Agent skill

Obsidian Vault Ingest Pipeline

by jason-effi-lab in jason-effi-lab/karpathy-llm-wiki-vault

Compiles raw articles, papers and transcripts sitting in an inbox folder into linked Obsidian source, entity and concept pages, then archives the originals.

No licenceAuto-check passedKnowledge Management

SKILL.md written in Chinese; this summary is our English description.

Install Obsidian Vault Ingest Pipeline

skills CLI
$ npx skills add jason-effi-lab/karpathy-llm-wiki-vault --skill ingest -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jason-effi-lab/karpathy-llm-wiki-vault ingest --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jason-effi-lab/karpathy-llm-wiki-vault.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ingest .claude/skills/ingest && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ingest
GitHub stars
721
Token cost
~669 tokens
SKILL.md length
159 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
None found

At a glance

Compiles raw articles, papers and transcripts sitting in an inbox folder into linked Obsidian source, entity and concept pages, then archives the originals.

  • Works in 3 steps: 用户执行 /ingest:扫描 raw/ 所有子目录(排除… → 用户执行 /ingest :仅处理指定文件。 → 隐式触发:用户说"把这个资料摄入知识库"、"导入这篇文章"时,自动执行…
  • Importing a saved article or PDF into a personal knowledge vault
  • SKILL.md covers 核心工作流:Inbox & Archive, 触发逻辑, 编译流水线 and 冲突处理流程, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Treats a `raw/` folder as an inbox of unprocessed markdown articles, papers and PDFs, and a `wiki/` folder as the compiled output, split into source summaries, entities (people, companies, tools, products) and concepts (frameworks, methodologies, theories). Running `/ingest` scans every unarchived file in `raw/`, while `/ingest <path>` processes just one, and the archive folder itself is never read.

For each file, the agent reads it, extracts a one- or two-sentence gist plus its entities and concepts, translates non-Chinese content into Chinese, writes a source summary page, and then creates or incrementally merges an entity or concept page for each item found. A detected conflict between new and existing knowledge pauses the run and asks you to choose between keeping both versions, overwriting, or abandoning that item, before the global index and an append-only log are updated and the source file is finally moved into the archive.

When your agent uses it

  • Importing a saved article or PDF into a personal knowledge vault
  • Processing everything waiting in the raw inbox folder at once
  • Turning a video transcript into linked entity and concept notes
  • Resolving a conflict between new material and an existing vault page

Example prompts

  • “请把这篇文章完整摄入到我的知识库里。”
  • “/ingest raw/02-papers/attention-is-all-you-need.pdf”
  • “Run /ingest and process everything waiting in the inbox.”

Requirements

  • An Obsidian vault with the raw/ and wiki/ folder structure already set up

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. 用户执行 /ingest:扫描 raw/ 所有子目录(排除 09-archive/),找出待处理文件。
  2. 用户执行 /ingest :仅处理指定文件。
  3. 隐式触发:用户说"把这个资料摄入知识库"、"导入这篇文章"时,自动执行 ingest。

What it can do on your machine

Read from SKILL.md and the folder at commit 18f4e71. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Obsidian Vault Ingest Pipeline loads about 669 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 159 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~669

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 159 words (~669 tokens).

“你正在维护一个 LLM Wiki(Obsidian 知识库)。raw/ 目录是"待处理收件箱",wiki/ 是"编译输出层"。”

— opening of SKILL.md by jason-effi-lab
name
ingest
user-invocable
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/ingest of jason-effi-lab/karpathy-llm-wiki-vault.

Open the folder on GitHubat commit 18f4e71

Compare with similar skills

Obsidian Vault Ingest Pipeline next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Obsidian Vault Ingest Pipeline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Obsidian Vault Ingest Pipeline this skilljason-effi-lab/karpathy-llm-wiki-vault721—~669Automated safety check: PassNone
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
LLM Wikipraneybehl/llm-wiki-plugin118—~5.7kAutomated safety check: PassMIT
LLM WikiCharlesHoskinson/sevenlayer116—~1.5kAutomated safety check: PassCustom licence
Wiki CoreIssacW228/student-llm-wiki177—~708Automated safety check: PassMIT
Obsidian Wiki Vault SetupAgriciDaniel/claude-obsidian15k—~1.3kAutomated safety check: PassMIT

Similar skills

  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    praneybehl/llm-wiki-plugin

    Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings.

    118 GitHub stars~5.7k tokensUpdated 27 days ago
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    CharlesHoskinson/sevenlayer

    Builds and maintains a persistent, interlinked Obsidian-compatible markdown knowledge wiki in a git repo via three operations — ingest a source into linked pages, answer a question from the…

    116 GitHub stars~1.5k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Wiki Core

    IssacW228/student-llm-wiki

    Core operating rules for the student knowledge wiki. An agent skill from IssacW228/student-llm-wiki.

