/release
Release a new version of atomic-agents to PyPI and GitHub. Use when the user asks to "release", "publish", "deploy", or "bump version" for atomic-agents.
$ npx -y skills add Eigenwise/atomic-agents --skill release --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/release
Context preview
The summary Claude sees to decide when to auto-load this skill.
Release a new version of atomic-agents to PyPI and GitHub. Use when the user asks to "release", "publish", "deploy", or "bump version" for atomic-agents.
SKILL.md
release.SKILL.mdname: release
description: Release a new version of atomic-agents to PyPI and GitHub. Use when the user asks to "release", "publish", "deploy", or "bump version" for atomic-agents.
allowed-tools: Read, Bash, Grep, Glob
metadata:
internal: true
Release Process for atomic-agents
Overview
This skill guides the release process for atomic-agents, including version bumping, PyPI publishing, and GitHub release creation.
Prerequisites
- Must be on `main` branch with clean working directory
- `.env` file must contain `PYPI_TOKEN` environment variable
- Must have push access to the repository
Release Types
| Type | When to Use | Example | |------|-------------|---------| | `major` | Breaking changes | 2.5.0 → 3.0.0 | | `minor` | New features (backwards compatible) | 2.5.0 → 2.6.0 | | `patch` | Bug fixes only | 2.5.0 → 2.5.1 |
Step-by-Step Process
1. Prepare the Branch
git checkout main
git pull
git status # Ensure clean working directory
2. Run Build and Deploy Script
**Important**: The script bumps versions, so if it fails partway through, reset to main before retrying.
powershell -ExecutionPolicy Bypass -File build_and_deploy.ps1 <major|minor|patch>
This script will:
- Read current version from `pyproject.toml`
- Increment version based on release type
- Update `pyproject.toml` with new version
- Run `uv sync` to update dependencies
- Run `uv build` to create distribution packages
- Run `uv publish` to upload to PyPI
3. If Script Fails - Reset and Retry
git checkout main
git reset --hard origin/main
# Fix the issue, then run script again
4. Commit and Push Version Bump
git add pyproject.toml uv.lock
git commit -m "Release vX.Y.Z"
git push
5. Create GitHub Release
gh release create vX.Y.Z --title "vX.Y.Z" --notes "RELEASE_NOTES_HERE"
Release Notes Template
## What's New
### Feature Name
Brief description of the feature.
#### Features
- Feature 1
- Feature 2
#### Improvements
- Improvement 1
#### Bug Fixes
- Fix 1
### Full Changelog
https://github.com/eigenwise/atomic-agents/compare/vOLD...vNEW
Checklist
- [ ] On main branch with clean working directory
- [ ] `.env` file has `PYPI_TOKEN`
- [ ] Determined correct release type (major/minor/patch)
- [ ] Build and deploy script completed successfully
- [ ] Version bump committed and pushed
- [ ] GitHub release created with release notes
Read more
name: release description: Release a new version of atomic-agents to PyPI and GitHub. Use when the user asks to "release", "publish", "deploy", or "bump version" for atomic-agents. allowed-tools: Read, Bash, Grep, Glob metadata: internal: true
Release Process for atomic-agents
Overview
This skill guides the release process for atomic-agents, including version bumping, PyPI publishing, and GitHub release creation.
Prerequisites
- Must be on `main` branch with clean working directory
- `.env` file must contain `PYPI_TOKEN` environment variable
- Must have push access to the repository
Release Types
| Type | When to Use | Example | |------|-------------|---------| | `major` | Breaking changes | 2.5.0 → 3.0.0 | | `minor` | New features (backwards compatible) | 2.5.0 → 2.6.0 | | `patch` | Bug fixes only | 2.5.0 → 2.5.1 |
Step-by-Step Process
1. Prepare the Branch
git checkout main git pull git status # Ensure clean working directory
2. Run Build and Deploy Script
**Important**: The script bumps versions, so if it fails partway through, reset to main before retrying.
powershell -ExecutionPolicy Bypass -File build_and_deploy.ps1 <major|minor|patch>
This script will:
- Read current version from `pyproject.toml`
- Increment version based on release type
- Update `pyproject.toml` with new version
- Run `uv sync` to update dependencies
- Run `uv build` to create distribution packages
- Run `uv publish` to upload to PyPI
3. If Script Fails - Reset and Retry
git checkout main git reset --hard origin/main # Fix the issue, then run script again
4. Commit and Push Version Bump
git add pyproject.toml uv.lock git commit -m "Release vX.Y.Z" git push
5. Create GitHub Release
gh release create vX.Y.Z --title "vX.Y.Z" --notes "RELEASE_NOTES_HERE"
Release Notes Template
## What's New ### Feature Name Brief description of the feature. #### Features - Feature 1 - Feature 2 #### Improvements - Improvement 1 #### Bug Fixes - Fix 1 ### Full Changelog https://github.com/eigenwise/atomic-agents/compare/vOLD...vNEW
Checklist
- [ ] On main branch with clean working directory
- [ ] `.env` file has `PYPI_TOKEN`
- [ ] Determined correct release type (major/minor/patch)
- [ ] Build and deploy script completed successfully
- [ ] Version bump committed and pushed
- [ ] GitHub release created with release notes
Other skills on atomic-agents.
- /create-atomic-agent
Build and wire an `AtomicAgent[InSchema, OutSchema]` — schemas, `AgentConfig`, `SystemPromptGenerator`, provider client, history, hooks, optional context providers. Use when the user asks to "create an agent", "add another agent", "build an `AtomicAgent`", "wire up an agent",
Open skill - /create-atomic-context-provider
Build a `BaseDynamicContextProvider` that injects a named, titled block into an agent's system prompt at every `run()` — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to "add a context provider", "inject X into the
Open skill - /create-atomic-schema
Design and write a `BaseIOSchema` input/output pair for an Atomic Agents agent or tool — docstrings, field descriptions, validators, error variants. Use when the user asks to "create a schema", "design the input/output schema", "define an `IOSchema`", "write a `BaseIOSchema`",
Open skill - /create-atomic-tool
Build a `BaseTool[InSchema, OutSchema]` subclass — input/output schemas, `BaseToolConfig`, `run()` (and optional `run_async()`), env-driven secrets, typed failure outputs. Use when the user asks to "add a tool", "create a tool", "wrap an API as a tool", "build a `BaseTool`",
Open skill - /framework
Guide for the Atomic Agents Python framework — schemas, agents, tools, context providers, prompts, orchestration, and provider configuration. Use when code imports from `atomic_agents`, defines an `AtomicAgent`, `BaseTool`, or `BaseIOSchema`, or the user asks about multi-agent
Open skill - /new-app
Scaffold a new Atomic Agents project from scratch — create the directory, `pyproject.toml`, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says "scaffold" / "new project" / "start from zero", or runs
Open skill

