New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Swarmvault

by swarmclawai in swarmclawai/swarmclaw

A skill your agent uses when working with a SwarmVault knowledge vault (raw/, wiki/, swarmvault.schema.md).

MITAuto-check passedAgent Workflows

Install Swarmvault

skills CLI
$ npx skills add swarmclawai/swarmclaw --skill swarmvault -a claude-code

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

GitHub CLI
$ gh skill install swarmclawai/swarmclaw swarmvault --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/swarmclawai/swarmclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/swarmvault .claude/skills/swarmvault && 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
swarmvault
GitHub stars
689
Token cost
~1.3k tokens
SKILL.md length
650 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when working with a SwarmVault knowledge vault (raw/, wiki/, swarmvault.schema.md).

  • Works in 6 steps: Read swarmvault.schema.md first before… → Read wiki/graph/report.md before broad… → Treat raw/ as immutable. Never edit,… → …
  • Working with a SwarmVault knowledge vault (raw/
  • SKILL.md covers Rules, Tool Palette, Workflow and Boundaries
  • Calls npx

What it does

Swarmvault is an agent skill from swarmclawai/swarmclaw. Use when working with a SwarmVault knowledge vault (raw/, wiki/, swarmvault.schema.md). Establishes schema-first conventions and prefers graph queries over broad search.

Its SKILL.md is about 1.3k 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 Agent Workflows, covering Second brain and Building AI agents. It works with Model Context Protocol. The repository describes itself as: Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude… The licence is MIT.

When your agent uses it

  • Working with a SwarmVault knowledge vault (raw/
  • Swarmvault.schema.md)

Example prompts

  • “/swarmvault”

Requirements

  • Node.js

Workflow steps

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

  1. Read swarmvault.schema.md first before any compile or query work. It defines categories, naming, freshness rules, and grounding…
  2. Read wiki/graph/report.md before broad file searching when it exists; otherwise start with wiki/index.md. Both summarize the vault…
  3. Treat raw/ as immutable. Never edit, rename, or delete files there. New sources go through ingest.
  4. Treat wiki/ as compiler-owned. Edits should preserve frontmatter fields exactly: page_id, source_ids, node_ids, freshness, source_hashes…
  5. Prefer graph queries over grep/glob for "how does X relate to Y" or "what depends on Z" questions. The vault's typed graph is more…
  6. Save high-value answers to wiki/outputs/ (use the query or explore tools) instead of leaving them only in chat. That way they become…

What it can do on your machine

Read from SKILL.md and the folder at commit ed38ba5. 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

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    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

Swarmvault loads about 1.3k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 650 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 swarmclawai/swarmclaw at commit ed38ba5, republished under its MIT licence (© swarmclawai). 650 words, ~1,303 tokens.

Download SKILL.mdSave it as .claude/skills/swarmvault/SKILL.md (or your agent's skills folder).
name
swarmvault
description
Use when working with a SwarmVault knowledge vault (raw/, wiki/, swarmvault.schema.md). Establishes schema-first conventions and prefers graph queries over broad search.
homepage
https://swarmvault.ai

SwarmVault

Use when the agent has a SwarmVault MCP server enabled (transport stdio, command npx -y @swarmvaultai/cli mcp) pointed at a vault directory.

A SwarmVault workspace is a three-layer knowledge system:

  • raw/ — immutable source inputs (PDFs, transcripts, code, emails, URLs, sheets). Never edit.
  • wiki/ — generated markdown owned by the agent and the SwarmVault compiler. Pages carry frontmatter (page_id, source_ids, node_ids, freshness, source_hashes).
  • state/ — generated indexes, graphs, and approvals. Treat as opaque output of compile.

The vault contract lives in swarmvault.schema.md at the workspace root. The vault config lives in swarmvault.config.json.

