Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add konglong87/superPM --skill start-super-pmgit clone --depth 1 https://github.com/konglong87/superPMWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/konglong87/superpm/start-super-pm)<a href="https://agentmods.dev/skills/konglong87/superpm/start-super-pm"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/start-super-pm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/konglong87/superpm/start-super-pm"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/start-super-pm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.05916 |
| Opus 5.5 | $0.00010 | $0.02366 |
| Sonnet 5.5 | $0.00005 | $0.01183 |
| Haiku 4.5 | $0.00003 | $0.00592 |
Grade A, and why
start-super-pm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
路由优先级
用户明确意图优先：显式指定 skill、只讨论/不写文件/不联网、跳过环节、已有相关资料等约束，不得被默认黄金路径覆盖。仅在任务与某个 PM skill 的触发条件明确匹配且用户需要其完整工作流时推荐调用；不因关键词或极小可能性强制触发。讨论请求可直接给思路，只讨论时不写文件。
新产品需求的消歧：首次规划一个新产品且没有相关头脑风暴产物时，“我已经想清楚了”“方向明确”“帮我设计需求”只表达想法具体，不是明确跳过 brainstorm。先进入 pm-brainstorm，询问一个关键问题后等待；不要因为“设计需求”跳到 pm-clarify / pm-feature。只有用户明确跳过、已有相关产物，或明确要求一个可独立完成的局部步骤时才直接走对应 skill。已有产品的定位讨论仍可用 pm-position；纯讨论不写文件。
跨 Agent 交互规则
当流程要求与用户交互时：
- 如果当前环境支持 AskUserQuestion，使用 AskUserQuestion（最佳体验）。
- 如果当前环境不支持 AskUserQuestion，必须用普通聊天消息提出同样问题。
- 一次只问一个问题。
- 提问后必须停止当前回合，等待用户回答（STOP and WAIT）。
- 未获用户要求产物时不写文件；需要补充关键输入时提问后等待。
- 已有相关且有效的 docs 可复用，无需重复提问；不相关文档不能替代证据。
常见误区 / Red Flags — STOP
出现以下情况立即停止并回溯：
| 误区 | 正确做法 |
|---|---|
| 使用"应该"、"大概"、"看起来"做结论 | 必须基于实际数据和验证 |
| 未运行检查就声称已完成 | 先验证，再陈述 |
| 用户明确要求轻量或跳过 | 尊重范围，标注未验证假设；不伪造已完成步骤 |
| "这次应该没问题"的想法 | 每次都要重新验证 |
Super-PM 自动触发系统
核心规则
先理解用户要解决的问题与交付边界，再选择明显匹配的 PM skill；若只是简短讨论，可直接回答。
如何访问 PM Skills
在 Claude Code： 使用 Skill 工具。调用 skill 时，其内容会被加载并呈现给你——直接遵循它。不要使用 Read 工具读取 skill 文件。
在其他环境： 查看你平台的文档了解如何加载 skills。
PM Skill 自动触发决策流程（详见下方各模块触发信号）
完整技能包的编排与交接参见
skills/_shared/workflow-contract.md，六条命令顺序由workflow-contract.json校验。若单独安装本 skill，直接按下方内置规则执行，不依赖这些共享文件。
⚠️ 最高优先级路由（仅适用于自然语言请求）
当用户用自然语言提出产品管理任务（而非显式输入 /pm-xxx slash command）：
- "我想做一个XX"
- "帮我规划XX产品"
- "帮我设计一下需求"
- "从0到1做XX"
- "讨论产品方向"
用户请求完整的新产品规划且缺少相关材料时，默认推荐 /pm-brainstorm。若用户只要求某个可独立完成的步骤，则直接进入该步骤并说明证据缺口。
下列情况可跳过默认头脑风暴路径：
- "跳过 brainstorm"
- "直接需求调研"
- "直接验证需求"
- "我已经完成头脑风暴"
仅凭“方向看起来明确”不足以声称头脑风暴已完成；但不应阻止用户明确提出的局部任务。
显式 skill 命令优先：用户直接输入 /pm-demand、/pm-docs 等时进入对应 skill，由该 skill 检查自身所需输入，不强制运行无关环节。
任务类型识别指南
🎯 需求洞察模块（自动触发 pm-demand 或相关 skill）
触发信号：
- 用户提到"需求"、"用户痛点"、"用户场景"、"用户故事"
- 用户想了解"用户想要什么"、"解决什么问题"
- 用户说"我想做一个XX"、"帮我规划XX"、"讨论产品方向"、"从零开始做XX"
- 用户提到具体产品形态但需求不明确：例如"社区"、"app"、"小程序"、"平台"、"工具"、"网站"
- 用户在收集用户反馈、用户调研
- 用户在规划用户旅程、用户画像
- 用户在持续追踪竞品动态、做竞品情报 / 竞品月报
- 用户要设计用户访谈、编写访谈提纲、做一手用户调研
- 用户要核对现有报告的关键结论、证据来源和日期
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 29d ago Changed · -1 lines d5aa9387b0b1
- 1mo ago First seen · 491 lines · 25 tokens per session scan A e11350a2cf3b
start-super-pm is a skill published in the GitHub repository konglong87/superPM (79 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 5,916 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
team-tasks
Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via…
multi-search
A web-search helper that chooses among DuckDuckGo, Tavily, Bing API, and Bing scraping based on the available network.
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
slack-construct-agents
Standing context for Slack sibling agents — one room per team, creator-posted introductions, bot-to-bot hop discipline. Ships as instructions.md composed into the group's CLAUDE.md at spawn; there is no workflow to invoke.
ledger-tasks-yylo
Comprehensive guide for using YYLO Ledger task management without bypassing controller routing, lifecycle state, or mutation receipts. Covers task commands, dependency management, best practices, and workflow patterns. Use when you need to interact with the YYLO Ledger board.