atomic-agents
Use Atomic Agents to build schema-driven agents, integrate tools and MCP connectors, adapt example applications, and maintain the monorepo safely.
Skill by VectorSpaceLab
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vectorspacelab-atomic-agents
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/atomic-agents
What's inside
- Skill name
atomic-agents- Description
- Use Atomic Agents to build schema-driven agents, integrate tools and MCP connectors, adapt example applications, and maintain the monorepo safely.
- License
- MIT
- Metadata
- disco-role: operating
- Instructions
- 35 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (31)
- SKILL.md
- package-summary.md · references/
- repo-provenance.md · references/
- repo-routing-metadata.json · references/
- troubleshooting.md · references/
- check_atomic_agents_env.py · scripts/
- SKILL.md · sub-skills/agent-core/
- api-reference.md · sub-skills/agent-core/references/
- troubleshooting.md · sub-skills/agent-core/references/
- workflows.md · sub-skills/agent-core/references/
- agent_core_smoke.py · sub-skills/agent-core/scripts/
- SKILL.md · sub-skills/example-workflows/
- dependency-matrix.md · sub-skills/example-workflows/references/
- example-index.md · sub-skills/example-workflows/references/
- troubleshooting.md · sub-skills/example-workflows/references/
- workflows.md · sub-skills/example-workflows/references/
- SKILL.md · sub-skills/mcp-integrations/
- api-reference.md · sub-skills/mcp-integrations/references/
- troubleshooting.md · sub-skills/mcp-integrations/references/
- workflows.md · sub-skills/mcp-integrations/references/
- check_mcp_imports.py · sub-skills/mcp-integrations/scripts/
- SKILL.md · sub-skills/repo-development/
- development.md · sub-skills/repo-development/references/
- docs-generation.md · sub-skills/repo-development/references/
- troubleshooting.md · sub-skills/repo-development/references/
- check_repo_layout.py · sub-skills/repo-development/scripts/
- SKILL.md · sub-skills/tooling-and-forge/
- api-reference.md · sub-skills/tooling-and-forge/references/
- cli-reference.md · sub-skills/tooling-and-forge/references/
- forge-catalog.md · sub-skills/tooling-and-forge/references/
- troubleshooting.md · sub-skills/tooling-and-forge/references/
SKILL.md (first lines)
# Atomic Agents Use this skill when a task mentions Atomic Agents, `atomic-agents`, `atomic-assembler`, Atomic Forge, MCP connectors, the example projects, or editing this repository. ## Start here 1. Read `references/package-summary.md` for the monorepo map, package names, and core terminology. 2. Read `references/repo-provenance.md` before deciding whether this skill matches the current checkout or needs refresh. 3. Read `references/troubleshooting.md` for cross-cutting install, import, CLI, and version-mismatch issues. 4. Use the route map below. Each subskill owns deeper references and any helper scripts. ## Install and smoke check - Public use: `pip install atomic-agents` - Checkout work: `uv sync` or `pip install -e .` - Smoke check: `python -c "import atomic_agents, atomic_assembler; print(atomic_agents.__version__)"` - CLI check: `atomic --help` ## Route map | User task | Use subskill | Why | | --- | --- | --- | | Build, run, stream, or debug a typed `AtomicAgent` with schemas, history, prompts, hooks, token counting, or multimodal content | `sub-skills/agent-core/SKILL.md` | Owns the core agent API, memory, context providers, hooks, and the fundamental schema contract. | | Define tools/resources/prompts, reason about Atomic Forge tool families, use the `atomic` CLI, or adapt tool-selection patterns | `sub-skills/tooling-and-forge/SKILL.md` | Owns `BaseTool`, `BaseResource`, `BasePrompt`, Atomic Forge, Atomic Assembler, and tool orchestration surfaces. | | Connect to MCP servers or troubleshoot dynamic MCP-generated tools, resources, and prompts | `sub-skills/mcp-integrations/SKILL.md` | Owns the MCP transport, schema transformation, and generated tool/resource/prompt factory surface. | | Adapt a concrete example project such as quickstart, multimodal, RAG, orchestration, memory, hooks, YouTube, DSPy, FastAPI, progressive disclosure, or `mcp-agent` | `sub-skills/example-workflows/SKILL.md` | Owns the example catalog, dependencies, and recipe-level guidance. | | Modify this checkout, run focused tests, update docs, or reason about release/CI behavior | `sub-skills/repo-development/SKILL.md` | Owns monorepo development commands, packaging conventions, docs checks, and maintainer workflow guidance. | ## Shared references and helpers - `references/repo-routing-metadata.json` records the router metadata consumed during import into the repo-skills router. - `scripts/check_atomic_agents_env.py` performs a safe import/version/CLI smoke check. - Read each subskill's `references/` and `scripts/` for workflow-specific guidance.
