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 prd-to-issuesgit 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/prd-to-issues)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/prd-to-issues"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/prd-to-issues/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/prd-to-issues"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/prd-to-issues.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 | $0.00147 | $0.02635 |
| Opus 5 | $0.00073 | $0.01318 |
| Sonnet 5 | $0.00029 | $0.00527 |
| Haiku 4.5 | $0.00015 | $0.00264 |
Grade A, and why
prd-to-issues 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD 到研发 Issue 拆解（prd-to-issues）
中文速查
- 中文名：PRD 到研发 Issue 拆解 / implementation issues
- 英文稳定名：
prd-to-issues - 分类：产品与 PRD / 工程交付
- 你可以这样叫我：
把 PRD 拆成 issue、需求文档拆任务、生成 GitHub issues、PRD 拆工单、拆 implementation issues、按 vertical slice 拆开发票 - 适合：把已经成型的 PRD、handoff、产品方案或 GitHub PRD issue 拆成端到端可验证、可独立领取的 GitHub implementation issues
- 不适合：从零起草 PRD，改用
prd-architect；评审 PRD 缺口，先用prd-review；制定文件级实现计划、测试策略和提交节奏，交给 Superpowerswriting-plans
Overview
这个 Skill 把 PM 侧需求交付物转成研发可领取的 issue backlog。核心原则是 vertical slice：每个 issue 应该交付一条窄但完整、可 demo、可验收的端到端路径，而不是按“前端 / 后端 / 测试 / 文档”横向拆票。
默认先输出 issue draft 和覆盖矩阵。只有用户明确确认后，才创建或修改 GitHub issues。
Workflow
- 定位输入来源：
- 当前上下文中的 PRD / handoff / 产品方案。
- 本地文件路径。
- GitHub issue URL 或编号；需要时用
gh issue view <number> --comments读取。 - 其他文档摘要；如果无法直接访问，要求用户提供正文或可读取路径。
- 确认输出模式：
draft-only：只输出 issue 拆解草案。默认模式。publish-after-approval：先出草案，用户确认后再创建 GitHub issues。- 不要在没有用户确认时直接
gh issue create。
- 运行 PRD readiness gate。按
references/prd-readiness-checklist.md判断 PRD 是否足够拆 issue：- 目标用户、问题、非目标、主流程、验收口径、关键约束、未决问题。
- 如果阻断信息缺失，先提出最少问题或建议回到
prd-review。 - 输入属于 Product Delivery Package 时，必须先运行 canonical Manifest validator，并只消费它证明为 current/ready 的
pre_split_review；缺失、stale、changes_requested或自审都立即停止拆分。
- 读取必要工程上下文：
- 项目 README、架构说明、ADR、领域词汇、已有 routes/schema/API/UI 约定。
.github/ISSUE_TEMPLATE/、label/type/milestone 约定。- 现有 GitHub issues，避免重复创建。
- 拆 vertical slices。先读取
references/vertical-slice-rules.md：- 每个 issue 必须端到端可验证。
- 优先小而完整的 AFK issue。
- 需要架构决策、设计确认、产品取舍或人工审查时标为 HITL。
- 不要把未确认决策伪装成 AFK 任务。
- 大需求同时建立
version_slice：每个 V1/V2/V3 必须有独立目标、范围、非目标、依赖、验收、风险、回滚点和交付证据；不能只按时间或前后端层级切分。
- 建立覆盖矩阵：
- 每个 PRD section、user story、requirement、验收标准要么被 issue 覆盖，要么明确排除并说明原因。
- 发现 PRD 缺口时，不要硬拆；标记为 HITL clarification 或建议先
prd-review。 - Product Delivery Package 模式下，把 version plan、issue drafts 和 coverage matrix 写入 Manifest，全部记录当前 Backlog Splitter 的
producer_identity，并用 actor-scoped validator 校验；这只形成待最终 Review 的 Package，不自行声明package_ready。
- 输出 draft issue plan。每个 issue 至少包含：
- Title
- Type: AFK / HITL
- Priority / suggested labels
- Source PRD sections
- User stories / requirements covered
- What to build
- Acceptance criteria
- Verification
- Blocked by
- Open questions
- 让用户确认：
- 粒度是否过粗或过细。
- 依赖是否正确。
- HITL / AFK 标注是否正确。
- 是否需要合并、拆分、改优先级或改标签。
- 经确认后发布。发布前读取
references/github-publish.md：- 先查重。
- 用项目 issue template 或
references/issue-body-template.md。 - 用临时文件或
--body-file创建多行 Markdown issue body。 - 按依赖顺序创建，先创建 blocker。
- 创建完成后回填 issue URL / 编号，不关闭或改写 parent PRD。
What ships with it
8 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 · 212 lines · 147 tokens per session scan A 1295b738d7c8
prd-to-issues is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 12d ago), licensed MIT. It adds 147 tokens to every session and 2,635 once invoked, about $0.0007 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.