    177 GitHub stars~708 tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • Obsidian Wiki Vault Setup

    AgriciDaniel/claude-obsidian

    Sets up or adopts a separate Obsidian knowledge vault through the claude-obsidian core script and routes follow-up work to the right wiki sub-skill.

    15k GitHub stars~1.3k tokensUpdated 29 days ago
    Knowledge ManagementAuto-check passed
  • Wiki Builder

    rohitg00/pro-workflow

    Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.

    2.9k GitHub stars~1k tokensUpdated 11 days ago
    Knowledge ManagementAuto-check passed

More from jason-effi-lab/karpathy-llm-wiki-vault

  • Knowledge Base Health Lint

    jason-effi-lab/karpathy-llm-wiki-vault

    Scans an Obsidian-style wiki for broken double-link references, orphan pages, files missing from the index and unresolved knowledge conflicts, then reports the findings.

    721 GitHub stars~336 tokensUpdated 6 mo ago
    Auto-check passed
  • Wiki Vault Query

    jason-effi-lab/karpathy-llm-wiki-vault

    Answers questions from a local Obsidian-style wiki by reading its index first, then the relevant pages, and replying with wiki-link citations instead of model memory.

    721 GitHub stars~383 tokensUpdated 6 mo ago
    Auto-check passed

Works with

Questions about Obsidian Vault Ingest Pipeline

What does Obsidian Vault Ingest Pipeline do?

Compiles raw articles, papers and transcripts sitting in an inbox folder into linked Obsidian source, entity and concept pages, then archives the originals. Treats a `raw/` folder as an inbox of unprocessed markdown articles, papers and PDFs, and a `wiki/` folder as the compiled output, split into source summaries, entities (people, companies, tools, products) and concepts (frameworks, methodologies, theories). Running `/ingest` scans every unarchived file in `raw/`, while `/ingest <path>` processes just one, and the archive folder itself is never read.

When should I use Obsidian Vault Ingest Pipeline?

Obsidian Vault Ingest Pipeline fits situations like: importing a saved article or PDF into a personal knowledge vault; processing everything waiting in the raw inbox folder at once; turning a video transcript into linked entity and concept notes; resolving a conflict between new material and an existing vault page.

How do I install Obsidian Vault Ingest Pipeline in Claude Code?

Run `npx skills add jason-effi-lab/karpathy-llm-wiki-vault --skill ingest -a claude-code`. Or copy the skill folder (.claude/skills/ingest in jason-effi-lab/karpathy-llm-wiki-vault) into .claude/skills/ingest in your project. Claude Code loads it when a task matches its description.

How do I install Obsidian Vault Ingest Pipeline in Codex?

Run `npx skills add jason-effi-lab/karpathy-llm-wiki-vault --skill ingest -a codex`. Or copy the skill folder (.claude/skills/ingest in jason-effi-lab/karpathy-llm-wiki-vault) into .agents/skills/ingest in your project. Codex loads it when a task matches its description.

Can I use Obsidian Vault Ingest Pipeline in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jason-effi-lab/karpathy-llm-wiki-vault --skill ingest -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ingest, .gemini/skills/ingest, .github/skills/ingest and .opencode/skills/ingest in your project.

What does Obsidian Vault Ingest Pipeline need to run?

SKILL.md names no scripts, command-line tools or credentials: Obsidian Vault Ingest Pipeline is instructions for the agent only. Our summary lists: An Obsidian vault with the raw/ and wiki/ folder structure already set up.

Does Obsidian Vault Ingest Pipeline access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Obsidian Vault Ingest Pipeline safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Obsidian Vault Ingest Pipeline use?

No licence was found for Obsidian Vault Ingest Pipeline or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Obsidian Vault Ingest Pipeline use?

About 669 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Obsidian Vault Ingest Pipeline?

Skills that share tags, products or a category with Obsidian Vault Ingest Pipeline: LLM Wiki (lewislulu/llm-wiki-skill, 655 stars), LLM Wiki (praneybehl/llm-wiki-plugin, 118 stars), LLM Wiki (CharlesHoskinson/sevenlayer, 116 stars) and Wiki Core (IssacW228/student-llm-wiki, 177 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Obsidian Vault Ingest Pipeline?

jason-effi-lab (a GitHub user) maintains it in jason-effi-lab/karpathy-llm-wiki-vault, which has 721 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on April 13, 2026.

Source: jason-effi-lab/karpathy-llm-wiki-vault on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.