Agent skill

Ingest

by jackwener in jackwener/llm-wiki

Ingest source material into an LLM Wiki vault. An agent skill from jackwener/llm-wiki.

Apache-2.0Auto-check passedKnowledge Management

Install Ingest

skills CLI
$ npx skills add jackwener/llm-wiki --skill ingest -a claude-code

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

GitHub CLI
$ gh skill install jackwener/llm-wiki 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/jackwener/llm-wiki.git skills-src && mkdir -p .claude/skills && cp -r skills-src/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
104
Token cost
~689 tokens
SKILL.md length
308 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

Ingest source material into an LLM Wiki vault. An agent skill from jackwener/llm-wiki.

  • Works in 5 steps: Locate the vault by finding… → Read wiki-purpose.md, wiki-schema.md,… → Skip material that the agent policy… → …
  • The user invokes /ingest
  • SKILL.md covers Before editing, Workflow and Quality bar
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ingest is an agent skill from jackwener/llm-wiki. Ingest source material into an LLM Wiki vault. Use whenever the user invokes /ingest, asks to turn documents, notes, chats, or URLs into durable wiki knowledge, or asks to create or update interconnected wiki pages from source material.

Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering LLM wikis. The repository describes itself as: Agent-native persistent knowledge management — compile knowledge once, query forever. The licence is Apache-2.0.

When your agent uses it

  • The user invokes /ingest
  • Asks to turn documents
  • URLs into durable wiki knowledge
  • Update interconnected wiki pages from source material

Example prompts

  • “/ingest”

Workflow steps

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

  1. Locate the vault by finding .llm-wiki/config.toml.
  2. Read wiki-purpose.md, wiki-schema.md, and wiki-agent.md when present.
  3. Skip material that the agent policy excludes, contains credentials or
  4. If the vault is empty, agree with the user on language, page layout,
  5. If the material would change established scope, page boundaries, naming, or

What it can do on your machine

Read from SKILL.md and the folder at commit cd54666. 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 yaml).

    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

Ingest loads about 689 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 308 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~689

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

The full file from jackwener/llm-wiki at commit cd54666, republished under its Apache-2.0 licence (© jackwener). 308 words, ~689 tokens.

Download SKILL.mdSave it as .claude/skills/ingest/SKILL.md (or your agent's skills folder).
name
ingest
description
Ingest source material into an LLM Wiki vault. Use whenever the user invokes `/ingest`, asks to turn documents, notes, chats, or URLs into durable wiki knowledge, or asks to create or update interconnected wiki pages from source material.

Ingest an LLM Wiki source

Turn a source into concise, attributable, interconnected wiki pages. The wiki is the maintained knowledge layer; sources/ is the immutable evidence layer.

Before editing

  1. Locate the vault by finding .llm-wiki/config.toml.
  2. Read wiki-purpose.md, wiki-schema.md, and wiki-agent.md when present. The latter defines vault-specific MUST / MAY / NEVER ingest criteria.
  3. Skip material that the agent policy excludes, contains credentials or personal data, or duplicates existing knowledge.
  4. If the vault is empty, agree with the user on language, page layout, directory structure, and filename conventions before creating pages.
  5. If the material would change established scope, page boundaries, naming, or linking strategy, present the proposed structure before editing. Apply straightforward additions directly.

Workflow

  1. Check wiki/, wiki-log.md, and llm-wiki search for prior ingestion of the source or its topics. Re-ingest only changed or newly useful material.

  2. Copy raw input to sources/YYYY-MM-DD/, preserving its original name. Add a version suffix if needed. Once saved, never edit that copy. Split large chat logs or collections by date or topic before saving.

  3. Extract claims, entities, decisions, open questions, and relationships.

  4. Create or merge focused pages in wiki/. Every page needs the fields required by wiki-schema.md; normally this includes:

    yaml
    ---
    title: Page Title
    description: One-line summary
    aliases: [alternate names]
    tags: [taxonomy tags]
    sources: [YYYY-MM-DD/source.md]
    created: YYYY-MM-DD
    updated: YYYY-MM-DD
    ---

    Bug or issue pages also need machine-readable status: open | resolved | wontfix.

