Home / ccoalm / ccl-skills · GitHub

multi-perspective-research SKILL.md skillA

multi-perspective-research from ccoalm/ccl-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add ccoalm/ccl-skills/multi-perspective-research@git:20260911.176f19b

Pins git:20260911.176f19b in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: ccoalm/ccl-skills
Path: skills/multi-perspective-research/SKILL.md
Versions recorded: 2
Latest version: git:20260911.176f19b, committed Sep 11, 2026
First version recorded: Aug 12, 2026
Size: 33,377 bytes
Repository stars: 6
License: Apache-2.0

调研一个主题 / 深度调研 / deep research / 调研某个产品·公司·赛道 / 多视角研究 / 帮我研究一下 X / 写作前调研 / 领域·组织研究（不喂决策）/ research a topic → run a structured research loop（视角枚举 → 矛盾图 → 合成简报 → 自评）with evidence-grounding discipline, instead of one-question surface answers; another installed deep-research skill may serve as a search tool inside this loop, not replace it. Skip：一查便知的单点事实问题 → 直接回答不套流程；请求点名了候选让选、或用裁决措辞要结论（选哪个 / 要不要上 X / 该不该做 / 可不可行）→ 先 `product-rd-workflow`（它可回调本技能产调研底稿）；纯主题/领域/产品/写作准备调研留在本技能；拷问已有方案 → `grill-me`；bug…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Multi-Perspective Research（多视角主题调研）

当用户要研究、调研、深入了解一个主题（写文档前、竞品/组织/领域研究、演讲/谈判准备，或被 `product-rd-workflow` 的选型/评估 gate 调用产调研底稿）时使用。单问单答只会返回最大众化的表面共识；本技能用结构化的多视角流程逼出争议、利益结构、历史先例和领域盲区。

方法改编自 STORM（Shao et al., "Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models", NAACL 2024；开源实现 `github.com/stanford-oval/storm`）。论文报告的同行评审评测显示，其成文条理性与覆盖面均显著优于 outline-driven RAG 基线（具体数字以原文为准：`aclanthology.org/2024.naacl-long.347`）。后续 Co-STORM（Jiang et al., EMNLP 2024）加入 moderator（从检索到但未被使用的信息中提问，专挖盲区）与动态思维导图。STORM 的核心洞察：研究质量取决于**提问的视角多样性**，而不是单个问题的措辞。

**主张边界（外部证据核查后收窄）**：证据支持多视角提问提升调研的*覆盖面、条理性和盲区发现*（写作/研究合成场景）；证据**不支持**"同一模型模拟多个 persona 辩论就能稳定提升事实正确性"——两项独立评测（Smit et al., "Should we be going MAD?", ICML 2024, PMLR v235；及 "Stop Overvaluing Multi-Agent Debate", arXiv:2502.08788, 2025）均显示同质 persona 辩论常打不过 self-consistency 等单模型基线，模型异构与真实检索才是可靠增益。所以本技能把多视角用于**提问与覆盖**，把正确性交给下面的证据落地纪律。

## 何时不用

- 用户已有方案、要的是追问和压力测试 → `grill-me`。
- 请求本质是交付决策（选型结论、可行性评估、方案评估）→ `product-rd-workflow` 的对应 gate 拥有决策与证据标准；本技能只产出调研底稿。判别标准取可操作面：请求**点名候选让选**或**用裁决措辞要结论**（选哪个/要不要/该不该/可不可行）→ `product-rd-workflow`；纯主题/领域/写作准备调研 → 本技能。调研中若演变为要拍板（用户开始追问"那选哪个"），当场移交 `product-rd-workflow`。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add ccoalm/ccl-skills/multi-perspective-research@sha256:6d3ae72a944725b9

The line at the top of this page pins the label git:20260911.176f19b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_xyuwc6hrhfujpzex.svg)](https://markdownregistry.com/a/art_xyuwc6hrhfujpzex)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 12, 2026 and Sep 11, 2026, about one every 30 days.

version	committed	commit	size	audit
git:20260911.176f19b latest	2026-09-11	176f19b	33,377 B	A	view · diff
git:20260812.206facb	2026-08-12	206facb	33,239 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (33377 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

ccoalm/ccl-skills · 6 stars · license Apache-2.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_xyuwc6hrhfujpzex
GET https://markdownregistry.com/api/v1/resolve?ref=ccoalm/ccl-skills/multi-perspective-research
GET https://markdownregistry.com/api/v1/blob/6d3ae72a944725b9e31ab871a09cec8bc4e07ff65f6e3a57de125f2106eff5c7

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.