Agent skill

Wiki Ingest

by thoreinstein in thoreinstein/gemini-obsidian

A skill your agent uses when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document.

ISCAuto-check passedKnowledge Management

Install Wiki Ingest

skills CLI
$ npx skills add thoreinstein/gemini-obsidian --skill wiki-ingest -a claude-code

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

GitHub CLI
$ gh skill install thoreinstein/gemini-obsidian 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/thoreinstein/gemini-obsidian.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/wiki-ingest .claude/skills/wiki-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
wiki-ingest
GitHub stars
102
Token cost
~1.2k tokens
SKILL.md length
493 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
ISC

At a glance

A skill your agent uses when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document.

  • Works in 9 steps: Identify Sources → Check Manifest → Extract Knowledge → …
  • The user wants to ingest external sources into the vault — PDFs
  • SKILL.md covers Workflow, Arguments and Tips
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Wiki Ingest is an agent skill from thoreinstein/gemini-obsidian. Use when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document. Triggers on "ingest", "process document", "import into vault", "distill this", "add to vault", or "extract knowledge from".

Its SKILL.md is about 1.2k 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. It works with Obsidian. The repository describes itself as: A Gemini CLI extension for interfacing with an Obsidian vault with local first RAG capabilities. The licence is ISC.

When your agent uses it

  • The user wants to ingest external sources into the vault — PDFs
  • Readwise exports
  • Process document
  • Import into vault

Example prompts

  • “ingest”
  • “process document”
  • “import into vault”
  • “/wiki-ingest”

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Identify Sources
  2. Check Manifest
  3. Extract Knowledge
  4. Deduplicate
  5. Present Plan
  6. Write Notes
  7. Placement Rules
  8. Update Manifest
  9. Suggest MOC Updates

What it can do on your machine

Read from SKILL.md and the folder at commit 9156cba. 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 json).

    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

Wiki Ingest loads about 1.2k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 493 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 thoreinstein/gemini-obsidian at commit 9156cba, republished under its ISC licence (© thoreinstein). 493 words, ~1,225 tokens.

Download SKILL.mdSave it as .claude/skills/wiki-ingest/SKILL.md (or your agent's skills folder).
name
wiki-ingest
description
Use when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document. Triggers on "ingest", "process document", "import into vault", "distill this", "add to vault", or "extract knowledge from".

Wiki Ingest

Distill external sources into vault-native notes following VAULT_CONVENTIONS, with provenance tracking and deduplication.

Workflow

1. Identify Sources

Accept one or more source paths from the user. Sources can be:

  • Files on disk (markdown, PDF, text, transcripts)
  • Vault-internal notes (Readwise highlights, working notes to promote)
  • A directory to scan for ingestible files

For vault-internal sources, use obsidian_read_note. For external files, use the Read tool.

2. Check Manifest

Read .manifest.json from the vault root using Read tool.

For each source path, check if it exists in sources:

  • Not present → new source, proceed to extract
  • Present but source modified since ingested_at → re-ingest
  • Present and unchanged → skip (tell user "already ingested, use --force to re-process")
3. Extract Knowledge

Read the source content. Identify:

  • Patterns — reusable approaches, techniques, or practices
  • Traps — pitfalls, anti-patterns, things that went wrong
  • Decisions — architectural or design choices with rationale
  • Concepts — definitions, mental models, frameworks

For each extraction, classify its provenance:

  • Extracted (unmarked) — directly stated in the source
  • Inferred ^[inferred] — synthesized, generalized, or implied but not stated
  • Ambiguous ^[ambiguous] — source is unclear or contradicts other sources
4. Deduplicate

For each extracted concept, search the vault:

  1. Call obsidian_rag_query with the concept name/summary, limit: 5
  2. If a strong match exists, read the existing note with obsidian_read_note
  3. Decide: merge into existing note or create new note

Merge when: the existing note covers the same concept and the new source adds information. Create when: no existing note covers this concept, or the angle is sufficiently different.

5. Present Plan

Before creating or modifying any notes, present the plan to the user:

## Ingest Plan for: <source name>

### New Notes
- Engineering/Patterns/<name>.md — <one-line summary>
- Engineering/Traps/<name>.md — <one-line summary>

### Merge Into Existing
- Engineering/Patterns/<existing>.md — adding: <what's new>

### Skipped
- <concept> — already covered in [[existing-note]]

Wait for user confirmation before proceeding.

Show full SKILL.md (226 more words)Show less
6. Write Notes

For new notes, use obsidian_create_note with content following VAULT_CONVENTIONS templates:

  • Set type: to pattern, trap, or decision
  • Set project: to the source project or "general"
  • Set tags: from content
  • Set created: to today's date
  • Set provenance: fractions based on inline marker counts
  • Include ## Links section with [[wikilinks]] to related vault notes
  • Add ## Sources section citing the ingested source

For merges, use obsidian_insert_at_heading or obsidian_replace_section to add new content to existing notes. Update the provenance: frontmatter if the mix changed, using obsidian_update_frontmatter.

7. Placement Rules
  • Cross-project patterns/traps/decisions → Engineering/Patterns/, Engineering/Traps/, Engineering/Decisions/
  • Project-specific knowledge → working/<project>/knowledge/
  • If unclear, ask the user
8. Update Manifest

After all notes are written, update .manifest.json:

For each processed source, add/update an entry in sources:

json
{
  "<source-path>": {
    "ingested_at": "<ISO8601 now>",
    "size_bytes": <file size>,
    "modified_at": "<source file mtime>",
    "source_type": "document",
    "pages_created": ["Engineering/Patterns/foo.md"],
    "pages_updated": ["Engineering/Traps/bar.md"]
  }
}

Update stats.total_sources_ingested and stats.total_pages. Set last_updated to now.

