How do I install the Llmwiki Ingest skill?

Run npx skillmds@latest add pratiyush/llmwiki-ingest in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Llmwiki Ingest safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Llmwiki Ingest?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Llmwiki Ingest free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Llmwiki Ingest?

pratiyush (@pratiyush) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Llmwiki Ingest by pratiyush — Agent Skill

Name: Llmwiki Ingest
Author: pratiyush

Llmwiki Ingest

Ingest one source document (or a folder of them) into the llmwiki. Use when the user drops a new markdown file, PDF, or URL into the wiki and asks you to process it. The user will typically say "ingest this", "add this to the wiki", "process this file into the wiki", or point at a file under `raw/`.

pratiyush Updated Sep 17, 2026

File contents

llmwiki-ingest

What this skill does

Takes a source file (or a folder) and turns it into wiki pages following the Karpathy LLM Wiki pattern:

Writes a wiki/sources/<slug>.md summary
Creates/updates entity pages for people, companies, projects, tools, libraries mentioned
Creates/updates concept pages for ideas, patterns, decisions discussed
Cross-links everything with [[wikilinks]]
Flags contradictions
Updates wiki/index.md, wiki/overview.md, wiki/log.md

When to use

User says "ingest this file", "add this to the wiki", "process this into the wiki"
User runs the /wiki-ingest slash command
User says "sync the wiki" — in that case, the llmwiki-sync skill runs the converter first, then invokes this skill for each new file

Workflow

Follow the Ingest Workflow from the repo's CLAUDE.md exactly:

Read the source file(s) with the Read tool
Read wiki/index.md and wiki/overview.md for context
Write wiki/sources/<slug>.md using the Source Page Format
Update wiki/index.md — new entry under ## Sources
Update wiki/overview.md if substantial new info
Create/update entity pages (wiki/entities/<TitleCase>.md)
Create/update concept pages (wiki/concepts/<TitleCase>.md)
Cross-link with [[wikilinks]] under ## Connections
Flag contradictions under ## Contradictions
Append to wiki/log.md: ## [YYYY-MM-DD] ingest | <title>

Session-specific rules

When the source is under raw/sessions/ (a session transcript converted by the converter):

Trust the frontmatter as authoritative (project, started, model, tools_used, etc.)
Do not copy the ## Conversation section verbatim — use it as raw material to summarise
Create a project entity page at wiki/entities/<ProjectSlug>.md with a ## Sessions list
Extract decisions into wiki/concepts/ — anything the user explicitly locked
Extract tools used — every entry in tools_used is a candidate entity
If is_subagent: true — link to the parent session rather than creating a new project entity

Hard rules

raw/ is immutable. Never modify files there.
No silent overwrites. Conflicting claims go under ## Contradictions.
Every page has a ## Connections section with at least one [[wikilink]].
Frontmatter is authoritative. Always populate title, type, tags, sources, last_updated.

---name: llmwiki-ingestdescription: Ingest one source document (or a folder of them) into the llmwiki. Use when the user drops a new markdown file, PDF, or URL into the wiki and asks you to process it. The user will typically say "ingest this", "add this to the wiki", "process this file into the wiki", or point at a file under `raw/`.---# llmwiki-ingest## What this skill doesTakes a source file (or a folder) and turns it into wiki pages following the Karpathy LLM Wiki pattern:1. Writes a `wiki/sources/<slug>.md` summary2. Creates/updates entity pages for people, companies, projects, tools, libraries mentioned3. Creates/updates concept pages for ideas, patterns, decisions discussed4. Cross-links everything with `[[wikilinks]]`5. Flags contradictions6. Updates `wiki/index.md`, `wiki/overview.md`, `wiki/log.md`## When to use- User says "ingest this file", "add this to the wiki", "process this into the wiki"- User runs the `/wiki-ingest` slash command- User says "sync the wiki" — in that case, the `llmwiki-sync` skill runs the converter first, then invokes this skill for each new file## WorkflowFollow the **Ingest Workflow** from the repo's `CLAUDE.md` exactly:1. Read the source file(s) with the Read tool2. Read `wiki/index.md` and `wiki/overview.md` for context3. Write `wiki/sources/<slug>.md` using the Source Page Format4. Update `wiki/index.md` — new entry under `## Sources`5. Update `wiki/overview.md` if substantial new info6. Create/update entity pages (`wiki/entities/<TitleCase>.md`)7. Create/update concept pages (`wiki/concepts/<TitleCase>.md`)8. Cross-link with `[[wikilinks]]` under `## Connections`9. Flag contradictions under `## Contradictions`10. Append to `wiki/log.md`: `## [YYYY-MM-DD] ingest | <title>`## Session-specific rulesWhen the source is under `raw/sessions/` (a session transcript converted by the converter):- **Trust the frontmatter** as authoritative (project, started, model, tools_used, etc.)- **Do not copy the `## Conversation` section verbatim** — use it as raw material to summarise- **Create a project entity page** at `wiki/entities/<ProjectSlug>.md` with a `## Sessions` list- **Extract decisions** into `wiki/concepts/` — anything the user explicitly locked- **Extract tools used** — every entry in `tools_used` is a candidate entity- **If `is_subagent: true`** — link to the parent session rather than creating a new project entity## Hard rules1. `raw/` is immutable. Never modify files there.2. No silent overwrites. Conflicting claims go under `## Contradictions`.3. Every page has a `## Connections` section with at least one `[[wikilink]]`.4. Frontmatter is authoritative. Always populate `title`, `type`, `tags`, `sources`, `last_updated`.

Frequently asked questions