plan stage.

Sep 17
wenjunduan Bundle

Roadmap 5

PACE 可选 stage。需求跨 3 个以上模块、需要拆成子 feature 序列时触发。

Sep 17
wenjunduan Bundle

Roadmap 6

PACE 可选 stage。存在 ≥2 个可独立验收交付的切片，或用户明确要求拆分时触发。

Sep 17
wenjunduan Skill

Roadmap 7

PACE 可选 stage. 大需求 (跨 ≥3 模块) 拆成子 feature 序列. 产出 .ai_state/roadmap/{slug}/items.yaml + roadmap.md. 每个子 item 完成后回写 status, 主 agent 自动进入下一个 item 的 plan stage.

Sep 17
wenjunduan Skill

Roadmap 8

PACE 可选 stage. 大需求 (跨 ≥3 模块) 拆成子 feature 序列. 产出 .ai_state/roadmap/{slug}/items.yaml + roadmap.md. 每个子 item 完成后回写 status, 主 agent 自动进入下一个 item 的 plan stage.

Sep 17
wenjunduan Skill

Brainstorm 4

PACE 可选最早 stage. 用户想法模糊时通过对话理清楚. AI 角色: 思考伙伴, 挖用户真正想解决的问题, 必要时提出更好的替代方案. 完成后产出 sprints/{date}-{slug}/brainstorm.md 并路由到 plan / roadmap / direct design.

Sep 17
wenjunduan Skill

Athena Dev 2

Athena 主入口 skill (Codex). 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 由 deprecated prompts/ 迁为 skill; 修 CC 残留 (session-start.cjs→py); 铁律引用名称化.

Sep 17
wenjunduan Skill

Brainstorm 5

PACE 可选最早 stage. 用户想法模糊时通过对话理清楚. AI 角色: 思考伙伴, 挖用户真正想解决的问题, 必要时提出更好的替代方案. 完成后产出 sprints/{date}-{slug}/brainstorm.md 并路由到 plan / roadmap / direct design.

Sep 17
wenjunduan Skill

Athena Dev 3

Athena 主入口 skill (Codex). 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 由 deprecated prompts/ 迁为 skill; 修 CC 残留 (session-start.cjs→py); 铁律引用名称化.

Sep 17
wenjunduan Skill

Athena Dev 4

Athena 主入口 skill (Codex). 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 由 deprecated prompts/ 迁为 skill; 修 CC 残留 (session-start.cjs→py); 铁律引用名称化. v9.9.0: 路由审议思维链 — 感知→假设→四维权衡→决策+置信度→落盘 route-note; 中途 re-route 只升不降.

Sep 17
wenjunduan Skill

Athena Dev 5

Athena 主入口 skill (Codex). 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 由 deprecated prompts/ 迁为 skill; 修 CC 残留 (session-start.cjs→py); 铁律引用名称化. v9.9.1: 路由输出可审计决策摘要 (候选、证据、权衡、决策、置信度), 不要求暴露私有思维链; re-route 只升不降.

Sep 17
wenjunduan Skill

Brainstorm 6

PACE 可选最早 stage. 用户想法模糊时通过对话理清楚. AI 角色: 思考伙伴, 挖用户真正想解决的问题, 必要时提出更好的替代方案. 完成后产出 sprints/{date}-{slug}/brainstorm.md 并路由到 plan / roadmap / direct design.

Sep 17
wenjunduan Skill

Athena Dev 6

Athena 主入口 skill (Codex). 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 由 deprecated prompts/ 迁为 skill; 修 CC 残留 (session-start.cjs→py); 铁律引用名称化. v9.9.1: 路由输出可审计决策摘要 (候选、证据、权衡、决策、置信度), 不要求暴露私有思维链; re-route 只升不降.

Sep 17
wenjunduan Skill

Athena Dev 7

Athena 主入口 skill (Codex). 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 由 deprecated prompts/ 迁为 skill; 修 CC 残留 (session-start.cjs→py); 铁律引用名称化. v9.9.1: 路由输出可审计决策摘要 (候选、证据、权衡、决策、置信度), 不要求暴露私有思维链; re-route 只升不降.

Sep 17
wenjunduan Skill

Brainstorm 7

PACE 可选最早 stage. 用户想法模糊时通过提问理清楚. v9.9.3 grill-me 化 (借 Matt Pocock grill-me, MIT): 一次一问 + strawman 推荐答 + 先查库再问人. AI 角色: 相不是生成提案让用户审, 而是用问题把用户的真实意图、约束、隐含假设挖到台面上. 完成后产出 sprints/{date}-{slug}/brainstorm.md (distilled log) 并路由到 plan / roadmap / direct design.

Sep 17
wenjunduan Skill

Athena Dev 10

Athena 主入口 skill. 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.6.4 升级: 加 brainstorm + roadmap 分诊 (铁律 14), 加路由检测自动 ultrathink 提示.

Sep 17
wenjunduan Skill

Brainstorm 10

PACE 可选最早 stage. 用户想法模糊时通过对话理清楚. AI 角色: 思考伙伴, 挖用户真正想解决的问题, 必要时提出更好的替代方案. 完成后产出 sprints/{date}-{slug}/brainstorm.md 并路由到 plan / roadmap / direct design.

