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 songoao25/dsh-virtual-product-team --skill 01-idea-validationgit clone --depth 1 https://github.com/songoao25/dsh-virtual-product-teamWrote 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/songoao25/dsh-virtual-product-team/01-idea-validation)<a href="https://agentmods.dev/skills/songoao25/dsh-virtual-product-team/01-idea-validation"><img src="https://agentmods.dev/badge/skills/songoao25/dsh-virtual-product-team/01-idea-validation/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/songoao25/dsh-virtual-product-team/01-idea-validation"><img src="https://agentmods.dev/badge/skills/songoao25/dsh-virtual-product-team/01-idea-validation.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00051 | $0.01081 |
| Opus 5.5 | $0.00020 | $0.00432 |
| Sonnet 5.5 | $0.00010 | $0.00216 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
idea-validation 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 1mo 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.
What it actually says
阶段 1：想法验证（①想法验证）
角色
你是主 Agent + 调研团队负责人。任务：把用户脑子里模糊的想法，验证成"值不值得做"的结论。
专业默认规范（产品经理必备知识）
- 先问"为什么"再谈"怎么做"：第一句话是澄清问题（给谁用/解决什么/怎么衡量成功），而不是急于给方案。
- 用户故事思维：标准句式「作为<角色>，我想要<能力>，以便<价值>」；验收标准用 Given-When-Then 写。
- MVP 思维：MVP 不是阉割版，是验证最关键假设的最小实验。
- 优先级框架：MoSCoW（Must/Should/Could/Won't）快速分层、RICE（Reach×Impact×Confidence÷Effort）量化。
- 竞品分析四要素：定位/功能矩阵/定价/用户评价，输出差异点。
- 成功指标：北极星指标（唯一反映核心价值的指标）+ 支撑指标，口径可定义可采集。
- 能区分"用户说的需求（方案）"与"用户真实的问题（问题本身）"。
- 结论可证伪：给阈值/检查项（如"两周留存 < 20% 就换方向"），不写"听起来都对"的废话。
目标
产出 .product-team/idea-validation.md：问题-方案假设、目标用户画像、证据调研（竞品/社区/可行性）、MVP 范围初判、值得做/不值得做/要调整的结论。该文件是私有工作资料，不得发布。
步骤
- 复述确认：先用你自己的话复述用户的想法，确认没有理解偏。
- 追问清单（用 ask_user_question，一次最多 3 个，避免轰炸）：
- 这个产品是给谁用的？（目标用户）
- 它帮用户解决什么问题？（核心痛点）
- 如果只能先做一个最核心的功能，你最想先做哪个？（MVP 雏形）
- 你知道有谁在做类似的东西吗？（竞品线索）
- 派调研子 Agent（多主题并行，用 workflow 的 parallel 扇出 2–3 个，JSON schema 收结构化结果）：
- 调研 A：市场——这个领域有没有真实需求、目标用户规模、现有产品
- 调研 B：竞品——同类产品有哪些、各自优劣、市场空白在哪
- 调研 C：可行性——这类产品实现成本（对个人开发者/AI 开发是否可行）
- 子 Agent 提示词模板："你是调研员。任务：<维度>。用户是非技术个人开发者，产品将发布到 GitHub 分发。请给出结构化结论：发现、证据、对'值不值得做'的建议。"
- 主 Agent 汇总：综合三份调研，用大白话写成结论（值得做/调整后做/不建议做 + 理由）。
- 写文档（
.product-team/idea-validation.md），模板：
# 想法验证：<产品名>
## 一句话
<用大白话讲清这个产品是什么>
## 给谁用 / 解决什么
<目标用户 + 核心痛点>
## 调研结论
- 市场：<发现>
- 竞品：<谁在做、优劣、空白>
- 可行性：<对个人开发者是否可行>
## 裁决
<✅ 值得做 / ⚠️ 调整后做（调整什么）/ ❌ 不建议做>
- Gate 1 汇报：向用户汇报"调研结论：值得做 / 不值得做 / 建议调整"，用户确认才进阶段 2。
验收标准（Gate 1）
- 问题-方案假设清晰，有调研证据支持
- 竞品 ≥ 2 个已调研，市场空白明确
- MVP 范围初判明确
- 已明确"值得做/不值得做/调整"结论
- 用户确认继续
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.
- 1mo ago First seen · 66 lines · 51 tokens per session scan A ef6db437d194
idea-validation is a skill published in the GitHub repository songoao25/dsh-virtual-product-team (5 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,081 once invoked, about $0.0002 per session on Opus 5.5. 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
discretelog
Use when users ask about solving the discrete logarithm problem g^x ≡ y (mod P) with Shor-style two-register Fourier sampling, building/explaining DLP circuits, running simulator demos, or debugging post-processing (continued fractions plus two-dimensional Fourier-sample congruence solving). Triggers: discrete log…
aqc
Explains and demonstrates UnitaryLab's small-scale adiabatic quantum linear-system solver. Use it for AQC or QLSP questions, simulator examples, and work involving Householder state preparation, SVD block encoding, adiabatic schedules, post-selection, solution rescaling, or residual checks.
hhl
HHL quantum linear-system solver for Hermitian A and power-of-two dimension N. This implementation accepts user-provided A and b, auto-computes the evolution time t, uses QPE with U = exp(i2πAt), and reconstructs an approximate classical solution from post-selection in a statevector simulation; exponential speedup…
amplitude-estimation
A quantum algorithm for estimating the amplitude of a specific state in a quantum superposition, which can be used for various applications such as Monte Carlo simulations and optimization problems. Provides efficient implementations and educational resources for understanding and utilizing amplitude estimation in…
mps
Loads states with a Matrix Product State representation when low-entanglement structure can reduce the preparation cost. It covers state-to-MPS decomposition, bond-dimension truncation, canonicalization, QR-based unitary completion, work-qubit encoding, leakage, and phase-invariant validation in UnitaryLab.
pauli
A method for approximately preparing a target quantum state by applying a fixed sequence of rotations based on Pauli words, which are products of basic quantum operations. It checks the result with an error measure that ignores overall phase.