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 agentmods add skills/ryanzhao1011/workframe/prd-writernpx skills add ryanzhao1011/workframe --skill prd-writergit clone --depth 1 https://github.com/ryanzhao1011/workframeWrote 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/ryanzhao1011/workframe/prd-writer)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/prd-writer"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/prd-writer.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.04782 |
| Opus 5 | $0.00048 | $0.02391 |
| Sonnet 5 | $0.00019 | $0.00956 |
| Haiku 4.5 | $0.00010 | $0.00478 |
Grade B, and why
prd-writer scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`cat .claude/workframe-state/plugin-root.txt`)照用,并提示用户 How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD 需求文档编写 Skill
前置依赖
- skill:
document-norms§1(文档归属矩阵)/ §2(frontmatter 字段标准,特别是 §2.6req_slug+sub_req_slug引用契约)。输出路径为projects/modules/<basic>/<sub>/requirements/<req_slug>/<sub_req_slug>/prd.md, frontmattertype: prd+module+req_slug+sub_req_slug必填(version字段 已废除——版本演进进prd.md正文「变更与决策记录」)。 - 项目 PRD 框架:Read
.claude/skills/prd-style/SKILL.md——本项目 PRD 的工序形态 (§1)、维度开关(§2)、章节结构(§3)、各章写法(§4)、标注习惯(§5)的唯一事实源。 缺失时 fallback:读框架默认模板<插件根>/templates/project-skills/prd-style/SKILL.md(插件根 =cat .claude/workframe-state/plugin-root.txt)照用,并提示用户 「本项目未配置 PRD 框架,本次按框架默认执行;正常装机会自动放入,可跑 doctor 检查, 或从上述模板复制到项目.claude/skills/prd-style/后按需修改」。 writing-guide.md(S3 填充前读):core 通用写作纪律。与项目框架冲突时以项目为准 (机器契约除外,见项目框架 §0)。
环境依赖:Node.js 18+(仅 S5 HTML 原型预览/截图需要,可选)
可选委托(按项目配备,不强依赖):截图归档委托
screenshotskill(详见 html-prototype.md);外部发布由项目配备的发布 skill 处理,不在本 skill 内;Obsidian CLI 增强按需委托obsidian-doc-structure/obsidian-link-audit/obsidian-safe-write, CLI 不可用时 fallback 到Read/rg/Edit。
Workflow:六段骨架
「做什么」由本 skill 固定;「用什么形态做」读项目框架 §1 工序形态声明。
S1 理解 读上下文 + 维度推断 → 呈现理解摘要 [固定]
S2 骨架确认 范围骨架(形态读框架 §1)→(启用图件时)结构图草稿
→ 章节预告(按框架 §3 裁剪)→(框架声明时)页面骨架 [形态可配]
S3 填充 按框架章节分波写,[待确认] 汇总一次问 [章节/波次可配]
S4 落盘 机器契约段:触发词 → 路径/frontmatter/索引 [固定]
S5 附属产物 按框架 §1 声明执行(图件渲染 / HTML 原型 / 无) [整段可配]
S6 发布 仅用户显式触发 [固定]
核心原则:AI 主动分析填充,用户确认补充。不确定的内容标 [待确认],汇总后一次性
问用户。所有交付物中不保留需求确认过程标记(如"Q12"、"用户澄清 #2"),确认结论作为正常
需求点融入正文对应位置。
demo 先行变体(项目框架启用原型工序、且用户已有可交互 demo 时的标准路径):
- S2 范围与结构草稿从 demo 反推(仍需用户确认——demo 可能只覆盖部分需求);页面骨架 确认跳过(以 demo 为准)
- S3 交互细节直接读 demo 的 HTML / JS 提取(状态文案、禁用逻辑、显隐条件、状态机以 代码为准),对话记录仅作补充
- S5 改为归档——demo 复制到
prototypes/(不重新生成),删除 tmp/ 原件避免双源; 按需截图归档assets/ - demo 本身的生成规范见 skill:
html-demo
S1 理解
What ships with it
3 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.
- 5d ago First seen · 277 lines · 97 tokens per session scan B 50f4adb90fba
prd-writer is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 18d ago), licensed MIT. It adds 97 tokens to every session and 4,782 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
discover
Runtime catalog — list all installed skills, agents, and active hooks. Use when you want to know what's available.
html-prototype
Generate HTML prototypes (single-file, browser-openable) for product mockups using the user's design system — fonts, color scales, radii, shadows, components, all driven by a tokens.css file. Use when the user asks to make a 原型 / mockup / HTML 设计图 / 设计图给前端 for a PRD module, OR redesign an existing prototype. Output…
feature-acceptance
研发提测后接管浏览器,对照 PRD(必给)+ HTML 原型(自动找)逐项验收线上实现,产出差异清单(实现 / 部分实现 / 未实现 / 与原型或 PRD 不一致)+ 截图证据 + 阻塞问题排序。Use whenever PM 说「验收 XX」「跑一下 XX」「研发提测了」「对一下需求和线上」「点一下 XX 看符不符合需求」「看哪些实现了哪些没做」「上线前 check」「灰度验收」「acceptance」「QA check」,or 给出 PRD 路径 + 线上 URL 让 Claude 走流程。也适用于 PM 想自己点某功能、判断和需求差异时陪她一起跑。区别于 prd skill:本 skill 验证线上现状,不修改 PRD…
prd
Write, rewrite, polish, restructure, or review product requirements documents (PRDs). Use whenever a task touches a 需求文档 / PRD —— 新写、重构、统一口径、补页面结构 / 字段 / 规则 / 边界 / 异常处理、加指标口径定义、按数据看板或某类骨架组织章节,或把讨论 / 会议记录整理成正式产品文档。Trigger even when the user does NOT say "写需求" —— e.g. "把这个加到…
gbg
Convert any plan, PRD, feature idea, or brief into a sequenced goal-by-goal execution document with reviewer-gated commits — for everyday feature development, MVPs, migrations, refactors, and hardening alike. Generates a project brief, per-goal scope/tasks/acceptance criteria, an LLM-reviewer prompt (Codex/etc.), a…
ui-walkthrough
把一份 UI 设计 HTML 和研发上线的页面,同视口、同状态截图比对 + 读 computed style 实锤,产出 UI 还原度差异清单(结构 / 组件 / 颜色 / 字体 / 圆角 / 图标 / 间距 七维,每条标明设计值 vs 线上值)。Use whenever PM 说「UI 走查」「走查一下 UI」「对一下 UI」「UI 还原度」「还原度走查」「线上跟设计稿对一下」「前端还原得对不对」「页面跟这份 HTML 对一下」「UI 验收」「设计还原走查」,或给出 设计 HTML 路径 + 线上 URL 让 Claude 比视觉差异。区别于 feature-acceptance skill:那个验业务逻辑 / 字段 / 操作…