Write the updated manifest back using the Write tool.

9. Suggest MOC Updates

For each new Engineering/ note created, check which thematic MOCs it belongs in. Suggest additions but don't auto-edit MOCs — use /moc-update for that.

Arguments

  • Source path(s): /wiki-ingest ~/Documents/paper.pdf
  • Optional project scope: /wiki-ingest working/appiary/knowledge/auth-notes.md
  • Optional force flag: /wiki-ingest --force <path> to re-ingest unchanged sources

Tips

  • Run /index first if obsidian_rag_query returns poor results
  • For Readwise books, ingest the book's highlight file (e.g., Readwise/Books/<title>.md)
  • Large sources may yield many extractions — review the plan carefully before confirming
  • Provenance fractions don't need to be exact; approximate to the nearest 0.05

© thoreinstein, ISC. 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/wiki-ingest of thoreinstein/gemini-obsidian.

Open the folder on GitHubat commit 9156cba

Compare with similar skills

Wiki 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.

Wiki Ingest compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wiki Ingest this skillthoreinstein/gemini-obsidian102—~1.2kAutomated safety check: PassISC
Obsidian Knowledge BuilderMichael-OvO/obsidian-knowledge-agent205—~917Automated safety check: PassMIT
Wiki NarrateAr9av/obsidian-wiki3.5k—~1.7kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Codex History IngestAr9av/obsidian-wiki3.5k—~2.2kAutomated safety check: NotesMIT
LLM Wikizosmaai/pi-llm-wiki608—~4.4kAutomated safety check: PassMIT

Similar skills

  • Obsidian Knowledge Builder

    Michael-OvO/obsidian-knowledge-agent

    Turns PDFs, slides, syllabi, papers and transcripts into structured, teaching-quality Obsidian notes, matching how much structure is built to how much the material needs.

    205 GitHub stars~917 tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • Wiki Narrate

    Ar9av/obsidian-wiki

    Turn a wiki topic into a cited Markdown briefing, plain-language explanation, or progressive lecture.

    3.5k GitHub stars~1.7k tokensUpdated yesterday
    Knowledge ManagementAuto-check passed
  • 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
  • Codex History Ingest

    Ar9av/obsidian-wiki

    Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge.

    3.5k GitHub stars~2.2k tokensUpdated yesterday
    Knowledge ManagementAuto-check: notes
  • LLM Wiki

    zosmaai/pi-llm-wiki

    Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern.

    608 GitHub stars~4.4k tokensUpdated 2 days 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 26 days ago
    Knowledge ManagementAuto-check passed

More from thoreinstein/gemini-obsidian

All 12 skills in this repo
  • Cross Linker

    thoreinstein/gemini-obsidian

    A skill your agent uses when the user wants to find and insert missing wikilinks across vault notes.

    102 GitHub stars~878 tokensUpdated 2 mo ago
    Auto-check passed
  • Vault Lint

    thoreinstein/gemini-obsidian

    A skill your agent uses when the user wants a health audit of the vault — stale content, provenance drift, frontmatter compliance, or MOC coverage gaps.

    102 GitHub stars~920 tokensUpdated 2 mo ago
    Auto-check passed
  • Compound

    thoreinstein/gemini-obsidian

    A skill your agent uses when the user wants to promote cross-project knowledge to the global Engineering/ folder, or says "promote knowledge", "compound notes", "knowledge synthesis", or "find…

    102 GitHub stars~454 tokensUpdated 2 mo ago
    Auto-check passed
  • Journal

    thoreinstein/gemini-obsidian

    A skill your agent uses when the user wants to work with their daily note — view today's entry, add a log, do a daily review, or capture quick thoughts.

    102 GitHub stars~283 tokensUpdated 2 mo ago
    Auto-check passed
  • Link Audit

    thoreinstein/gemini-obsidian

    A skill your agent uses when the user wants to audit vault link health, find broken wikilinks, orphaned notes, or semantic clusters.

    102 GitHub stars~408 tokensUpdated 2 mo ago
    Auto-check passed
  • Links

    thoreinstein/gemini-obsidian

    A skill your agent uses when the user wants to explore connections between notes, see what links to or from a note, or says "links", "backlinks", "connections", or "graph".

    102 GitHub stars~232 tokensUpdated 2 mo ago
    Auto-check passed

Works with

Questions about Wiki Ingest

What does Wiki Ingest do?

A skill your agent uses when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document. Wiki Ingest is an agent skill from thoreinstein/gemini-obsidian. Use when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document.

When should I use Wiki Ingest?

Wiki Ingest fits situations like: the user wants to ingest external sources into the vault — PDFs; readwise exports; process document; import into vault.

How do I install Wiki Ingest in Claude Code?

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

How do I install Wiki Ingest in Codex?

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

Can I use Wiki 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 thoreinstein/gemini-obsidian --skill wiki-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/wiki-ingest, .gemini/skills/wiki-ingest, .github/skills/wiki-ingest and .opencode/skills/wiki-ingest in your project.

What does Wiki Ingest need to run?

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

Does Wiki 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 Wiki 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 Wiki Ingest use?

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

How many tokens does Wiki Ingest use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 Wiki Ingest?

Skills that share tags, products or a category with Wiki Ingest: Obsidian Knowledge Builder (Michael-OvO/obsidian-knowledge-agent, 205 stars), Wiki Narrate (Ar9av/obsidian-wiki, 3.5k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars) and Codex History Ingest (Ar9av/obsidian-wiki, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wiki Ingest?

thoreinstein (a GitHub user) maintains it in thoreinstein/gemini-obsidian, which has 102 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on July 31, 2026.

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