Agent skill

Mindbase

by frankchu91 in frankchu91/mindbase-llm-wiki

Maintain a persistent AI-tended research wiki. An agent skill from frankchu91/mindbase-llm-wiki.

MITAuto-check passedKnowledge Management

Install Mindbase

skills CLI

$ npx skills add frankchu91/mindbase-llm-wiki --skill mindbase -a claude-code

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

GitHub CLI

$ gh skill install frankchu91/mindbase-llm-wiki mindbase --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/frankchu91/mindbase-llm-wiki.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/plugin/skills/mindbase .claude/skills/mindbase && 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/

Paste into Claude Code

Install the "mindbase" agent skill from https://github.com/frankchu91/mindbase-llm-wiki/tree/main/apps/plugin/skills/mindbase into .claude/skills/mindbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindbase", 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

$skill-installer install https://github.com/frankchu91/mindbase-llm-wiki/tree/main/apps/plugin/skills/mindbase

Type 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.

skills CLI

$ npx skills add frankchu91/mindbase-llm-wiki --skill mindbase -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install frankchu91/mindbase-llm-wiki mindbase --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki.git skills-src && mkdir -p .agents/skills && cp -r skills-src/apps/plugin/skills/mindbase .agents/skills/mindbase && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "mindbase" agent skill from https://github.com/frankchu91/mindbase-llm-wiki/tree/main/apps/plugin/skills/mindbase into .agents/skills/mindbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindbase", 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.

skills CLI

$ npx skills add frankchu91/mindbase-llm-wiki --skill mindbase -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install frankchu91/mindbase-llm-wiki mindbase --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/apps/plugin/skills/mindbase .cursor/skills/mindbase && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "mindbase" agent skill from https://github.com/frankchu91/mindbase-llm-wiki/tree/main/apps/plugin/skills/mindbase into .cursor/skills/mindbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindbase", 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

$ gemini skills install https://github.com/frankchu91/mindbase-llm-wiki.git --path apps/plugin/skills/mindbase

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add frankchu91/mindbase-llm-wiki --skill mindbase -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install frankchu91/mindbase-llm-wiki mindbase --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/apps/plugin/skills/mindbase .gemini/skills/mindbase && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "mindbase" agent skill from https://github.com/frankchu91/mindbase-llm-wiki/tree/main/apps/plugin/skills/mindbase into .gemini/skills/mindbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindbase", 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.

GitHub CLI

$ gh skill install frankchu91/mindbase-llm-wiki mindbase

Installs 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).

skills CLI

$ npx skills add frankchu91/mindbase-llm-wiki --skill mindbase -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki.git skills-src && mkdir -p .github/skills && cp -r skills-src/apps/plugin/skills/mindbase .github/skills/mindbase && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "mindbase" agent skill from https://github.com/frankchu91/mindbase-llm-wiki/tree/main/apps/plugin/skills/mindbase into .github/skills/mindbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindbase", 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.

skills CLI

$ npx skills add frankchu91/mindbase-llm-wiki --skill mindbase -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install frankchu91/mindbase-llm-wiki mindbase --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/frankchu91/mindbase-llm-wiki.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/apps/plugin/skills/mindbase .opencode/skills/mindbase && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "mindbase" agent skill from https://github.com/frankchu91/mindbase-llm-wiki/tree/main/apps/plugin/skills/mindbase into .opencode/skills/mindbase/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mindbase", 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.

Facts

Skill name: mindbase
GitHub stars: 128
Token cost: ~1.1k tokens
SKILL.md length: 357 words
Files: 1
Skills in repo: 1
Repo updated: Sep 14, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Maintain a persistent AI-tended research wiki. An agent skill from frankchu91/mindbase-llm-wiki.

Works in 5 steps: Mission → Per-project layout (memorize this) → The 4 Operations → …
Wants to ingest a source (PDF
SKILL.md covers 1 — Mission, 2 — Per-project layout…, 3 — The 4 Operations and 4 — Anti-patterns, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Mindbase is an agent skill from frankchu91/mindbase-llm-wiki. Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…", "what do I know about X", "lint my wiki", "build context", "rebuild wiki", "summarize what I learned".

Its SKILL.md is about 1.1k 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, Linting and formatting and Second brain. It works with Model Context Protocol and Ollama. The repository describes itself as: Karpathy's LLM Wiki idea as a product — an AI that builds and maintains a markdown wiki from your notes and sources. MCP server + web UI, runs on free local models (Ollama), no… The licence is MIT.

When your agent uses it

Wants to ingest a source (PDF
Capture a thought
Build the wiki context
Query whats already known

Example prompts

“add this to my wiki”
“today I decided…”
“what do I know about X”
“/mindbase”

Workflow steps

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

Mission
Per-project layout (memorize this)
The 4 Operations
Anti-patterns
Audit trail

What it can do on your machine

Read from SKILL.md and the folder at commit 7aa8fcd. 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.
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

Mindbase loads about 1.1k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 357 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~107
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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 frankchu91/mindbase-llm-wiki at commit 7aa8fcd, republished under its MIT licence (© frankchu91). 357 words, ~1,054 tokens.

