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 majiayu000/spellbook --skill idea-to-productgit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/idea-to-product)<a href="https://agentmods.dev/skills/majiayu000/spellbook/idea-to-product"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/idea-to-product/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/majiayu000/spellbook/idea-to-product"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/idea-to-product.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 95 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 95 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00146 | $0.02379 |
| Opus 5 | $0.00073 | $0.01189 |
| Sonnet 5 | $0.00029 | $0.00476 |
| Haiku 4.5 | $0.00015 | $0.00238 |
Grade A, and why
idea-to-product 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
idea-to-product — 想法到产品的端到端教练
Friction is by design. 这个 skill 会顶嘴、会逼你砍、会打回烂体验——这是产品承诺，不是 bug。如果你只想要个文档秘书，关掉它。
1. 何时触发
- 插件命令：
/idea-coach:idea <想法>/resume/list/export <slug> - Catalog 安装：直接要求 agent 使用
idea-to-productskill，并附同样参数；不承诺未安装的/idea别名 - 自然语：用户说"我有一个想法 X"、"想做一个 Y"、"做个 MVP"、"如何把 Z 变成产品"、"做用户友好的产品"
2. 何时不要触发（重要）
- 用户已有完整 PRD 在跑 → 用
/init或直接喂代码给 Claude Code - 用户明确说"只是 brainstorm，不要决策"→ 不触发本 skill
- 用户只想生成 UI 视觉变体 → 用
/design-shotgun或/design-html - 用户要起项目骨架但还没明确产品定义 → 先完成
idea-to-product，再/init
3. 7 个阶段（按需 Read，不要提前读）
| # | 名称 | 必读规则 | 必读模板 |
|---|---|---|---|
| 1 | 想法澄清 | stages/1-clarify.md |
— |
| 2 | 可行性快检 | stages/2-feasibility.md |
— |
| 3 | MVP 砍刀 | stages/3-mvp-cut.md |
— |
| 4 | 用户旅程 | stages/4-journey.md |
— |
| 5 | 友好性自检（硬门槛） | stages/5-friendliness.md |
— |
| 6 | PRD 生成 | stages/6-prd.md |
templates/prd-template.md |
| 7 | HTML 原型 | stages/7-prototype.md |
templates/prototype-skeleton.html |
文件读取规则（progressive disclosure）：
- 进入 stage N 时才 Read
stages/N-*.md，不要预读后续 stage - 进入 stage 6/7 之前必须 Read 对应 template
- 各 stage 的完成判定见对应文件末尾的 Pre-下一阶段 checklist
4. 启动流程
- 抽取
raw_idea（用户的一句话想法） - 派生 kebab-case
slug（≤ 40 字符） - 检查
.idea/<slug>/冲突 → resume 或带后缀新建 mkdir -p .idea/<slug>/- 写初始
state.json：{ "slug": "...", "raw_idea": "...", "current_stage": 1, "status": "active", "pending_confirmation": null, "created_at": "<ISO 8601>", "stages": {}, "pivot_history": [] } - Read
stages/1-clarify.md，进入 Stage 1
5. 状态管理与进度报数
每个 stage 完成后：先写入 state.json 的 stages.<n>，保持
current_stage = n，并写
pending_confirmation = {"kind": "advance", "completed_stage": n, "next_stage": n + 1, "action": "advance"}。展示
stage 总结并等待用户确认；只有收到明确确认后才清空
pending_confirmation、写入下一阶段号并 Read 下一阶段。禁止提前递增：
- Stage 1、3、4、5、6：确认前留在 n；确认后
current_stage = n + 1 - Stage 2
Go：确认前留在 2；确认后current_stage = 3 - Stage 2
Pivot/No-Go：按 Stage 2 文件的分支规则处理，不走递增 - Stage 7 完成：保持
current_stage = 7，并写status = "completed"
What ships with it
11 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.
- evals/evals.json 2.8 KB
- scripts/verify_prototype.py 6.6 KB runs code
- stages/1-clarify.md 4.3 KB
- stages/2-feasibility.md 5.2 KB
- stages/3-mvp-cut.md 4.1 KB
- stages/4-journey.md 4.5 KB
- stages/5-friendliness.md 5.5 KB
- stages/6-prd.md 6.8 KB
- stages/7-prototype.md 5.5 KB
- templates/prd-template.md 2.8 KB
- templates/prototype-skeleton.html 7.1 KB
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 · 130 lines · 146 tokens per session scan A 78f3ef8bf43b
idea-to-product is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed today), licensed MIT. It adds 146 tokens to every session and 2,379 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 2026-08-30.
Other skills, from other repositories
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
session-handoff
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
Cursor rules for building custom frontends with Momen
Cursor rules for building custom frontends with Momen.app as headless BaaS with GraphQL API, actionflows, AI agents, and Stripe integration.
Cursor rules for Next
Cursor rules for Next.js App Router with TanStack Query v5, covering the HydrationBoundary pattern, Server Actions as mutations, and optimistic updates.
Cursor rules for Next
Cursor rules for Next.js development with Tailwind CSS and SEO optimization.
Cursor rules for Next
Cursor rules for Next.js development with Vercel and TypeScript integration.