Token导航 LogoToken导航

Agent Skill · 研究检索

karpathy-llm-wiki(karpathy LLM wiki 搜索)

karpathy-llm-wiki 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

karpathy-llm-wiki 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,674 个 Skill 里排第 3,972。

总安装 37,440周安装 1,453GitHub Stars 667下载 12,120核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:karpathy-llm-wiki(karpathy LLM wiki 搜索)
来源仓库:https://github.com/astro-han/karpathy-llm-wiki
仓库路径:skills/karpathy-llm-wiki
安装命令:
npx skills add https://github.com/astro-han/karpathy-llm-wiki --skill karpathy-llm-wiki
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/astro-han/karpathy-llm-wiki --skill karpathy-llm-wiki

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于基于 LLM 构建个人知识库,将原始资料编译为可检索的 wiki 文章并支持持续积累。适用于按主题组织 raw/ 目录下的源材料,并自动生成结构化 wiki 条目供后续问答使用。

使用时维护 raw/ 不可变、wiki/ 可编译的分层结构,体现 Karpathy 提出的 compounding artifact 理念。安装方式为 GitHub,支持 Codex、Claude、Cursor 和 Gemini CLI,需定期更新与交叉验证准确性。

karpathy-llm-wiki 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/karpathy-llm-wiki

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/astro-han/karpathy-llm-wiki --skill karpathy-l…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

karpathy-llm-wiki 怎么安装?

在终端执行 npx skills add https://github.com/astro-han/karpathy-llm-wiki --skill karpathy-llm-wiki。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

karpathy-llm-wiki 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

karpathy-llm-wiki 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

karpathy-llm-wiki 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

karpathy-llm-wiki 用的人多吗?

公开数据是累计安装 37,440 次,近一周安装 1,453 次,下载 12,120 次,GitHub 667 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

karpathy-llm-wiki 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
karpathy-llm-wiki

karpathy LLM wiki 搜索 · 本页

37,440667需要联网未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Karpathy LLM Wiki

Build and maintain a personal knowledge base using LLMs. You manage two directories: raw/ (immutable source material) and wiki/ (compiled knowledge articles). Sources go into raw/, you compile them into wiki articles, and the wiki compounds over time.

Core ideas from Karpathy:

  • "The LLM writes and maintains the wiki; the human reads and asks questions."
  • "The wiki is a persistent, compounding artifact."

Architecture

Three layers, all under the user's project root:

raw/ — Immutable source material. You read, never modify. Organized by topic subdirectories (e.g., raw/machine-learning/).

wiki/ — Compiled knowledge articles. You have full ownership. Organized by topic subdirectories, one level only: wiki/<topic>/<article>.md. Contains two special files:

  • wiki/index.md — Global index. One row per article, grouped by topic, with link + summary + Updated date.
  • wiki/log.md — Append-only operation log.

SKILL.md (this file) — Schema layer. Defines structure and workflow rules.

Templates live in references/ relative to this file. Read them when you need the exact format for raw files, articles, archive pages, or the index.

Initialization

Triggers only on the first Ingest. Check whether raw/ and wiki/ exist. Create only what is missing; never overwrite existing files:

  • raw/ directory (with .gitkeep)
  • wiki/ directory (with .gitkeep)
  • wiki/index.md — heading # Knowledge Base Index, empty body
  • wiki/log.md — heading # Wiki Log, empty body

If Query or Lint cannot find the wiki structure, tell the user: "Run an ingest first to initialize the wiki." Do not auto-create.


Ingest

Fetch a source into raw/, then compile it into wiki/. Always both steps, no exceptions.

Fetch (raw/)

  1. Get the source content using whatever web or file tools your environment provides. If nothing can reach the source, ask the user to paste it directly.
  2. Pick a topic directory. Check existing raw/ subdirectories first; reuse one if the topic is close enough. Create a new subdirectory only for genuinely distinct topics.
  3. Save as raw/<topic>/YYYY-MM-DD-descriptive-slug.md. See references/raw-template.md for the exact format.

- Slug from source title, kebab-case, max 60 characters. - Published date unknown → omit the date prefix from the file name (e.g., descriptive-slug.md). The metadata Published field still appears; set it to Unknown. - If a file with the same name already exists, append a numeric suffix (e.g., descriptive-slug-2.md). - Include metadata header: source URL, collected date, published date. - Preserve original text. Clean formatting noise. Do not rewrite opinions.

Compile (wiki/)

Determine where the new content belongs:

  • Same core thesis as existing article → Merge into that article. Add the new source to Sources/Raw. Update affected sections.
  • New concept → Create a new article in the most relevant topic directory. Name the file after the concept, not the raw file.
  • Spans multiple topics → Place in the most relevant directory. Add See Also cross-references to related articles elsewhere.

These are not mutually exclusive. A single source may warrant merging into one article while also creating a separate article for a distinct concept it introduces. In all cases, check for factual conflicts: if the new source contradicts existing content, annotate the disagreement with source attribution. When merging, note the conflict within the merged article. When the conflicting content lives in separate articles, note it in both and cross-link them.

