literature-survey SKILL.md skillA
literature-survey from kendrick-stein/mcislab_deepread is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kendrick-stein/mcislab_deepread/literature-survey@git:20260805.b2d71d9Pins git:20260805.b2d71d9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kendrick-stein/mcislab_deepread
- Path
skills/1-literature/literature-survey/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260805.b2d71d9, committed Aug 5, 2026
- First version recorded
- Jul 21, 2026
- Size
- 21,656 bytes
- Repository stars
- 12
- License
- none declared
当 Supervisor 说"调研""survey""了解研究现状"，或需要系统了解某主题的文献全貌时，搜索外部文献、批量 digest、综合生成调研报告.
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
## Purpose 给定一个研究主题，主动搜索外部文献、自动调用 paper-digest 生成结构化笔记，最终综合所有论文产出一份领域调研报告。 ## Steps ### Step 1：明确调研范围 解析用户输入，确定以下参数： | 参数 | 默认值 | 说明 | |:-----|:-------|:-----| | `topic` | （必填） | 研究主题 | | `year_range` | 近 3 年 | 时间范围 | | `venue_preference` | 无 | venue 偏好 | | `max_papers` | 20 | 最终纳入调研的论文数量上限 | | `scope` | `full` | `full` = 外部搜索 + vault 综合；`vault-only` = 只综合库内已读论文，产出报告到 Reports/（触发词："根据已读论文写个 XX 报告""vault 里关于 XX 的综合"） | 基于 topic 生成 **搜索策略**，覆盖两组角度。 若上层传入 `--run-id`，读取并复用该 manifest；校验 topic 与 artifact paths 后，从 `--resume-stage` 或首个未完成 stage 继续，禁止重复已完成 discovery/digest。否则生成新 `run_id`（如 `survey-<topic>-YYYYMMDD-HHMM`）。所有模式均遵循 `references/research-run-protocol.md`。 **A. 覆盖角度**（建立地图）： 1. **核心主题**：topic 本身的直接搜索 2. **相关方法**：该领域的主流技术路线 3. **Survey / 综述**：搜索已有 survey 论文作为参考锚点 4. **Benchmark / 数据集**：该领域常用的评测基准 5. **应用场景**：下游应用或跨领域迁移 **B. 证据完整性角度**（区分"文献地图"与"论文列表"，至少各跑一条）： 6. **矛盾检索**：challenge / failure / limitation / counterexample / reassessment / replication——主动找与主流结论相反的证据 7. **负结果检索**：negative result / no improvement / failed to reproduce / ablation 失败——被主流叙事略过的证据 8. **邻域检索**：相邻学科是否以不同术语研究了同一问题或机制 9. **术语漂移检索**：用该问题在不同年代/学科的旧名称重新检索，避免只用当前流行词 …
Read the whole file at its exact version.
How to install
mdr add kendrick-stein/mcislab_deepread/literature-survey@sha256:10346d5d062a3319The line at the top of this page pins the label git:20260805.b2d71d9, 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_ptunupftbwtp5uxo)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 21, 2026 and Aug 5, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260805.b2d71d9 latest | 2026-08-05 | b2d71d9 | 21,656 B | A | view · diff |
| git:20260728.634c4b7 | 2026-07-28 | 634c4b7 | 21,318 B | A | view · diff |
| git:20260724.32f0da4 | 2026-07-24 | 32f0da4 | 20,484 B | A | view · diff |
| git:20260723.fb64ba4 | 2026-07-23 | fb64ba4 | 19,669 B | A | view · diff |
| git:20260721.8854a74 | 2026-07-21 | 8854a74 | 12,393 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 (21656 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
kendrick-stein/mcislab_deepread · 12 stars · license none declared · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ptunupftbwtp5uxo GET https://markdownregistry.com/api/v1/resolve?ref=kendrick-stein/mcislab_deepread/literature-survey GET https://markdownregistry.com/api/v1/blob/10346d5d062a33197cb737573ad15657a73392ee72a34c072af4a3b139f4d6d0
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.