Skip to content
Agentmart
Submit a tool

need-research

决策级盲区调研 — 当用户说 /need-research、"扫我的盲区"、"我不知道我不知道什么"、"给我决策建议"时触发。语义=补 unknown unknowns:不只答问的,更找没问但会咬人的,最终给带默认值的决策选择题。硬约束:总代理≤10(常态 3-8 sonnet)、全程禁…

Skill by 0fuk

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying need-research?

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/0fuk-need-research

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

决策级盲区调研 — 当用户说 /need-research、"扫我的盲区"、"我不知道我不知道什么"、"给我决策建议"时触发。语义=补 unknown unknowns:不只答问的,更找没问但会咬人的,最终给带默认值的决策选择题。硬约束:总代理≤10(常态 3-8 sonnet)、全程禁 opus、主循环零子代理。通用技能;args=调研问题(可空)。

Use cases: research

Reviews

Write a review

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. Checked Oct 25, 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/need-research

What's inside

Skill name
need-research
Description
决策级盲区调研 — 当用户说 /need-research、"扫我的盲区"、"我不知道我不知道什么"、"给我决策建议"时触发。语义=补 unknown unknowns:不只答问的,更找没问但会咬人的,最终给带默认值的决策选择题。硬约束:总代理≤10(常态 3-8 sonnet)、全程禁 opus、主循环零子代理。通用技能;args=调研问题(可空)。
License
MIT
Instructions
31 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# /need-research — 决策级盲区调研

## 语义
用户潜台词:「我要做决策,但怀疑认知有洞。」交付三层:①你问的(证据齐全)②你没问但该知道的(按咬人程度排序)③决策选择题(每题带推荐默认值+一句理由;拍板权在用户)。

## 硬约束
- 总代理 ≤10;常态 3-8;宽度跟真实维度走,禁凑数。
- 全程禁 opus;主循环(定题/盲区地图/仲裁/终审/写报告)零子代理;所有 `agent()` 显式 model+effort。
- 调研=sonnet·high;挑刺复核=sonnet·max 双盲;机械盘点=haiku·low(大切片改 sonnet)。
- 带预算守卫;截断必 log 被放弃的覆盖面。

## 流程
**第 0 步 定题(主循环亲做)**:①先定这次调研服务哪个决策——没决策的调研是消遣;不清楚就问(≤3 问);**无人值守窗改为按默认假设开工+入候 owner 清单**。②已知盘点——先查 `~/.claude/research-index.md` 与项目文档有无同题既往报告,只研增量。③画盲区地图——从原题出发列相邻维度:风险合规/真实全周期成本/替代方案(含不做)/时间窗/退出成本/二阶后果/内行会追问什么。④维度清单 3-8 条,至少 1 条纯盲区猎手。
**第 1 步 调研并发派出**:每维度一代理。prompt 必含证据纪律(结论带来源+日期;营销页标 `[营销源]` 降权;找不到写找不到);一手优先;findings 落盘 scratchpad,返回结构化 key_claims(id/claim/evidence/confidence)。盲区猎手 prompt 明写「任务不是答 X,是找 X 周边用户没意识到的坑」。
**第 2 步 双盲对抗(1-2 个,互不知晓)**:V1 证据实在性(逐条重抓来源,不支撑=REFUTED/弱=WEAKENED);V2 反证搜索(换关键词/语言/信源找反例,专抓过期信息、促销价冒充常价、幸存者偏差)。另答 `missed`:整个调研漏了什么。
**第 3 步 终审(主循环)**:仲裁 REFUTED;冲突亲开证据裁决;`missed` 重要的补 1 代理或诚实标未覆盖;写报告;**证伪战果单独成节**。两轮挑刺复核零 REFUTED/WEAKENED 时主循环亲抽 2-3 条承重 claim。

## 交付规格
- 最终报告 HTML(不是 md),浅色、说人话;视觉引用项目设计规范(无则 orch-plan 的通用骨架)。
- 结构(顺序即优先级):一句话答案 / 你问的 / 你没问但该知道的 / 证伪战果 / 决策选择题 / 诚实未知 / 证据附录(可折叠)。
- **决策选择题格式与 /feature-dev 决策包统一**:每题=选项+推荐默认值(加粗)+一句理由+**代价与可逆性**(选错后果/何时还能反悔)。不替用户拍板。
- 落盘报完整绝对路径;同时在 `~/.claude/research-index.md` 追加一行(题目+路径+日期),供下次「只研增量」。
- 排期建议禁日历日串行,画依赖图。

## 规模路由(报给用户选了哪档)
轻(单维度核查)=2 研+1 挑刺复核;标准(选型/方案比较)=4-5 研(含 1 猎手)+2 挑刺复核;重(战略/合规/大额)=6-8 研+2 挑刺复核(硬顶 10)。超出重档分两轮,第一轮收敛后由用户定第二轮方向。

## 反模式
只答原题不扫盲区;盲区清单凑数(每条必答「不知道会怎么被咬」);opus「就这一个环节」;建议写成论文而非选择题;挑刺复核只盖章不证伪;有既往报告还整题重跑;报告落成 md。

From 0fuk/OpenACCP, MIT.

More from 0fuk/OpenACCP

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Oct 14, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/0fuk/OpenACCP
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from 0fuk

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 need-research 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 need-research?

CallGet help
Cite this page

need-research skill. Agent Mart. https://agentmart.dev/skills/0fuk-need-research (last updated 2026-10-24)