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…
Produce a day/week/month knowledge digest summarizing what was learned, updated, and connected in the wiki.
$ npx skills add Ar9av/obsidian-wiki --skill wiki-digest -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Ar9av/obsidian-wiki wiki-digest --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Ar9av/obsidian-wiki.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.skills/wiki-digest .claude/skills/wiki-digest && rm -rf skills-srcUse ~/.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/
Install the "wiki-digest" agent skill from https://github.com/Ar9av/obsidian-wiki/tree/main/.skills/wiki-digest into .claude/skills/wiki-digest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-digest", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Ar9av/obsidian-wiki/tree/main/.skills/wiki-digestType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Ar9av/obsidian-wiki --skill wiki-digest -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Ar9av/obsidian-wiki wiki-digest --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ar9av/obsidian-wiki.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.skills/wiki-digest .agents/skills/wiki-digest && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "wiki-digest" agent skill from https://github.com/Ar9av/obsidian-wiki/tree/main/.skills/wiki-digest into .agents/skills/wiki-digest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-digest", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Ar9av/obsidian-wiki --skill wiki-digest -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Ar9av/obsidian-wiki wiki-digest --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ar9av/obsidian-wiki.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.skills/wiki-digest .cursor/skills/wiki-digest && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "wiki-digest" agent skill from https://github.com/Ar9av/obsidian-wiki/tree/main/.skills/wiki-digest into .cursor/skills/wiki-digest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-digest", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Ar9av/obsidian-wiki.git --path .skills/wiki-digest--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Ar9av/obsidian-wiki --skill wiki-digest -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Ar9av/obsidian-wiki wiki-digest --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ar9av/obsidian-wiki.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.skills/wiki-digest .gemini/skills/wiki-digest && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "wiki-digest" agent skill from https://github.com/Ar9av/obsidian-wiki/tree/main/.skills/wiki-digest into .gemini/skills/wiki-digest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-digest", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Ar9av/obsidian-wiki wiki-digestInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Ar9av/obsidian-wiki --skill wiki-digest -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Ar9av/obsidian-wiki.git skills-src && mkdir -p .github/skills && cp -r skills-src/.skills/wiki-digest .github/skills/wiki-digest && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "wiki-digest" agent skill from https://github.com/Ar9av/obsidian-wiki/tree/main/.skills/wiki-digest into .github/skills/wiki-digest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-digest", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Ar9av/obsidian-wiki --skill wiki-digest -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Ar9av/obsidian-wiki wiki-digest --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Ar9av/obsidian-wiki.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.skills/wiki-digest .opencode/skills/wiki-digest && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "wiki-digest" agent skill from https://github.com/Ar9av/obsidian-wiki/tree/main/.skills/wiki-digest into .opencode/skills/wiki-digest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-digest", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
wiki-digestProduce a day/week/month knowledge digest summarizing what was learned, updated, and connected in the wiki.
Wiki Digest is an agent skill from Ar9av/obsidian-wiki. Produce a day/week/month knowledge digest summarizing what was learned, updated, and connected in the wiki. Use for readable recent-learning summaries; wiki-status reports source and ingestion state instead.
Its SKILL.md is about 2.8k 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: Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents. The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4a0630b. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash, markdown and yaml).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Wiki Digest loads about 2.8k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 1,195 words of instructions outside code blocks.
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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
line `@name` override → walk up CWD for `.env` → global config → prompt setup). This gives `OBSIDIAN_VAULT_PATH` and `OBAutomated 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.
The full file from Ar9av/obsidian-wiki at commit 4a0630b, republished under its MIT licence (© Ar9av). 1,195 words, ~2,845 tokens.
.claude/skills/wiki-digest/SKILL.md (or your agent's skills folder).You are generating a human-readable digest of recent wiki activity: what was learned, what was updated, what themes are emerging, and what's worth reviewing. This skill summarizes knowledge, not sources — think of it as a weekly review session, not an ingestion status report.
Writing profile: Before drafting or rewriting natural-language Markdown, read and apply the Writing Profile Resolution section in llm-wiki/SKILL.md. Framework schema, provenance, safety, and operation-specific requirements take precedence.