From VectorSpaceLab/AREX-Skill, MIT.
More from VectorSpaceLab/AREX-Skill
- 0.563score
data-designer-repo-skill
VectorSpaceLab
Use when you need to design DataDesigner configs, run preview/create/validate workflows, inspect the CLI or agent context, work with plugins or MCP tools, or…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
everos
VectorSpaceLab
Use this skill for EverOS local-first Markdown memory service setup, HTTP memory and knowledge APIs, cascade/OME operations, and observability integration.
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
bentoml
VectorSpaceLab
Use BentoML to author model-serving Services, build and containerize Bentos, run HTTP/gRPC servers and clients, manage models, operate the CLI and BentoCloud…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
dash
VectorSpaceLab
Use when building, debugging, testing, or maintaining Plotly Dash applications, callbacks, server backends, component packages, renderer internals, and Dash…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
diffusers
VectorSpaceLab
Use this skill for Hugging Face Diffusers tasks: pipeline inference, schedulers, adapters/loaders, training recipes, modular pipelines, conversion helpers…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
espnet
VectorSpaceLab
Use when working with ESPnet speech AI toolkit: installation, ESPnet2 recipes and training, pretrained inference/model zoo, ESPnet3 stage workflows, and…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
alphafold3
VectorSpaceLab
Use this skill for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
autogen
VectorSpaceLab
Use this skill for maintaining, migrating, debugging, and safely operating Microsoft AutoGen Python 0.7.x applications, including AgentChat, Core runtimes…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
browser-use
VectorSpaceLab
Use this self-contained Browser Use repo skill for Python agents that automate websites, browser sessions, custom tools, LLM/provider setup, persistent CLI…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
dagster
VectorSpaceLab
Use when working with Dagster OSS: assets, jobs, Definitions, config/resources, schedules/sensors, automation, CLI/local development, deployment operations…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
datasets
VectorSpaceLab
Use this skill when working with Hugging Face Datasets: loading local or Hub datasets, defining Features schemas, processing/streaming datasets, converting…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
geopandas
VectorSpaceLab
Use when working with GeoPandas GeoDataFrame and GeoSeries workflows, vector geospatial I/O, CRS-aware spatial operations, mapping, geocoding, and…
SkillBFreshness: B★ 341Claude Code +9
Signals
- Stars
- 341
- Forks
- 26
- Open issues
- 0
- Last commit (this folder)
- Aug 26, 2026 (2 months ago)
- Last release
- Sep 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/VectorSpaceLab/AREX-Skill
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from VectorSpaceLab
- 0.563score
bentoml
VectorSpaceLab
Use BentoML to author model-serving Services, build and containerize Bentos, run HTTP/gRPC servers and clients, manage models, operate the CLI and BentoCloud…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
dagster
VectorSpaceLab
Use when working with Dagster OSS: assets, jobs, Definitions, config/resources, schedules/sensors, automation, CLI/local development, deployment operations…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
alphafold3
VectorSpaceLab
Use this skill for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
autogen
VectorSpaceLab
Use this skill for maintaining, migrating, debugging, and safely operating Microsoft AutoGen Python 0.7.x applications, including AgentChat, Core runtimes…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
browser-use
VectorSpaceLab
Use this self-contained Browser Use repo skill for Python agents that automate websites, browser sessions, custom tools, LLM/provider setup, persistent CLI…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
dash
VectorSpaceLab
Use when building, debugging, testing, or maintaining Plotly Dash applications, callbacks, server backends, component packages, renderer internals, and Dash…
SkillBFreshness: B★ 341Claude Code +9
Cite this page
atomic-agents skill. Agent Mart. https://agentmart.dev/skills/vectorspacelab-atomic-agents (last updated 2026-10-24)