Sep 17
wenjunduan Skill

Athena Dev 11

Athena 主入口 skill. 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 铁律引用名称化 (CC/CX 编号非对称, 引用一律用铁律[名称]).

Sep 17
wenjunduan Skill

Brainstorm 11

PACE 可选最早 stage. 用户想法模糊时通过对话理清楚. AI 角色: 思考伙伴, 挖用户真正想解决的问题, 必要时提出更好的替代方案. 完成后产出 sprints/{date}-{slug}/brainstorm.md 并路由到 plan / roadmap / direct design.

Sep 17
wenjunduan Skill

Athena Dev 12

Athena 主入口 skill. 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 铁律引用名称化 (CC/CX 编号非对称, 引用一律用铁律[名称]).

Sep 17
wenjunduan Skill

Athena Dev 13

Athena 主入口 skill. 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 铁律引用名称化 (CC/CX 编号非对称, 引用一律用铁律[名称]). v9.9.0: 路由审议思维链 — 感知→假设→四维权衡→决策+置信度→落盘 route-note; 中途 re-route 只升不降.

Sep 17
wenjunduan Skill

Athena Dev 14

Athena 主入口 skill. 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 铁律引用名称化 (CC/CX 编号非对称, 引用一律用铁律[名称]). v9.9.1: 路由输出可审计决策摘要 (候选、证据、权衡、决策、置信度), 不要求暴露私有思维链; re-route 只升不降.

Sep 17
wenjunduan Skill

Athena Dev 15

Athena 主入口 skill. 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 铁律引用名称化 (CC/CX 编号非对称, 引用一律用铁律[名称]). v9.9.1: 路由输出可审计决策摘要 (候选、证据、权衡、决策、置信度), 不要求暴露私有思维链; re-route 只升不降.

Sep 17
wenjunduan Skill

Athena Dev 16

Athena 主入口 skill. 接收用户任务, 做 PACE 路由分诊 (brainstorm/roadmap/plan/...), 启动对应 stage. v9.7.0: 铁律引用名称化 (CC/CX 编号非对称, 引用一律用铁律[名称]). v9.9.1: 路由输出可审计决策摘要 (候选、证据、权衡、决策、置信度), 不要求暴露私有思维链; re-route 只升不降.

Sep 17
wenjunduan Skill

Brainstorm 12

PACE 可选最早 stage. 用户想法模糊时通过提问理清楚. v9.9.3 grill-me 化 (借 Matt Pocock grill-me, MIT): 一次一问 + strawman 推荐答 + 先查库再问人. AI 角色: 相不是生成提案让用户审, 而是用问题把用户的真实意图、约束、隐含假设挖到台面上. 完成后产出 sprints/{date}-{slug}/brainstorm.md (distilled log) 并路由到 plan / roadmap / direct design.

Sep 17
nahisaho Skill

Orchestrator 7

Route an agent-skills-builder request to the smallest valid sub-skill flow. Use when deciding whether work should go to discovery, single-skill generation, suite generation, validation, harness design, or release readiness.

Sep 17
yejiming Bundle

Bitget Wallet 2

Interact with Bitget Wallet API for crypto market data, token info, swap quotes, RWA (real-world asset) stock trading, and security audits. Use when the user asks about wallet, token prices, market data, swap/trading quotes, RWA stock discovery and trading, token security checks, K-line charts, or token rankings on supported chains (ETH, SOL, BSC, Base, etc.).

Sep 17
codyswanngt Bundle

Lisa E2e Coverage Gaps 2

Explore gaps in the automated…

Sep 17
dingxingdi Bundle

Open Domain Data Discovery And Table Selection 2

Skill: open-domain data discovery and table selection

Sep 17
sethdford Skill

Definition Of Done 2

PRD and requirements skill for product managers.

Sep 17
sethdford Skill

Change Management 2

Stakeholder management skill for product managers.

Sep 17
s3yed Skill

Deployment Inspection 2

End-to-end investigation of a live client deployment — platform detection, subdomain discovery, deployment API access (Netlify), JS bundle analysis, repo discovery.

Sep 17
agents-store Skill

MCP Tools 3

Set up and use shadcn MCP servers for AI-assisted component discovery and installation. This skill should be used when the user asks about "shadcn MCP", "shadcn MCP server", "set up shadcn MCP for Claude", "component MCP tools", "Jpisnice shadcn MCP", "shadcn-ui-mcp-server", "AI component installation", or needs to configure MCP servers for shadcn/ui component work.

Sep 17
mkurman Skill

To Prd

Turn the current conversation context into a PRD and submit it as a GitHub issue. Use when user wants to create a PRD from the current context.

Sep 17
mkurman Skill

To Issues

Break a plan, spec, or PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Sep 17

Frequently asked questions

What are Product & Planning agent skills?

Which Product & Planning skills are most installed?

Popular Product & Planning skills on SkillMD right now include roadmap, roadmap, roadmap. Rankings shift as installs change; sort this page by "Most installs" for the live list.

Do Product & Planning skills work with Claude Code and Cursor?

Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.