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/feature-breakdownnpx skills add ryanzhao1011/workframe --skill feature-breakdowngit 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/feature-breakdown)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/feature-breakdown"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/feature-breakdown.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 | $0.00041 | $0.02035 |
| Opus 5 | $0.00020 | $0.01018 |
| Sonnet 5 | $0.00008 | $0.00407 |
| Haiku 4.5 | $0.00004 | $0.00203 |
Grade A, and why
feature-breakdown 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 4d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
功能拆解技能
拆解原则
- 粒度控制:推荐 0.5–1 天内可完成;研发执行任务优先 ≤4 小时;非研发任务(调研、内容、交付物)按"可独立验收的交付物"拆
- 独立可测:每条 Story 满足 INVEST 全部 6 项
- 依赖明确:
depends_on字段 + 关键路径标注 - 价值优先:先拆高价值 Story,再拆技术支撑任务
非软件项目映射:Epic = 目标/交付物;Story = 阶段成果;Task = 行动项。INVEST 和价值矩阵同样适用,Step 3 技术层可跳过。
拆解流程
第 1 步:确认 Epic 边界
从需求文档中提取 Epic 范围:
Epic: EPIC-{序号}
标题:{一句话描述}
范围:{包含哪些功能模块}
排除:{明确不包含的内容}
来源:modules/<basic>/<sub>/requirements/<req_slug>/(需求资产包)
小型需求(Quick Brief 级别)可跳过此步,直接拆 Story。
第 2 步:选择拆分技术
根据需求特征选择最合适的拆分方式:
| 技术 | 适用场景 | 示例 |
|---|---|---|
| A. 按工作流步骤 | 有明确的用户操作流程 | 操作流程:选择配置→输入内容→设定参数→提交→查看结果 |
| B. 按用户角色 | 多角色使用同一功能 | 普通用户的操作视图 / 管理员的配置管理 / 超级管理员的全局设置 |
| C. 按数据类型 | 涉及多种数据实体 | 内容数据 / 模板数据 / 用户配额数据 |
| D. 按 CRUD 操作 | 数据实体的标准管理 | 模板的创建/查看/编辑/删除 |
| E. 主路径优先 | 需要快速验证核心假设 | 先实现最小可用的核心流程,再补充配置和管理功能 |
决策建议:
- 有明确操作流 → 优先选 A
- 多角色场景 → 优先选 B
- 标准 CRUD → 优先选 D
- 不确定 → 默认选 E(降低风险)
第 3 步:按交付链路拆分 Task
每条 Story 进一步拆分为 Task,按依赖方向排列。选择最贴合项目类型的维度:
| 维度 | 适用场景 | 示例 |
|---|---|---|
| 技术层(软件项目) | Web/移动端研发 | 数据层 → API 层 → 业务层 → UI 层 → 集成层 |
| 交付物/里程碑 | 客户交付、研究类 | 调研报告 → 方案草稿 → 客户确认 → 终稿交付 |
| 内容生产流 | 内容创作 | 选题确认 → 初稿 → 审校 → 发布 → 数据复盘 |
| 角色流转 | 跨角色协作 | PM 需求 → Dev 实现 → QA 验收 |
| 风险假设 | 有核心不确定性 | 先验证最高风险假设,再补全路径 |
第 4 步:工时估算
| 复杂度 | 预估工时 | 典型任务 |
|---|---|---|
| 简单 | 1-2 小时 | 简单 CRUD、UI 微调、配置变更 |
| 中等 | 2-3 小时 | 业务逻辑、数据校验、组件开发 |
| 复杂 | 3-4 小时 | 复杂交互、外部集成、性能优化 |
| 超标 | >4 小时 | 必须继续拆分 |
第 5 步:价值 vs 工作量矩阵
对拆解后的 Story 进行 2×2 矩阵评估:
低工作量 高工作量
高价值 │ ★ 优先做 │ 计划做(安排迭代) │
低价值 │ 顺手做(填充空闲)│ 不做(除非必须) │
评估维度:
- 价值:用户影响力 + 战略对齐度 + 业务紧迫性
- 工作量:开发工时 + 技术风险 + 依赖复杂度
第 6 步:INVEST 验证
对每条 Story 逐项检查:
| 原则 | 检查问题 | 通过? |
|---|---|---|
| I ndependent(独立) | 不依赖未承诺的其他 Story? | ☐ |
| N egotiable(可谈判) | 有多种实现方案可选? | ☐ |
| V aluable(有价值) | 对用户或业务有明确价值? | ☐ |
| E stimable(可估算) | 团队理解范围,能给出工时? | ☐ |
| S mall(足够小) | 可在一个迭代内完成? | ☐ |
| T estable(可测试) | 有可写出验收方向?(详细 AC 由 acceptance-criteria 细化) | ☐ |
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.
- 4d ago First seen · 155 lines · 41 tokens per session scan A fdb4f8735aa2
feature-breakdown is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 18d ago), licensed MIT. It adds 41 tokens to every session and 2,035 once invoked, about $0.0002 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
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…