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 PANGKAIFENG/ai-product-manager-skills --skill stylework-requirement-planninggit clone --depth 1 https://github.com/PANGKAIFENG/ai-product-manager-skillsWrote 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/pangkaifeng/ai-product-manager-skills/stylework-requirement-planning)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/stylework-requirement-planning"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/stylework-requirement-planning/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/pangkaifeng/ai-product-manager-skills/stylework-requirement-planning"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/stylework-requirement-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00154 | $0.01537 |
| Opus 5 | $0.00077 | $0.00768 |
| Sonnet 5 | $0.00031 | $0.00307 |
| Haiku 4.5 | $0.00015 | $0.00154 |
Grade A, and why
stylework-requirement-planning 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 12d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StyleWork 需求排期共创
Overview
先把一批需求解释成人能讨论的主题地图,回答“这一批在解决什么”,再与用户共创优先级和迭代建议。Skill 只读分析,不修改云效,不修改钉钉,也不修改用户提供的源 Excel;用户最终手工调整。
Core Boundaries
- 不调用
stylework-yunxiao-requirement-sync,不导出、不新建 Sheet、不写回任何系统。 - 不把标题推断写成已确认事实;事实、推断和建议必须分开。
- 不要求批量补录描述、提出方、期望时间、收益数据或完整 PRD 才开始分析。
- 信息不足时仍输出临时建议,并为每个关键判断标注理由、缺失信息、风险和置信度。
- 不替负责人承诺交期,不把建议迭代描述成已经排定。
Minimum Input
接受 Excel、CSV、钉钉 Sheet 的只读内容、截图或用户粘贴的需求列表。优先使用已有字段:
标题、负责人、创建者、迭代、技术难度、优先级、客户名称、URL
描述是可选增强信息,不是启动门槛。若 URL 可用且少量关键需求仅凭标题无法判断,可在用户已经授权查看的前提下,用浏览器只读打开这些需求详情;不要批量修改、评论或改变状态。
Workflow
1. Establish the evidence ledger
记录:
- 已确认字段与用户补充事实;
- 从标题或分组推断的主题;
- 缺失信息;
- 冲突;
- 当前排期假设。
标题只能支持初步分类。模糊标题不得被补造成具体业务目标、客户承诺或技术方案。
2. Summarize what the batch is solving
先完成主题聚类,再讨论逐条排期。输出每个主题:
- 主题名;
- “在解决什么”一句话;
- 代表需求;
- 数量与当前迭代分布;
- 主题性质:用户体验、业务能力、平台基建、可靠性/治理、探索验证或其他;
- 判断依据与置信度。
同时标记:重复/高度相似项、依赖、前置能力、可能的能力链和模糊项。不要因标题相似就自动合并,只输出合并候选和需要核对的差异。
3. Invite high-value clarification
在主题摘要后,向用户提出最多 1-3 个批次级高价值问题,优先确认:
- 当前领导或阶段重点;
- 已承诺客户、固定日期或必须上线事项;
- 本月最需要形成的业务结果,或明确不能做的方向。
不要把每条需求的未知项变成几十个问题。若用户暂时不回答、明确要求直接给建议,或上下文已经足够,继续输出临时版,不暂停整个排期。
4. Apply the planning rubric
读取 references/planning-rubric.md。依次判断:
- 外部硬约束与紧迫性;
- 领导/阶段方向和业务结果;
- 客户影响范围;
- 是否是其他需求的前置能力或共同底座;
- 依赖顺序、技术难度、验证成本和交付风险;
- 需求清晰度与可执行性;
- 负责人和迭代负载是否存在明显集中。
技术难度影响拆分和排期顺序,不自动降低业务优先级。高价值高难度项可建议先做验证或拆分前置任务,而不是简单后移。
5. Produce a co-planning draft
按 references/output-contract.md 输出:
- 批次主题地图;
- 重复、依赖、前置能力和模糊项清单;
- 建议的迭代重点与负载观察;
- 逐需求当前/建议迭代与当前/建议优先级;
- 理由、依赖、风险、缺失信息和置信度;
- 本轮最值得用户调整或确认的 1-3 个决策。
对 26.8.1 这类迭代解释为 2026 年 8 月第 1 周。若迭代日历与此不同,采用用户给出的团队定义。
6. Revise with user direction
用户补充重点方向或澄清需求后:
- 明确列出哪些建议发生变化及原因;
- 保留未变化项,不整表重写得难以比较;
- 更新置信度与剩余风险;
- 输出新的建议草案,仍不执行外部写入。
Confidence Rules
- 高:有明确描述、外部承诺或可验证依赖,且建议直接由证据支持。
- 中:标题和现有字段较清楚,但业务收益、容量或依赖仍有一项关键假设。
- 低:主要依赖模糊标题推断,或缺少会显著改变排期的事实。
低置信度不等于不建议;它表示用户应优先复核。
Definition of Done
- 先解释整批需求在解决什么,再进入逐条排期。
- 重复、依赖、前置能力和模糊项均已显式标记。
- 问题不超过 1-3 个批次级高价值问题,没有要求团队批量补录大量字段。
- 信息不足的项仍有临时建议,且理由、缺失信息、风险和置信度完整。
- 当前值与建议值分开,事实与推断分开。
- 全程只读,没有修改云效、钉钉或源文件。
What ships with it
7 files 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.
- 12d ago First seen · 123 lines · 154 tokens per session scan A 8701a113df86
stylework-requirement-planning is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 12d ago), licensed MIT. It adds 154 tokens to every session and 1,537 once invoked, about $0.0008 per session on Opus 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 2026-08-31.
Other skills, from other repositories
grill-me
Grill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report without writing code. Use when the user wants to clarify requirements, stress-test an idea, compare approaches, or plan before coding.
eol-process
Run a product sunset end to end — decide, align, plan, prepare, announce, close. Use when you need the whole EOL process, not just one artifact.
epic-breakdown-advisor
Break down epics into user stories with Humanizing Work split patterns. Use when a backlog item is too large to estimate, sequence, or deliver safely.
prd-development
Build a structured PRD that connects problem, users, solution, and success criteria. Use when turning discovery notes into an engineering-ready document for a major initiative.
altitude-horizon-framework
Understand the PM-to-Director transition through altitude and horizon thinking. Use when diagnosing scope, time-horizon, or leadership-level gaps.
prioritization-advisor
Choose a prioritization framework based on stage, team context, and stakeholder needs. Use when deciding between RICE, ICE, value/effort, or another scoring approach.