WRITING.md preferences apply only to newly drafted or rewritten natural-language Markdown; preserve source content and structured records.
llm-wiki/SKILL.md (inline @name override → walk up CWD for .env → global config → prompt setup). This gives OBSIDIAN_VAULT_PATH and OBSIDIAN_LINK_FORMAT.$OBSIDIAN_VAULT_PATH/log.md — last 200 lines — for entries within the period (timestamps are ISO-8601 prefixed lines).$OBSIDIAN_VAULT_PATH/hot.md for current session context.$OBSIDIAN_VAULT_PATH/_insights.md exists, read its Anchor Pages table — you'll use it later to identify which new pages became hubs.Glob all .md files under $OBSIDIAN_VAULT_PATH. Skip special/system files:
index.md, log.md, hot.md, AGENTS.md, _insights.md_meta/, _archives/, _raw/journal/digest-*.md)For each remaining page, read its frontmatter:
created — when the page was first writtenupdated — when it was last modifiedClassify:
created is within the periodupdated is within the period but created is before itIf fewer than 5 pages were active, note it and offer to widen: "Only 3 pages were active in the last 7 days — want a monthly digest instead?" Stop here unless the user says to continue.
For each active page, collect: title, category, tags, summary (frontmatter field), lifecycle, any ^[ambiguous] or ^[inferred] markers in the body.
From all active pages' tags, tally theme frequency:
For each tag across new + updated pages:
count how many active pages carry it
Sort descending, take top 5Also read $OBSIDIAN_VAULT_PATH/_meta/taxonomy.md (if it exists). Flag any tag from step 1 that does not appear in the taxonomy — these are new vocabulary words that emerged this period.
Note which categories grew most (concepts/, entities/, skills/, synthesis/, references/, etc.).
Scan new and updated pages for cross-category wikilinks — links that bridge different knowledge layers. These are the most intellectually interesting outputs of the period.
For each active page, extract all [[wikilink]] targets. Classify each link by the target's category prefix. Flag links that cross categories (e.g., a concepts/ page linking to an entities/ page, or a synthesis/ page bridging two topics).
Rank candidates by interestingness:
_insights.md bridge data if available)_insights.md anchors)synthesis/ page (deliberate cross-cutting)^[inferred] (synthesized connection, not directly stated)Take the top 3–5 connections. Write each as a plain-English sentence: not just "A → B" but why the connection is interesting.
Scan active pages and _raw/ for unresolved work:
lifecycle: draft or lifecycle: stub^[ambiguous] markers across all active pages (don't list every one — just the count and which pages have the most)$OBSIDIAN_VAULT_PATH/_raw/ (anything here hasn't been promoted)_meta/taxonomy.mdFrom the existing (pre-period) pages, identify 2–3 worth revisiting given this week's new context.
Heuristic: find pre-period pages that share the most tags with the active pages from Step 1. These are foundational pages whose topic was extended this period — the new pages build on them but the user may not have revisited the foundation.
Also include any pre-period page that now has 2+ new incoming links from active pages (it just became more connected — a sign it's load-bearing).
Write each recommendation with a concrete reason: "[[concepts/attention-mechanism]] — your foundational page; three new papers ingested this week all extend it", not just the page title.
Produce a structured, scannable markdown report. The Headlines section is the most important — it should feel like the opening of a good newsletter, synthesizing actual insight rather than listing page names.
Apply the link format from llm-wiki/SKILL.md (Link Format section) using OBSIDIAN_LINK_FORMAT. Default is [[wikilink]].
# Wiki Digest — [Period Label]
> [N new pages · M updated pages · period: YYYY-MM-DD to YYYY-MM-DD]
## Headlines
- [Concrete insight #1 — synthesize the actual knowledge, not just "learned about X"]
- [Concrete insight #2]
- [Concrete insight #3]
## New Knowledge
### New pages ([count])
| Page | Category | Summary |
|---|---|---|
| [[concepts/foo]] | concept | One-sentence summary from frontmatter |
| [[entities/bar]] | entity | One-sentence summary |
### Notable updates ([count])
| Page | What changed |
|---|---|
| [[skills/react-hooks]] | Added patterns for useCallback with async effects |
*(If no updates, omit this subsection.)*
## Emerging Themes
- **#[tag]** ([N pages]) — [One sentence on why this topic was active]
- **#[tag]** ([N pages]) — [...]
