survey-refresh SKILL.md skillA
survey-refresh 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/survey-refresh@git:20260805.a2e3e32Pins git:20260805.a2e3e32 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/survey-refresh/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260805.a2e3e32, committed Aug 5, 2026
- First version recorded
- Jul 21, 2026
- Size
- 10,035 bytes
- Repository stars
- 12
- License
- none declared
当 Workbench/survey-updates.json 中某 survey 积压了新消化的论文（autoresearch 检测到 ≥5 篇 或最老条目超 7 天），或 Supervisor 说"刷新一下 XX survey"时， 把新论文笔记增量合并进对应 Topics/*-Survey.md，并同步刷新其 DomainMap。.
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
信息流闭环的消费端：paper-digest 只记账（survey-updates.json），本 skill 负责把积压的新论文
增量合并进 survey，让 survey 随日常阅读越来越完善，而不必重跑完整 literature-survey。
与 literature-survey 的分工：本 skill **不做任何外部搜索**，只消化库内已 digest 的新笔记；
全量调研（含外部检索）仍由 literature-survey 承担。
## Steps
### Step 1：取 pending 列表
```bash
python3 scripts/survey_updates.py pending --survey {survey-name}
```
- 为空则终止：向调用方报告"无待处理条目"。
- 超过 8 篇时只取最早的 8 篇（按 added_at），其余留给下一轮——避免单次 context 过长。
### Step 2：读取 survey 现状
用 Read 读取 `Topics/{survey-name}.md` 全文，记住其章节结构、分类框架、已覆盖的论文集合、
Key Takeaways / Open Questions。
### Step 3：逐篇读新论文笔记
对 pending 中每篇，用 Read 读取 `Papers/` 笔记全文，提取：核心贡献、关键数据、
与 survey 现有分类的关系（落入哪个既有小节？是否挑战某个既有结论？是否开辟新分类？）。
同时读取 `content_scope`、`verification_status` 与 `## Evidence Ledger`：
- `source-checked`：可使用 ledger 中 `source-verified` 的 claim，但仍只能表述为“原文一致性已核查”，不能写成独立复现。
- `partial`：只使用 source-verified 行；其他 claim 必须降级或省略。
- `unverified` / 缺少字段的 legacy note：可作为论文存在性与主题归类证据，但不得凭它新增关键数字、共识、Key Takeaway 或 Validated Gap。
- `abstract-only`：不得支撑机制、失败条件、benchmark 横向比较或强 novelty claim。
处理 `CUA-Survey` 时，额外建立一行分类记录再决定落点：
| 字段 | 允许值 / 判断 |
|:--|:--|
| `platform` | web / mobile / desktop / cross-platform / hybrid GUI+API/CLI |
…Read the whole file at its exact version.
How to install
mdr add kendrick-stein/mcislab_deepread/survey-refresh@sha256:8fc0c7a8b87bfdd0The line at the top of this page pins the label git:20260805.a2e3e32, 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_agr4lnwzyuc3fqwc)
2 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.a2e3e32 latest | 2026-08-05 | a2e3e32 | 10,035 B | A | view · diff |
| git:20260728.634c4b7 | 2026-07-28 | 634c4b7 | 9,442 B | A | view · diff |
| git:20260724.32f0da4 | 2026-07-24 | 32f0da4 | 8,571 B | A | view · diff |
| git:20260723.fb64ba4 | 2026-07-23 | fb64ba4 | 8,591 B | A | view · diff |
| git:20260721.f94abc2 | 2026-07-21 | f94abc2 | 6,608 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 (10035 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_agr4lnwzyuc3fqwc GET https://markdownregistry.com/api/v1/resolve?ref=kendrick-stein/mcislab_deepread/survey-refresh GET https://markdownregistry.com/api/v1/blob/8fc0c7a8b87bfdd0440f0346350a6a7a65628d24cd52c469be8d88642ecca9c3
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.