agentjido/jido_run/jido-action
- community
Checking that the SKILL.md file is still in the repository.
Builder-oriented guidance for the upstream `jido_action` package. Use when Codex needs to scaffold or review `Jido.Action` modules, validate action inputs and outputs, compose actions into agent workflows, or turn action docs into runnable Elixir examples.
Install
npx vskill@latest install agentjido/jido_run/jido-actionSKILL.md
Jido Action
jido_action is the upstream Hex package name.
Start Here
Use this skill when the task is centered on Jido.Action as the unit of executable work.
Good triggers:
- "Create a new
Jido.Actionfor this side effect." - "Review this action for schema validation or output shape."
- "Turn the action docs into a runnable example."
- "Figure out whether this logic belongs in one action or in agent orchestration."
Read references/builder-notes.md before editing when the task involves action contracts, composition, retries, or error boundaries.
Primary Workflows
Scaffold an action
- Start from the action's boundary: one job, one clear input contract, one clear result shape.
- Define parameters and validation up front instead of burying checks in
run/2. - Keep side effects explicit so callers can reason about retries and compensation.
Extend or refactor an action
- Split oversized actions when they hide orchestration, branching, or unrelated IO.
- Preserve stable inputs and outputs when improving internals.
- Prefer composition through other Jido layers over building a giant action with internal state machines.
Turn docs into runnable examples
- Use realistic params and output values.
- Show how an action is invoked in isolation before showing how an agent or directive uses it.
- Include one error path if the action handles validation or external failures.
Review boundaries
- Keep low-level units of work in
Jido.Action. - Keep routing, branching, and multi-step control flow in
jidoorjido-behaviortree. - Keep signal schemas in
jido-signal.
Build Checklist
- Define the input schema first.
- Decide whether the action is pure, IO-bound, or adapter-like.
- Return consistent success and failure shapes.
- Add focused tests for validation, happy path, and recoverable failure.
Boundaries
- Do not use one action to represent a whole agent workflow.
- Do not hide long-lived state inside the action module.
- Do not mix unrelated side effects just because they happen in one feature.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpriv/skills/arrowcircle-jido-skills/skills/jido-action/SKILL.md
Popularity
- Repository stars
- 44
- Repository forks
- 20
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 17 May 2026, 5 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/agentjido/jido_run/jido-action)