- **#[NEW TAG]** ([N pages]) ⭐ *New vocabulary — not yet in taxonomy*
Most active category: **[category/]** ([N pages added or updated])
## Key Connections Made
- [[concepts/A]] → [[entities/B]] — [Plain-English reason this connection is interesting]
- [[synthesis/X]] created — bridges [[concepts/Y]] and [[concepts/Z]] for the first time
- *(up to 5 connections)*
## Open Threads
- **Drafts to compile** ([count]): [[concepts/foo]], [[concepts/bar]] — still in draft lifecycle
- **Ambiguous claims**: [N] `^[ambiguous]` markers across [M] pages — run `/wiki-synthesize` to resolve
- **Unstaged notes**: [N] files in `_raw/` — run `/wiki-ingest _raw/` to promote them
- **Taxonomy gaps**: Tags `#newtag1`, `#newtag2` used but not in taxonomy — run `/tag-taxonomy`
*(Omit any subsection where count is 0.)*
## Recommended Re-reads
- [[concepts/X]] — [Specific reason: "3 new papers this week all extend this concept"]
- [[synthesis/Y]] — [Specific reason: "2 new pages created this week reference it"]
- [[skills/Z]] — [Specific reason: "now has 4 new incoming links — it's become a hub"]
---
*Generated by wiki-digest · [TIMESTAMP] · [N pages scanned in [VAULT_PATH]]*Visibility: If a page is tagged visibility/pii, exclude it from all tables and connection lists (but count it in the totals, noted as "+ N private"). If the user explicitly says "include private pages" or "full digest", include them normally.
Default (chat output): Print the digest directly. At the end, ask:
"Want me to save this as journal/digest-YYYY-MM-DD.md?"
If user prefixed with "save" or "write" (e.g., /wiki-digest save or "generate and save my weekly digest"):
$OBSIDIAN_VAULT_PATH/journal/digest-YYYY-MM-DD.md (weekly/monthly) or journal/digest-YYYY-MM-DD-daily.md (daily)---
title: "Wiki Digest — [Period Label]"
category: journal
tags: [digest, meta/review]
sources: []
created: TIMESTAMP
updated: TIMESTAMP
summary: "Weekly knowledge digest: [N new, M updated pages]. Top themes: [tag1], [tag2]."
---index.md with the new entry under Journal.manifest.json (digests aren't source ingestions)Either way, append to log.md:
- [TIMESTAMP] DIGEST period="7d" new_pages=N updated_pages=M themes=T connections=C saved=false| Situation | Handling |
|---|---|
| Fewer than 5 active pages | Offer to widen the period; proceed only if user confirms |
| Empty vault (no pages at all) | Tell the user to run an ingest first; stop |
No _meta/taxonomy.md | Skip taxonomy gap check; omit that line from Open Threads |
No _insights.md | Skip hub-based scoring in Step 3; still produce connections section |
All pages are visibility/pii | Report "N private pages active this period" with no details; offer full mode |
| Period spans a wiki rebuild | Note it in the digest: "Wiki was rebuilt during this period — page dates reflect post-rebuild state" |
log.md append. It does not modify existing wiki pages.wiki-status. This skill answers "what did I learn", not "what's pending".QMD is a search index, not the source of truth. If $QMD_WIKI_COLLECTION is empty or unset, skip this step. Run it only after this skill has written or rewritten vault markdown. If QMD refresh fails, do not roll back the vault changes; report the QMD status separately.
Use $QMD_CLI if set; otherwise use qmd.
