nextclaw: Skill for Claude Code

.agents/wiki/skills/strategy/one-shot-product-bet-discovery/SKILL.md

one-shot-product-bet-discovery is a skill for Claude Code, Codex from Peiiii/nextclaw. It costs 73 tokens per session (2,069 once invoked), scanned A, original, MIT.

A decision method for choosing a single high-stakes business opportunity from a small set of finalists. It compares likely success, evidence, constraints, risks, and the tests that could change the ranking.

In plain words
What is it for?
It is for comparing up to a few mature candidates, identifying fatal assumptions and information advantages, estimating conservative probability ranges, and deciding whether a real-world test is justified.
Why use it?
It helps avoid lowering the success standard to fit a favourite idea or mistaking an appealing vision for a likely business. It separates current evidence from what might only be true after validation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Peiiii/nextclaw's own configuration. It tells Claude Code and Codex how to work on nextclaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nextclaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Peiiii/nextclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Peiiii/nextclaw/master/.agents/wiki/skills/strategy/one-shot-product-bet-discovery/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Peiiii/nextclaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for one-shot-product-bet-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/peiiii/nextclaw/one-shot-product-bet-discovery/github.svg)](https://agentmods.dev/skills/peiiii/nextclaw/one-shot-product-bet-discovery)
Your own site
<a href="https://agentmods.dev/skills/peiiii/nextclaw/one-shot-product-bet-discovery"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/one-shot-product-bet-discovery/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.

agentmods 80×15 button for one-shot-product-bet-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/peiiii/nextclaw/one-shot-product-bet-discovery"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/one-shot-product-bet-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,069 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.02069
Opus 5.5 $0.00029 $0.00828
Sonnet 5.5 $0.00015 $0.00414
Haiku 4.5 $0.00007 $0.00207

Measured 1mo ago against content hash 54001fc6b79b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

one-shot-product-bet-discovery 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.

.agents/wiki/skills/strategy/one-shot-product-bet-discovery/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

单次重注商业机会判断

目标

寻找在当前证据下能够越过用户最低胜率的商业机会,而不是为既定愿景或产品形态补理由。候选可以是软件、软硬结合、产品化服务、交易或网络、资产收购、运营型生意及其组合;AI 也可以只存在于供给侧。找不到时明确报告“尚未找到”,不得降低门槛、偷换成功定义或把未来实验成功后的条件概率当成当前概率。若门槛显著高于充分竞争市场的基准,必须找到并验证能够解释超额概率的信息差;不能只在市场已知 idea 中挑相对最好的一项。

这里的概率是用于决策的保守区间,不是假装精确的统计结果。愿景吸引力、技术或交付可行性和商业成功率必须分开判断。

进入条件

开始时冻结本轮成功合同:

  • 成功结果与时间范围;
  • 最低可接受概率;
  • 创始人的资金、时间、能力、分发与机会成本约束;
  • 允许验证到什么程度,以及什么损失不可接受;
  • 品类级胜利、可持续垂直生意、现金流资产经营和技术原型中,本轮究竟判断哪一个。
  • 相邻模式的基准成功率,以及候选需要用什么信息优势解释从基准到目标门槛的提升。

同时确认候选搜索 owner 已形成可审阅账本:主要结构视角已覆盖,原始池经过批量证据和统一过滤,留下不超过三个结构不同的决赛候选。若当前只有创始人的初始想法、零散竞品或第一个看起来合理的方向,不进入本 Skill,也不提前做真实试用。

上下文已有答案时直接复述并继续;只有缺失项会实质改变判断时才询问。事实、外部基准、推断和待验证假设分开记录。

决赛比较与证伪

对每个候选回答:谁会持续付费、为什么现在必须解决、为什么创始人能做到、第一批客户或可收购资产从哪里来、平台或既有供给为何不能轻易抹平、交付成本与信任风险是否可承受。写出关键成立条件、最强反方解释、单点致命假设,以及能够最大幅度改变候选排序的一组证据。

真实世界验证只用于区分桌面证据无法区分的决赛候选。访谈只能验证语言;真实委托、订单或收购谈判验证行为;续约、复购或持续交易验证重复价值;付费验证优先级;交付毛利验证经济性;扩权验证信任;可重复获客或可重复并购验证生意。

给出当前概率区间与依据,并把“验证后的条件概率”单列;区间跨过门槛、或仍依赖未验证的致命假设,都不算达标。每轮在同一探索账本中记录候选因什么证据升降级。已经被证伪的方向没有新证据不得换名字重新进入。

