memory-retrieve SKILL.md skillA
memory-retrieve 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/memory-retrieve@git:20260728.634c4b7Pins git:20260728.634c4b7 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/5-evolution/memory-retrieve/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260728.634c4b7, committed Jul 28, 2026
- First version recorded
- Apr 28, 2026
- Size
- 2,554 bytes
- Repository stars
- 12
- License
- none declared
被其他 skill 内部调用，从 Workbench/memory/ 中检索与当前任务相关的历史经验。 当 idea-generate 需要查失败方向、experiment-design 需要查有效方法、 或任何 skill 需要历史上下文时调用.
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 memory-retrieve 是 MindFlow 记忆系统的检索接口。它被其他 skill 内部调用（如 idea-generate 查失败方向、experiment-design 查有效方法），从 `Workbench/memory/` 的结构化记忆文件中检索与当前任务语义相关的历史经验。 这是 Layer 1 的轻量实现——纯 Markdown 文件读取 + LLM 语义匹配，零外部依赖。未来 Layer 2 可用向量检索替换，接口不变。 ## Steps ### Step 1：确定检索范围 根据 `scope` 参数确定要读取的记忆文件： | scope | 目标文件 | |:------|:---------| | `patterns` | `Workbench/memory/patterns.md` | | `insights` | `Workbench/memory/insights.md` | | `effective-methods` | `Workbench/memory/effective-methods.md` | | `failed-directions` | `Workbench/memory/failed-directions.md` | | `all` | 以上全部 | ### Step 2：读取记忆文件 用 Read 读取 scope 对应的记忆文件。若文件不存在或为空，返回空结果并告知调用方"该记忆类别暂无条目"。 ### Step 3：语义匹配 逐条扫描记忆文件中的条目（每个 `### [YYYY-MM-DD]` 标题为一条），判断其与 `query` 的语义相关性。判断标准： - 条目的 observation/claim/method 是否与 query 描述的任务/问题直接相关 - 条目中引用的论文/实验是否与 query 涉及的领域重叠 - 条目的 lesson/pitfall 是否对 query 的任务有参考价值 ### Step 4：返回结果 返回 top-k 相关条目（默认 k=5），每条包含： - 条目原文（完整保留，不做概括改写） - 来源文件路径（如 `[[Workbench/memory/patterns.md#条目标题]]`） 若相关条目不足 k 条，返回全部匹配条目，不补凑。 ## Guard - **只读**：不修改任何记忆文件，不修改任何 vault 文件 - **原文保真**：返回结果必须包含条目原文和 `[[wikilink]]` 来源引用，不做概括性改写 - **诚实返回**：若无相关条目，返回空结果，不编造记忆内容 ## Verify …
Read the whole file at its exact version.
How to install
mdr add kendrick-stein/mcislab_deepread/memory-retrieve@sha256:4ea1272037199b72The line at the top of this page pins the label git:20260728.634c4b7, 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_4ow2cercuzmj3hp2)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Apr 28, 2026 and Jul 28, 2026, about one every 91 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260728.634c4b7 latest | 2026-07-28 | 634c4b7 | 2,554 B | A | view · diff |
| git:20260428.bf023ec | 2026-04-28 | bf023ec | 2,363 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 (2554 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_4ow2cercuzmj3hp2 GET https://markdownregistry.com/api/v1/resolve?ref=kendrick-stein/mcislab_deepread/memory-retrieve GET https://markdownregistry.com/api/v1/blob/4ea1272037199b72341e09c74b6c6a5c33dfbc1ead94b3b72a1912081846b149
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.