  5. Merge rather than overwrite. When sources conflict, preserve both claims, identify their sources, and flag the conflict rather than silently choosing one.

  6. Add [[wikilinks]] for related entities, including useful not-yet-created pages, and finish each page with a ## Related section.

  7. Append a concise ## [YYYY-MM-DD] ingest | … entry to wiki-log.md with pages created or updated.

  8. Run llm-wiki sync after the changes.

Quality bar

  • Summarize rather than copy source text.
  • Keep every claim traceable through sources frontmatter.
  • Keep each page about one topic; split pages that become multi-topic.
  • Write in the language specified in .llm-wiki/config.toml.

© jackwener, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/ingest of jackwener/llm-wiki.

Open the folder on GitHubat commit cd54666

Compare with similar skills

Ingest 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.

Ingest compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ingest this skilljackwener/llm-wiki104—~689Automated safety check: PassApache-2.0
Karpathy LLM WikiAstro-Han/karpathy-llm-wiki2.4k—~3.6kAutomated safety check: PassMIT
LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything85k1 repos~1.5kAutomated safety check: PassMIT
Hermes History IngestAr9av/obsidian-wiki3.5k1 repos~2.2kAutomated safety check: NotesMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Wiki Builderrohitg00/pro-workflow2.9k—~1kAutomated safety check: PassNone

Similar skills

  • Karpathy LLM Wiki

    Astro-Han/karpathy-llm-wiki

    A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.

    2.4k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed
  • LLM Wiki Knowledge Graph

    Egonex-AI/Understand-Anything

    Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.

    85k GitHub starsUsed in 1 repo~1.5k tokens
    Knowledge ManagementAuto-check passed
  • Hermes History Ingest

    Ar9av/obsidian-wiki

    Ingest Hermes agent history into Obsidian as distilled knowledge.

    3.5k GitHub starsUsed in 1 repo~2.2k tokens
    Knowledge ManagementAuto-check: notes
  • 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
  • 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 8 days ago
    Knowledge ManagementAuto-check passed
  • Wiki Query

    rohitg00/pro-workflow

    Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. An agent skill from rohitg00/pro-workflow.

    2.9k GitHub starsUsed in 1 repo~554 tokens
    Knowledge ManagementAuto-check passed

More from jackwener/llm-wiki

  • Lint

    jackwener/llm-wiki

    Audit and safely maintain an LLM Wiki vault. An agent skill from jackwener/llm-wiki.

    104 GitHub stars~450 tokensUpdated 2 mo ago
    Auto-check passed
  • Query

    jackwener/llm-wiki

    Answer questions from an LLM Wiki vault. An agent skill from jackwener/llm-wiki.

    104 GitHub stars~479 tokensUpdated 2 mo ago
    Auto-check passed
  • Research

    jackwener/llm-wiki

    Research a topic for an LLM Wiki vault. An agent skill from jackwener/llm-wiki.

    104 GitHub stars~516 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Ingest

What does Ingest do?

Ingest source material into an LLM Wiki vault. An agent skill from jackwener/llm-wiki. Ingest is an agent skill from jackwener/llm-wiki. Ingest source material into an LLM Wiki vault.

When should I use Ingest?

Ingest fits situations like: the user invokes /ingest; asks to turn documents; URLs into durable wiki knowledge; update interconnected wiki pages from source material.

How do I install Ingest in Claude Code?

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

How do I install Ingest in Codex?

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

Can I use Ingest 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 jackwener/llm-wiki --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 Ingest need to run?

SKILL.md names no scripts, command-line tools or credentials: Ingest is instructions for the agent only.

Does Ingest 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 Ingest 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 Ingest use?

Ingest is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ingest use?

About 689 tokens (SKILL.md is roughly 2.8k 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 Ingest?

Skills that share tags, products or a category with Ingest: Karpathy LLM Wiki (Astro-Han/karpathy-llm-wiki, 2.4k stars), LLM Wiki Knowledge Graph (Egonex-AI/Understand-Anything, 85k stars), Hermes History Ingest (Ar9av/obsidian-wiki, 3.5k stars) and LLM Wiki (lewislulu/llm-wiki-skill, 655 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ingest?

jackwener (a GitHub user) maintains it in jackwener/llm-wiki, which has 104 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on July 10, 2026.

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