信息差资格门

当目标胜率高于相邻行业或商业结构基准时,信息差是必要而非充分条件。它可以是公开事实推导出的少数派因果判断、未被价格反映的时间窗口,或独有数据、渠道和资产入口,但必须写清:具体预测与期限、市场共识、未被套利原因、领先指标、创始人捕获路径和窗口失效方式。

“市场很大”“别人没做好”“我更努力或更会用 AI”“竞品暂时少”都不构成信息差。没有合格信息差时,保守区间上界不得越过用户门槛;返回未来判断搜索,不能调整权重制造达标结论。

创始人的 AI 局部峰值

当胜出理由包含“更充分地使用 AI”时,必须说清比较对象与局部结果;区分 Token、Agent 数和真实的问题分解、验证、纠偏与持续完成;用交付周期、完成率、人工救火或用户结果证明优势;并说明它如何在别人获得同类模型前沉淀为付费、系统、数据、分发、合同或所有权。只靠创始人长期超负荷操作不能提高商业成功率。

小团队更可能在工作数字化、反馈短、结果可验证、失败可回退且大组织存在协调或利益冲突的区域形成峰值;否则 AI 杠杆不得作为主要胜出理由。

机会应把模型进步作为生产资料和顺风,而不是把当前模型缺陷当作护城河。自动完成某个边界清楚的认知或执行任务、比通用模型多一点提示技巧,通常会被模型能力吞没;除非它同时积累独立、持久且可捕获的资产,否则不能作为 all-in 方向。重运营或线下交付不自动出局,但必须证明毛利、质量控制、区域密度或资产复用能够让小团队长期承受。

All-in 资格门

只有同时满足以下条件,方向才能标记为 all-in qualified:

  • 成功合同没有在评估中被悄悄缩小;
  • 保守概率区间整体越过用户门槛,而不只是乐观端越过;
  • 真实付费、续约或复购、核心结果、可重复触达和可承受单位经济已有行为证据;
  • 候选宣称的核心差异真实创造价值,不是展示功能;
  • 创始人优势能够转化为产品、交付系统、分发、合同、网络或资产所有权优势,并适合长期投入;
  • 不存在一个尚未验证、失败即推翻整个方向的致命假设;
  • 超过市场基准的概率提升有一条已获得行为或领先指标支持的信息差,且创始人能在窗口关闭前捕获;
  • 用户理解剩余风险后仍认可这个方向。

未通过时只允许标记为 探索中、值得验证 或 已淘汰。没有合格方向也是有效结论。

常见偷换

偷换 正确处理
“实验成功后可能超过 50%” 当前仍未达标,单列条件概率
“我们能做出来或交付一次” 只证明技术或单次交付可行,不证明续约、毛利、付费或分发
“市场很大、趋势正确” 继续回答为什么这一小群用户会现在选择我们
“巨头不够专注” 说明可持续的结构性约束,不把意愿猜测当护城河
“下载、注册或赞美很多” 寻找续约、复购、持续交易、付费、扩权与替代成本证据
“只有一次机会,所以必须现在选” 稀缺性提高证据门槛,不提高方向本身的胜率
“我比别人更会用 AI” 定义局部基准、外部结果和优势捕获路径
“这是现有选项里概率最高的一个” 最高不等于越过门槛;缺少信息差时回到未来判断搜索
“竞品还不多” 区分市场不存在、需求不存在和认知领先;写出共识基线、未套利原因与窗口

Read the full file on GitHub · 87 lines

Changes

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.

  1. 1mo ago First seen · 87 lines · 73 tokens per session scan A 54001fc6b79b

Subscribe to this mod's changes

one-shot-product-bet-discovery is a skill published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 2,069 once invoked, about $0.0003 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 2026-09-20.

Related

one-shot-product-bet-discovery compared with skills from other repositories

one-shot-product-bet-discovery next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
one-shot-product-bet-discoveryPeiiii/nextclawSkill263yesterdayMITA73Claude Code, Codex
ha-skill-creatorshiwenwen/hope-agentSkill1.9kyesterdayMITA106Claude Code
ha-browsershiwenwen/hope-agentSkill1.9kyesterdayMITA140Claude Code
ha-logsshiwenwen/hope-agentSkill1.9kyesterdayMITA183Claude Code, Codex
ha-pet-importshiwenwen/hope-agentSkill1.9kyesterdayMITA109Codex
ha-skill-installershiwenwen/hope-agentSkill1.9kyesterdayMITA82Claude Code, Codex
email-draftshiwenwen/hope-agentSkill1.9kyesterdayMITA46Claude Code, Codex