double6-deep-research SKILL.md skillA
double6-deep-research from double6-ai/double6-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add double6-ai/double6-skills/double6-deep-research@v2.3.0Pins v2.3.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- double6-ai/double6-skills
- Path
skills/double6-deep-research/SKILL.md- Versions recorded
- 7
- Latest version
- v2.3.0, committed Oct 23, 2026
- First version recorded
- Jul 26, 2026
- Size
- 24,794 bytes
- Repository stars
- 39
- License
- MIT
面向开放全景、固定对象比较和有界决策问题，使用宿主已有搜索与网页读取能力完成多来源深度研究并交付完整、可读、可核验的报告。用于用户要求深入调研某一主题、比较多个对象、形成有证据的决策建议、梳理某领域截至当前的研究进展或核验一组复杂事实，也适用于英文 deep research、landscape review、evidence-based comparison 请求；不用于无需多来源综合与证据审计即可完成的轻量请求，例如任务状态查询、简单事实查询或单页内容摘要。.
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
# Double6 Deep Research 目标是回答用户的问题并交付一份真正可读的完整报告。来源数量、ledger 大小、字段数量和 validator 通过都不能代替报告质量。 ## 1. 冻结任务合同 把用户请求拆成明确的问题清单，记录： - 研究对象、时间范围、地域和排除项； - 每个必须回答的问题； - 用户需要的输出形态、比较维度和决策用途； - 哪些结论需要当前信息，哪些可以使用稳定历史材料。 有关键歧义且不同解释会改变报告时再提问；否则采用保守假设并在报告中说明。报告语言和 格式跟随用户请求；用户未指定时使用其提问语言。 买车、选课、选工具或其它要做决定的问题，先问清最多三个会改变结论的条件，例如地点、 时间范围和预算或备选对象。用户已经写明的不要再问。问完或沿用用户原话后，把这些条件写进 `request_snapshot.md` 或报告里的 `## 假设`；英文可以用 `## Assumptions`。并在 `research_record.json` 里设置 `decision_task: true` 和最多三条 `decision_assumptions`。 假设不能写成官方事实。 成本、时延、部署、采用、风险等用户明确要求的维度必须分别成为可检查的问题，不能合并成 “应考虑这些因素”的泛化清单。 ## 2. 制定自适应研究计划 先写 `research_plan.md` 并在对话里贴出，再开始搜索或打开网页。计划要有三块，标题跟随用户语言： - 要回答的问题（`## 要回答的问题` 或 `## Questions`）：逐条写下即将研究的问题； - 准备查的来源（`## 准备查的来源` 或 `## Sources`）：每类问题准备打开的来源类型； - 会标成未知的内容（`## 会标成未知的内容` 或 `## Unknowns`）：打不开或对不上的对象、数字和维度会怎样标出。 问号用全角或半角都可以，检查时会忽略空格和标点。 用户没有反对再动手。每轮检索结束后，用一两句话追加到 `research_log.md`：打开了什么、还缺什么。 对话里也发这句进度。不要等全文写完才第一次告诉用户在查什么。 为每个问题先冻结覆盖合同：需要哪些来源类型、是否必须有利益关系独立的证据、必须执行 哪些时效性／反证／遗漏检查，以及需要覆盖哪些对象和比较维度。优先一手来源；比较胜负、 行动建议、风险、真实采用等结论不能只依赖利益相关方自述。 不要预先规定统一来源总数。开放全景通常需要比固定比较更多来源，但是否充分取决于： - 每个重要问题是否已经有证据； - 关键对象和反例是否覆盖； - 来源是否足以区分事实、厂商自述和推断； - 继续搜索是否仍会改变主要结论。 …
Read the whole file at its exact version.
How to install
mdr add double6-ai/double6-skills/double6-deep-research@sha256:dc14f155d7de34d3The line at the top of this page pins the label v2.3.0, 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.
[](https://markdownregistry.com/a/art_2ad7xvispt2npzrd)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Jul 26, 2026 and Oct 23, 2026, about one every 15 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.3.0 latest | 2026-10-23 | d66a08f | 24,794 B | A | view · diff |
| v2.3.0 | 2026-10-15 | 4581f08 | 23,735 B | A | view · diff |
| v2.2.1 | 2026-10-08 | adfe92f | 18,757 B | A | view · diff |
| v2.0.2 | 2026-07-31 | 362ae31 | 6,479 B | A | view · diff |
| v2.0.1 | 2026-07-31 | 5bb7449 | 6,510 B | A | view · diff |
| git:20260727.45ec00f | 2026-07-27 | 45ec00f | 8,916 B | A | view · diff |
| git:20260726.9e1f595 | 2026-07-26 | 9e1f595 | 6,341 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (24794 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
double6-ai/double6-skills · 39 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2ad7xvispt2npzrd GET https://markdownregistry.com/api/v1/resolve?ref=double6-ai/double6-skills/double6-deep-research GET https://markdownregistry.com/api/v1/blob/dc14f155d7de34d3f1ed2decedd416dea4ceb11633fc5e310569feea630f4270
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.