Download SKILL.mdSave it as .claude/skills/mindbase/SKILL.md (or your agent's skills folder).

name: mindbase
description: Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…", "what do I know about X", "lint my wiki", "build context", "rebuild wiki", "summarize what I learned".

MindBase: Karpathy's LLM-Wiki Pattern (wiki v2 edition)

You operate as the maintainer of the user's per-project research wiki.

1 — Mission

Build and maintain a compounding knowledge base. The user feeds sources (papers, URLs, daily thoughts). You write structured markdown across README.md + context.md + sources/ so the wiki gets richer with every source.

This is NOT RAG — knowledge accumulates, doesn't get re-derived. Your job is the bookkeeping humans abandon: cross-references, summary updates, contradiction flagging, log keeping.

2 — Per-project layout (memorize this)

~/mindbase-data/projects/<project-id>/
├── README.md           Operations manual — how this project works. User-editable.
├── context.md          Curated truth, regenerated by /mb:build. LLM-owned.
├── index.yaml          Auto-generated nav manifest. Never edit manually.
├── soul.md             OPTIONAL — project identity/mission/voice.
├── sources/
│   ├── contributors/<user>/YYYY-MM-DD.md   Append-only daily entries.
│   ├── research/<slug>.md                   /mb:research output.
│   └── raw/<date>/<id>.{md,meta.json,...}  PDFs, web clips.
├── state/<agent>/...                       Agent-managed, opaque to /mb:build.
├── logs/YYYY-MM-DD.md                      Daily audit log.
└── artifacts/                              Generated outputs.

Project location resolution (in order):

Explicit --project <id> in command args
MINDBASE_PROJECT_ID environment variable
~/mindbase-data/config.json → currentProjectId
If none → tell user to run /mb:load or /mb:init

Every operation reads via mindbase MCP tools — never grep the wiki manually.

3 — The 4 Operations

3.1 INGEST/CONTRIBUTE — `/mb:contribute <text-or-path-or-url>`

Input scale calibrates the output:

Short user thought (≲ 200 chars, time-anchored, first-person): 1-3 actions — append to today's contributor file + optional concept link. Routing keywords: daily:, concept:, daily+concept: force route.
Substantive source (URL / PDF / long paste): full extraction, 5-15 actions touching context.md + sources/research/.
Ambiguous middle: decide by content type. Decision/insight → capture scale. Multi-claim narrative → ingest scale.

Always call mindbase_contribute (plan/approve/execute primitive). Never write contributor files directly with Edit/Write.

3.2 BUILD — `/mb:build`

Rebuilds context.md from sources/contributors/ + sources/research/ since the last build. Atomic, transactional, idempotent. Always invoked via the builder sub-agent which has restricted tools — Read + mindbase_* only, no Edit/Write/Bash.

Show full SKILL.md (132 more words)Show less

3.3 QUERY — `/mb:ask <q>`

Hybrid search (bm25 + semantic) over the current project, optionally cross-project. Cites slugs/lines. If the answer compounds, offer /mb:contribute to file it back as a concept.

3.4 LINT — `/mb:lint`

Health check: orphans, contradictions, stale claims, missing cross-references, gaps. Calls mindbase_run_wiki_health. Always invoked via curator sub-agent (read-only).

4 — Anti-patterns

❌ Don't write to context.md directly. Call /mb:build which dispatches the builder.
❌ Don't grep wiki/ files manually — call search_wiki MCP tool which uses the index.
❌ Don't skip the discuss-takeaways turn for substantive sources. Read → discuss → propose plan → execute.
❌ Don't fabricate routing prefixes. If user wrote daily:, respect it; otherwise let the LLM router decide.

5 — Audit trail

Every mindbase_* MCP tool that writes also appends to logs/<today>.md. You don't have to log manually. Format: ## [YYYY-MM-DD HH:MM] {ingest|build|lint|...} | <topic> | created X updated Y.

Files

Just SKILL.md in apps/plugin/skills/mindbase of frankchu91/mindbase-llm-wiki.

Open the folder on GitHubat commit 7aa8fcd

Compare with similar skills

Mindbase 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.