See references/article-template.md for article format. Key points:

  • Sources field: author, organization, or publication name + date, semicolon-separated.
  • Raw field: markdown links to raw/ files, semicolon-separated.
  • Relative paths from wiki/<topic>/ use ../../raw/<topic>/<file>.md (two levels up to project root).

Cascade Updates

After the primary article, check for ripple effects:

  1. Scan articles in the same topic directory for content affected by the new source.
  2. Scan wiki/index.md entries in other topics for articles covering related concepts.
  3. Update every article whose content is materially affected. Each updated file gets its Updated date refreshed.

Archive pages are never cascade-updated (they are point-in-time snapshots).

Post-Ingest

Update wiki/index.md: add or update entries for every touched article. When adding a new topic section, include a one-line description. The Updated date reflects when the article's knowledge content last changed, not the file system timestamp. See references/index-template.md for format.

Append to wiki/log.md:

## [YYYY-MM-DD] ingest | <primary article title>
- Updated: <cascade-updated article title>
- Updated: <another cascade-updated article title>

Omit - Updated: lines when no cascade updates occur.


Query

Search the wiki and answer questions. Examples of triggers:

  • "What do I know about X?"
  • "Summarize everything related to Y"
  • "Compare A and B based on my wiki"

Steps

  1. Read wiki/index.md to locate relevant articles.
  2. Read those articles and synthesize an answer.
  3. Prefer wiki content over your own training knowledge. Cite sources with markdown links: [Article Title](wiki/topic/article.md) (project-root-relative paths for in-conversation citations; within wiki/ files, use paths relative to the current file).
  4. Output the answer in the conversation. Do not write files unless asked.

Archiving

When the user explicitly asks to archive or save the answer to the wiki:

  1. Write the answer as a new wiki page. See references/archive-template.md. When converting conversation citations to the archive page, rewrite project-root-relative paths (e.g., wiki/topic/article.md) to file-relative paths (e.g., ../topic/article.md or article.md for same-directory).

- Sources: markdown links to the wiki articles cited in the answer. - No Raw field (content does not come from raw/). - File name reflects the query topic, e.g., transformer-architectures-overview.md. - Place in the most relevant topic directory.

  1. Always create a new page. Never merge into existing articles (archive content is a synthesized answer, not raw material).
  2. Update wiki/index.md. Prefix the Summary with [Archived].
  3. Append to wiki/log.md: ## [YYYY-MM-DD] query | Archived: <page title>

Lint

Quality checks on the wiki. Two categories with different authority levels.

Deterministic Checks (auto-fix)

Fix these automatically:

Index consistency — compare wiki/index.md against actual wiki/ files (excluding index.md and log.md):

  • File exists but missing from index → add entry with (no summary) placeholder. For Updated, use the article's metadata Updated date if present; otherwise fall back to file's last modified date.
  • Index entry points to nonexistent file → mark as [MISSING] in the index. Do not delete the entry; let the user decide.

Internal links — for every markdown link in wiki/ article files (body text and Sources metadata), excluding Raw field links (validated by Raw references below) and excluding index.md/log.md (handled above):

  • Target does not exist → search wiki/ for a file with the same name elsewhere.

- Exactly one match → fix the path. - Zero or multiple matches → report to the user.

Raw references — every link in a Raw field must point to an existing raw/ file:

  • Target does not exist → search raw/ for a file with the same name elsewhere.

- Exactly one match → fix the path. - Zero or multiple matches → report to the user.

See Also — within each topic directory:

  • Add obviously missing cross-references between related articles.
  • Remove links to deleted files.

Heuristic Checks (report only)

These rely on your judgment. Report findings without auto-fixing:

  • Factual contradictions across articles
  • Outdated claims superseded by newer sources
  • Missing conflict annotations where sources disagree
  • Orphan pages with no inbound links from other wiki articles
  • Missing cross-topic references
  • Concepts frequently mentioned but lacking a dedicated page
  • Archive pages whose cited source articles have been substantially updated since archival

Post-Lint

Append to wiki/log.md:

## [YYYY-MM-DD] lint | <N> issues found, <M> auto-fixed

Conventions

  • Standard markdown with relative links throughout.
  • wiki/ supports one level of topic subdirectories only. No deeper nesting.
  • Today's date for log entries, Collected dates, and Archived dates. Updated dates reflect when the article's knowledge content last changed. Published dates come from the source (use Unknown when unavailable).
  • Inside wiki/ files, all markdown links use paths relative to the current file. In conversation output, use project-root-relative paths (e.g., wiki/topic/article.md).
  • Ingest updates both wiki/index.md and wiki/log.md. Archive (from Query) updates both. Lint updates wiki/log.md (and wiki/index.md only when auto-fixing index entries). Plain queries do not write any files.

平台分布

Codex

36.56%
按下载量换算4,431

Claude

28.28%
按下载量换算3,428

Cursor

18.83%
按下载量换算2,282

Gemini CLI

8.25%
按下载量换算1,000

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills