Skip to content
Agentmart
Submit a tool

six-lens-opportunity-scan

对明确机会做市场、资本、行业、政策、用户、竞品六看压力测试并输出YES/CONDITIONAL/WATCH/NO。

Skill by xgl1103

IndexedMIT
Write a review

Chalk Labs

Need help deploying six-lens-opportunity-scan?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/xgl1103-six-lens-opportunity-scan

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

对明确机会做市场、资本、行业、政策、用户、竞品六看压力测试并输出YES/CONDITIONAL/WATCH/NO。

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/six-lens-opportunity-scan

What's inside

Skill name
six-lens-opportunity-scan
Description
对明确机会做市场、资本、行业、政策、用户、竞品六看压力测试并输出YES/CONDITIONAL/WATCH/NO。
License
MIT
Instructions
51 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • worker-task.md · references/

SKILL.md (first lines)

# 六看机会扫描 Skill

## 触发
输入已是明确机会命题,至少有目标用户/客户、核心场景和核心问题;可来自单品机会因子、客户、销售、管理层、内部提案、行业/政策/技术变化。模糊的“AI+养老”等先收敛,不直接六看。

## 原则
先判断外部机会,不设计产品;每一看同时找正向和反向信号;事实、判断、未知分离;宏观趋势不能直接证明细分机会;不知道是有效结论;3天轻扫描解决广度,7天深扫描只补影响决策的关键未知。

## 执行
先锁定机会名称、定义、用户、场景、问题、来源、区域、时间范围和当前最需要回答的问题。六维为市场、资本、行业、政策、用户、同类竞品。每维输出判断问题、关键事实/数据、代表案例、来源、支持信号、反向信号、当前判断、信息缺口、是否继续验证。不同维度采用不同来源,关键事实尽量回到可靠/原始来源,冲突标记,不补全。

## 检索通道轻量检查

六看开始前,如需确认检索通道可用,只做通道检查,不搜集产品、市场、竞品或政策证据。

- 检查前先读取 `docs/agent/retrieval-policy.md`。
- 只检查文件中标记为可用的通道;`web_search`(searxng)已知不可用,不得用它探测或反复重试。
- 首选通道最多做一次轻量探测;失败时最多再尝试一次已记录的备用通道。
- 探测通过后立即启动六看子 Agent;探测失败且备用通道也不可用时,停止六看并向用户说明原因。

## 分片执行(硬约束)

六看不得由单个子 Agent 在一次上下文里跑完全部六维。默认拆 **3 个 worker × 2 维**:

| worker | 分片 |
| --- | --- |
| W1 | market, user |
| W2 | capital, policy |
| W3 | industry, competitor |

- 每完成一维**立即**落盘:`innovation:task part --id ID --stage SIX_LENS --part <维度> --file <分片文件>`;
- 单 worker 工具调用上限写入任务信封 `tool_budget`(默认 20);达到上限即中断当前维度并落盘,**不允许耗尽上下文**;
- 任一分片失败只重跑该分片;已 DONE 的分片由 `innovation:task init` 保留,不会被重置;
- 全部完成后由主 Agent 合并:`innovation:task merge --id ID --stage SIX_LENS`。缺片时合并会被拒绝,除非显式 `--allow-partial`(仅用于明确降级为观察)。

## 结论
- YES:外部证据足够支持下一阶段。`market`/`user`/`competitor` 三个核心维度任一缺结论或为 WATCH/NO 时,不得判 YES。
- CONDITIONAL:有机会信号,但关键未知可能改变判断;生成 Evidence Task,补证后更新。
- WATCH:信号不足或时间窗口未到,进入外部机会观察池。
- NO:核心假设不成立或反向证据更强,停止/归档。

## 输出
首屏六看判断看板;正式使用《T-A02 六看扫描表》;列出六维判断、最多3条最强正向信号、最多3条最强反向信号、最多3个最大未知、当前建议和1–3个下一步验证重点。完成后停止,不自动进入适配度、PRD、Demo、MVP、BOM、商业计划或立项。

## 交接
只有 YES,或 CONDITIONAL 且关键阻断已补齐,才向适配度评估交接 Opportunity ID、定义、用户/客户、场景、问题、支付方、六维结果、证据、正反信号、最大未知、结论和下一任务。六看 NO 不因本组织有技术而继续评分。

## 子 Agent 任务书
分片任务书模板、JSON 字段约束、落盘与合并命令见 `references/worker-task.md`。

From xgl1103/ai-product-manager-employee, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 21, 2026 (27 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get six-lens-opportunity-scan running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying six-lens-opportunity-scan?

CallGet help
Cite this page

six-lens-opportunity-scan skill. Agent Mart. https://agentmart.dev/skills/xgl1103-six-lens-opportunity-scan (last updated 2026-10-24)