Rules

  1. Read swarmvault.schema.md first before any compile or query work. It defines categories, naming, freshness rules, and grounding conventions for this specific vault.
  2. Read wiki/graph/report.md before broad file searching when it exists; otherwise start with wiki/index.md. Both summarize the vault structure so you don't re-scan everything.
  3. Treat raw/ as immutable. Never edit, rename, or delete files there. New sources go through ingest.
  4. Treat wiki/ as compiler-owned. Edits should preserve frontmatter fields exactly: page_id, source_ids, node_ids, freshness, source_hashes. If those drift, the next compile will overwrite or flag the page.
  5. Prefer graph queries over grep/glob for "how does X relate to Y" or "what depends on Z" questions. The vault's typed graph is more reliable than text search.
  6. Save high-value answers to wiki/outputs/ (use the query or explore tools) instead of leaving them only in chat. That way they become first-class vault content for next time.

Tool Palette

The SwarmVault MCP server exposes the following tools (names are prefixed by SwarmClaw with mcp_<sanitized server name>_, e.g. mcp_SwarmVault_query_vault). Match the user's intent to the closest tool:

Vault inspection:

  • workspace_info — return current vault paths and high-level counts. Use this first when you've never seen this vault.
  • list_sources — list source manifests under raw/.
  • search_pages — full-text search across compiled wiki pages.
  • read_page — read a specific wiki page by its wiki/-relative path.

Graph (prefer over grep for relational questions):

  • graph_report — machine-readable graph report and trust artifact. Read this before broad searching.
  • query_graph — traverse the graph from search seeds without calling an LLM provider.
  • get_node — explain a graph node, its page, community, neighbors, and group patterns.
  • get_neighbors — neighbors of a node or page target.
  • get_hyperedges — list graph hyperedges, optionally filtered.
  • shortest_path — shortest path between two graph targets.
  • god_nodes — highest-connectivity nodes (the vault's hubs).
  • blast_radius — impact analysis: what depends on this file or module?
Show full SKILL.md (258 more words)Show less

Question answering:

  • query_vault — natural-language question against the vault. Returns grounded citations. Pass save: true to persist the answer to wiki/outputs/.

Ingest and maintenance:

  • ingest_input — add a file path or URL to raw/ and register it as a managed source.
  • compile_vault — re-derive wiki/ pages, graph, and search index. Run after ingest, after schema changes, or when freshness is stale.
  • lint_vault — anti-drift and vault health checks.

If the MCP server is unavailable but the agent has a shell or execute tool, the same operations are available via swarmvault <subcommand> (or npx -y @swarmvaultai/cli <subcommand>) with the working directory set to the vault root.

Workflow

For a fresh question against the vault:

  1. Call workspace_info if you haven't already, then read swarmvault.schema.md. If wiki/graph/report.md or wiki/index.md exists, skim it.
  2. Use query_vault (or query_graph / get_node / shortest_path for relational questions). Cite returned source_ids and node_ids.
  3. If the answer reveals a gap, propose ingest_input for the missing source, then compile_vault.
  4. Save the final answer with query_vault save: true so it becomes vault content under wiki/outputs/.

For a new source the user mentions:

  1. ingest_input the file/URL.
  2. compile_vault to derive new wiki pages, graph, and search index.
  3. lint_vault to check frontmatter and links.
  4. Skim the new pages in wiki/sources/ and confirm provenance.

Boundaries

  • Don't run compile against an unreviewed change to swarmvault.schema.md — lint first.
  • Don't promote candidate pages (wiki/candidates/) to wiki/concepts/ or wiki/entities/ without the user's confirmation; the approval flow exists for a reason.
  • Don't push the vault graph to Neo4j or export to Obsidian without an explicit ask.

© swarmclawai, MIT. 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/swarmvault of swarmclawai/swarmclaw.

Open the folder on GitHubat commit ed38ba5

Compare with similar skills

Swarmvault 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.

Swarmvault compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Swarmvault this skillswarmclawai/swarmclaw689—~1.3kAutomated safety check: PassMIT
Dashclaw Governanceucsandman/DashClaw311—~2.7kAutomated safety check: PassMIT
Magic ResumeMagic-Resume/Magic-Resume101—~663Automated safety check: PassMIT
Register On Dashclawucsandman/DashClaw311—~1.3kAutomated safety check: PassMIT
Neo4j Agent Memory Skillneo4j-contrib/neo4j-skills114—~5.8kAutomated safety check: PassMIT
Agent Squad Python Guide2FastLabs/agent-squad7.8k—~4.7kAutomated safety check: PassApache-2.0

Similar skills

  • Dashclaw Governance

    ucsandman/DashClaw

    Governance behavior for AI agents governed by DashClaw. An agent skill from ucsandman/DashClaw.