${QMD_CLI:-qmd} updateIf the output says vectors are needed or embeddings may be stale, run:
${QMD_CLI:-qmd} embedVerify the collection with either:
${QMD_CLI:-qmd} ls "$QMD_WIKI_COLLECTION"or, when a specific page path is known:
${QMD_CLI:-qmd} get "qmd://$QMD_WIKI_COLLECTION/<page>.md" -l 5Record one of:
QMD refreshed: update + embed + verifiedQMD refreshed: update only + verifiedQMD skipped: QMD_WIKI_COLLECTION unsetQMD skipped: qmd CLI unavailableQMD failed: <short error summary>© Ar9av, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .skills/wiki-digest of Ar9av/obsidian-wiki.
Open the folder on GitHubat commit 4a0630b
Wiki Digest 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Wiki Digest this skillAr9av/obsidian-wiki | 3.5k | — | ~2.8k | Automated safety check: Notes | MIT | |
| LLM Wikilewislulu/llm-wiki-skill | 655 | — | ~3.7k | Automated safety check: Pass | None | |
| LLM Wikizosmaai/pi-llm-wiki | 608 | — | ~4.4k | Automated safety check: Pass | MIT | |
| LLM Wikipraneybehl/llm-wiki-plugin | 118 | — | ~5.7k | Automated safety check: Pass | MIT | |
| Karpathy WikiSherwinQ/karpathy-wiki | 114 | — | ~967 | Automated safety check: Pass | MIT | |
| My LLM WikiMartinLwx/dotfiles | 140 | — | ~2.7k | Automated safety check: Pass | None |
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…
zosmaai/pi-llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern.
praneybehl/llm-wiki-plugin
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings.
SherwinQ/karpathy-wiki
A skill your agent uses when building or maintaining a personal knowledge base with LLM assistance.
MartinLwx/dotfiles
Provides access to the user's personal wiki, including notes, research, project documentation, decisions, and archived knowledge.
xoai/sage-wiki
Reference skill for sage-wiki — local-first knowledge graph with MCP server, REST API, compiled wiki, and Obsidian-compatible output.
Ar9av/obsidian-wiki
Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge.
Ar9av/obsidian-wiki
Ingest GitHub Copilot CLI/session history into Obsidian as distilled knowledge.
Ar9av/obsidian-wiki
Ingest Hermes agent history into Obsidian as distilled knowledge.
Ar9av/obsidian-wiki
Adjust the user's Obsidian visual layout with CSS snippets. An agent skill from Ar9av/obsidian-wiki.
Ar9av/obsidian-wiki
Ingest OpenClaw session/history data into Obsidian as distilled knowledge.
Ar9av/obsidian-wiki
Turn the current conversation or finding into a structured permanent wiki note.
Works with
Categories
Produce a day/week/month knowledge digest summarizing what was learned, updated, and connected in the wiki. Wiki Digest is an agent skill from Ar9av/obsidian-wiki. Produce a day/week/month knowledge digest summarizing what was learned, updated, and connected in the wiki.
Wiki Digest fits situations like: readable recent-learning summaries; wiki-status reports source and ingestion state instead.
Run `npx skills add Ar9av/obsidian-wiki --skill wiki-digest -a claude-code`. Or copy the skill folder (.skills/wiki-digest in Ar9av/obsidian-wiki) into .claude/skills/wiki-digest in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Ar9av/obsidian-wiki --skill wiki-digest -a codex`. Or copy the skill folder (.skills/wiki-digest in Ar9av/obsidian-wiki) into .agents/skills/wiki-digest in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ar9av/obsidian-wiki --skill wiki-digest -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-digest, .gemini/skills/wiki-digest, .github/skills/wiki-digest and .opencode/skills/wiki-digest in your project.
SKILL.md names no scripts, command-line tools or credentials: Wiki Digest is instructions for the agent only.
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.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Wiki Digest is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Wiki Digest: LLM Wiki (lewislulu/llm-wiki-skill, 655 stars), LLM Wiki (zosmaai/pi-llm-wiki, 608 stars), LLM Wiki (praneybehl/llm-wiki-plugin, 118 stars) and Karpathy Wiki (SherwinQ/karpathy-wiki, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Ar9av (a GitHub user) maintains it in Ar9av/obsidian-wiki, which has 3,538 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 8, 2026.
Source: Ar9av/obsidian-wiki on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.