Mindbase compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Mindbase this skillfrankchu91/mindbase-llm-wiki	128	—	~1.1k	Automated safety check: Pass	MIT	24 days ago
Swarmvaultswarmclawai/swarmvault	708	—	~6.1k	Automated safety check: Pass	MIT	3 mo ago
Second Braincoreyhaines31/makerskills	848	—	~2.9k	Automated safety check: Pass	MIT	1 mo ago
Perfupraullenchai/Rapid-MLX	3.9k	—	~1.6k	Automated safety check: Notes	Custom licence	today
Release Sample SweepAtmosphere/atmosphere	3.8k	—	~4.2k	Automated safety check: Pass	Apache-2.0	2 days ago
Integrate Modeltryonlabs/opentryon	551	—	~1.1k	Automated safety check: Pass	Custom licence	2 days ago

Similar skills

Swarmvault
swarmclawai/swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval…
708 GitHub stars~6.1k tokensUpdated 3 mo ago
Knowledge ManagementAuto-check passed
Second Brain
coreyhaines31/makerskills
When you want to capture into, compile, query, lint, or connect your personal Second Brain.
848 GitHub stars~2.9k tokensUpdated 1 mo ago
Knowledge ManagementAuto-check passed
Perfup
raullenchai/Rapid-MLX
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR
3.9k GitHub stars~1.6k tokensUpdated today
AI & LLM EngineeringAuto-check: notes
Release Sample Sweep
Atmosphere/atmosphere
Run the pre-release end-to-end sweep of every user-facing surface — the 33 samples under samples/ (booted from their packaged artifacts and driven in a real browser via chrome-devtools MCP), the…
3.8k GitHub stars~4.2k tokensUpdated 2 days ago
MobileAuto-check passed
Integrate Model
tryonlabs/opentryon
Integrates a hosted API or local/open-weight model end-to-end across OpenTryOn (adapter, CLI registry, MCP, docs) and TryOn Studio (catalog, Connect keys, planner).
551 GitHub stars~1.1k tokensUpdated 2 days ago
AI & LLM EngineeringAuto-check passed
Agent Framework
jihadkhawaja/Egroo
Build, extend, and debug AI agents in Egroo using the Microsoft Agent Framework (C .NET).
178 GitHub stars~1.9k tokensUpdated 6 mo ago
AI & LLM EngineeringAuto-check passed

Works with

Questions about Mindbase

What does Mindbase do?

Maintain a persistent AI-tended research wiki. An agent skill from frankchu91/mindbase-llm-wiki. Mindbase is an agent skill from frankchu91/mindbase-llm-wiki. Maintain a persistent AI-tended research wiki.

When should I use Mindbase?

Mindbase fits situations like: wants to ingest a source (PDF; capture a thought; build the wiki context; query whats already known.

How do I install Mindbase in Claude Code?

Run `npx skills add frankchu91/mindbase-llm-wiki --skill mindbase -a claude-code`. Or copy the skill folder (apps/plugin/skills/mindbase in frankchu91/mindbase-llm-wiki) into .claude/skills/mindbase in your project. Claude Code loads it when a task matches its description.

How do I install Mindbase in Codex?

Run `npx skills add frankchu91/mindbase-llm-wiki --skill mindbase -a codex`. Or copy the skill folder (apps/plugin/skills/mindbase in frankchu91/mindbase-llm-wiki) into .agents/skills/mindbase in your project. Codex loads it when a task matches its description.

Can I use Mindbase 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 frankchu91/mindbase-llm-wiki --skill mindbase -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mindbase, .gemini/skills/mindbase, .github/skills/mindbase and .opencode/skills/mindbase in your project.

What does Mindbase need to run?

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

Does Mindbase 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 Mindbase 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 Mindbase use?

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

How many tokens does Mindbase use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Mindbase?

Skills that share tags, products or a category with Mindbase: Swarmvault (swarmclawai/swarmvault, 708 stars), Second Brain (coreyhaines31/makerskills, 848 stars), Perfup (raullenchai/Rapid-MLX, 3.9k stars) and Release Sample Sweep (Atmosphere/atmosphere, 3.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mindbase?

frankchu91 (a GitHub user) maintains it in frankchu91/mindbase-llm-wiki, which has 128 GitHub stars. The repository was last updated on September 14, 2026.

Source: frankchu91/mindbase-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.

Install Mindbase

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

MindBase: Karpathy's LLM-Wiki Pattern (wiki v2 edition)

1 — Mission

2 — Per-project layout (memorize this)

3 — The 4 Operations

3.1 INGEST/CONTRIBUTE — /mb:contribute <text-or-path-or-url>

3.2 BUILD — /mb:build

3.3 QUERY — /mb:ask <q>

3.4 LINT — /mb:lint

4 — Anti-patterns

5 — Audit trail

Files

Compare with similar skills

Similar skills

Swarmvault

Second Brain

Perfup

Release Sample Sweep

Integrate Model

Agent Framework

Related

Questions about Mindbase

3.1 INGEST/CONTRIBUTE — `/mb:contribute <text-or-path-or-url>`

3.2 BUILD — `/mb:build`

3.3 QUERY — `/mb:ask <q>`

3.4 LINT — `/mb:lint`