    311 GitHub stars~2.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Magic Resume

    Magic-Resume/Magic-Resume

    How AI agents integrate with Magic Resume — read and safely edit a user's resumes through the native MCP server (@magic-resume/mcp).

    101 GitHub stars~663 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Register On Dashclaw

    ucsandman/DashClaw

    Register any agent (including this one) as a governed agent on a DashClaw instance

    311 GitHub stars~1.3k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Neo4j Agent Memory Skill

    neo4j-contrib/neo4j-skills

    Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com.

    114 GitHub stars~5.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Agent Squad Python Guide

    2FastLabs/agent-squad

    Map of the agent-squad Python framework for async multi-agent orchestration: which agent, classifier, storage and tool provider to pick, and the pitfalls to avoid.

    7.8k GitHub stars~4.7k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

  • Agent Squad for TypeScript

    2FastLabs/agent-squad

    Guide to building Node.js and TypeScript apps on the agent-squad package: orchestrator, agent types, classifier routing, storage, retrievers and MCP tools.

    7.8k GitHub stars~4.3k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

More from swarmclawai/swarmclaw

All 12 skills in this repo

  • Openai Image Gen

    swarmclawai/swarmclaw

    Generate images via OpenAI Images API (GPT Image, DALL-E 3, DALL-E 2).

    689 GitHub stars~705 tokensUpdated 3 mo ago
    Auto-check passed

  • Skill Creator

    swarmclawai/swarmclaw

    Create, edit, improve, or audit skills for SwarmClaw agents.

    689 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed

  • Nano Banana Pro

    swarmclawai/swarmclaw

    Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

    689 GitHub stars~481 tokensUpdated 3 mo ago
    Auto-check passed

  • Coding Agent

    swarmclawai/swarmclaw

    Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell.

    689 GitHub stars~900 tokensUpdated 3 mo ago
    Auto-check passed

  • GitHub

    swarmclawai/swarmclaw

    GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries.

    689 GitHub stars~820 tokensUpdated 3 mo ago
    Auto-check passed

  • Swarmclaw

    swarmclawai/swarmclaw

    AI agent runtime and multi-agent orchestration platform. An agent skill from swarmclawai/swarmclaw.

    689 GitHub stars~2k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Categories

Questions about Swarmvault

What does Swarmvault do?

A skill your agent uses when working with a SwarmVault knowledge vault (raw/, wiki/, swarmvault.schema.md). Swarmvault is an agent skill from swarmclawai/swarmclaw.md).

When should I use Swarmvault?

Swarmvault fits situations like: working with a SwarmVault knowledge vault (raw/; swarmvault.schema.md).

How do I install Swarmvault in Claude Code?

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

How do I install Swarmvault in Codex?

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

Can I use Swarmvault 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 swarmclawai/swarmclaw --skill swarmvault -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/swarmvault, .gemini/skills/swarmvault, .github/skills/swarmvault and .opencode/skills/swarmvault in your project.

What does Swarmvault need to run?

Going by SKILL.md and its folder, Swarmvault needs the command-line tools its instructions call (npx). Our summary lists: Node.js.

Does Swarmvault access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Swarmvault 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 Swarmvault use?

Swarmvault 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 Swarmvault use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 Swarmvault?

Skills that share tags, products or a category with Swarmvault: Dashclaw Governance (ucsandman/DashClaw, 311 stars), Magic Resume (Magic-Resume/Magic-Resume, 101 stars), Register On Dashclaw (ucsandman/DashClaw, 311 stars) and Neo4j Agent Memory Skill (neo4j-contrib/neo4j-skills, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Swarmvault?

swarmclawai (a GitHub organization) maintains it in swarmclawai/swarmclaw, which has 689 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on June 30, 2026.

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