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 | $0.00026 | $0.00541 |
| Sonnet 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 10d 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.
- 10d 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 6d ago), licensed MIT. It adds 51 tokens to every session and 1,081 once invoked, about $0.0003 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
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.
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.
superposition
Prepares a normalized state with sparse computational-basis support using compact coefficient preparation followed by a support permutation. The current implementation is exact up to floating-point error but materializes dense matrices.
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…
shor
Use this skill when the user asks for Shor integer factorization, quantum order-finding, period estimation, or implementing/running/debugging ShorAlgorithm in this repository (especially matrix/operator methods, IQFT-based phase post-processing, and continued-fraction period recovery). Keywords: shor, factor N, order…
simon
Use for implementing, explaining, running, or debugging Simon's algorithm in this repository, especially for oracle construction, measurement interpretation, GF(2) post-processing, simulator state extraction, and compatible reimplementation. Skill-first for covered code generation, runnable examples, execution…