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 protect-my-hair/nucleus-marketplace --skill requirement-solution-designgit clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplaceWrote 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/protect-my-hair/nucleus-marketplace/requirement-solution-design)<a href="https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/requirement-solution-design"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/requirement-solution-design/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/protect-my-hair/nucleus-marketplace/requirement-solution-design"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/requirement-solution-design.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 | $0.00031 | $0.02214 |
| Opus 5 | $0.00015 | $0.01107 |
| Sonnet 5 | $0.00006 | $0.00443 |
| Haiku 4.5 | $0.00003 | $0.00221 |
Grade A, and why
requirement-solution-design 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求方案设计
核心原则
方案思路被人明确选定前，只能提出方案候选；需求实现方案被评审通过前，不得进入 requirement-decomposition、特性拆解或开发准备。
未读取 PRD、evaluation.md、现有特性树、架构文档和可用代码事实，不得生成方案候选。
未读取 evaluation.md 的"需求尺寸"及父级 requirement-design 的设计深度，不得生成方案候选；需求尺寸和设计深度只决定方案交流深度，不代表人天、sprint、story points 或交付排期。
本阶段三个人审前 subagentPreReview 预审点统一按 _shared/references/subagent-precheck-protocol.md 执行：requirement-solution-review（呈现候选请求选择前）、selected-approach-confirmation（写选择事实前）、implementation-solution-review（请求实现方案评审通过前）。任一预审未取得"材料可提交人工审查"结论前，不得进入对应人审/确认点。
不得请求人工选择方案，除非 requirement-solution-review.subagentPreReview 已确认材料可提交人工审查。不得请求人工评审通过，除非 implementation-solution-review.subagentPreReview 已确认材料可提交人工审查。
缺少明确选定事实时，不得写 selected-approach-evidence.json 或 implementation-solution-candidate.md；推荐倾向不是授权，候选文件不是选择事实。
需求实现方案未评审通过时，不得进入产品子需求拆分、特性拆解、feature-doc-design 或开发准备。
本阶段只写 .nucleus/runs/**/requirement-solution-design/** 候选证据，不写正式 docs/requirement/**、docs/features/**、源码、测试、提交、推送、PR 或 PMS 状态。
使用边界
使用：需求已接纳或条件接纳，需要回答"怎么满足"；父级 requirement-design 编排方案设计阶段。
不使用：需求还在澄清/评估/接纳阶段；已进入拆分、开发准备、测试或代码实现；用户要求直接写研发计划、源码、PR 或推进 PMS。
只解决：产品能力和承载范围、方案未知数/依赖/影响/取舍/风险/验证策略、方案候选对话呈现与选定事实读取、需求实现方案候选和评审门禁。
不解决：不重新判断是否接纳、不替人选择方案、不做拆分或特性拆解、不把 Nucleus 写成 PMS 后端或独立服务。
启动后先做三个判断
- 能否生成方案候选：接纳事实、PRD、
evaluation.md、需求尺寸、设计深度、特性树、架构和代码事实都已读取。 - 能否写需求实现方案候选：候选已通过
requirement-solution-review预审并对话呈现，人的选择回复已通过selected-approach-confirmation预审。 - 能否进入下游：需求实现方案候选已评审通过，父级解锁
requirement-decomposition；本 Skill 自己不进入下游。
任何判断缺事实都停在当前节点并说明缺口；不得用 .ac 文件、review report、summary 或 result.json 制造人工选择、人工评审或 PMS 状态事实。
Checklist
独立启动时，先为以下每项创建宿主 todo/task 并按顺序执行；由 requirement-design 编排调用时，以下项作为父级任务包的当前阶段子任务执行。.ac 文件只是镜像证据，不能替代宿主任务、人工选择、人工评审或 PMS 状态。
- 验证入口事实：读取
.nucleus/context/<workflowRunId>.json、需求目录和接纳证据；缺项 ALERT_AND_BLOCK。 - 读取仓库事实：PRD、
evaluation.md、docs/features/**/feature.md、架构文档和可用代码事实；能从仓库答的不问用户。 - 读取需求尺寸和设计深度：尺寸来自
evaluation.md，深度来自父级；缺失或已变更时 STOP。 - 复述方案问题：说明要补齐的能力、承载范围、取舍和不可确认事实；猜测写成问题。
- 必要时只问一个问题：仍缺影响方案选择的输入时一次只问一个关键问题。
- 生成方案候选证据：按需求尺寸裁剪交流深度（参考
references/solution-method.md），写候选、取舍、风险、验证策略和推荐倾向。 - 调度候选评审预审：按
_shared/references/subagent-precheck-protocol.md对requirement-solution-review执行预审。 - 呈现候选并等待选择：预审通过后按
references/solution-presentation-format.md展示；未明确选定时 STOP。 - 调度选择确认预审：按预审协议对
selected-approach-confirmation执行预审，复核选择事实明确、来源有效、在候选范围内。 - 写需求实现方案候选：预审通过后写
selected-approach-evidence.json和implementation-solution-candidate.md。 - 调度实现方案预审：按预审协议对
implementation-solution-review执行预审。 - 停在评审门禁：预审通过后请求需求实现方案人工评审；评审通过前 STOP，通过后交回父级。
What ships with it
6 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 · 97 lines · 31 tokens per session scan A f3fa67be805d
requirement-solution-design is a skill published in the GitHub repository protect-my-hair/nucleus-marketplace (162 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 2,214 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…