agentjido

Builder-oriented guidance for the upstream `ash_jido` package. Use when Codex needs to expose Ash actions as Jido actions, wire Ash resources into agent workflows, emit or consume signals around Ash changes, or review boundary decisions between Ash domains and Jido agents.

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.

Builder-oriented guidance for the upstream `jido_behaviortree` package. Use when Codex needs to model agent decision trees, selectors, sequences, or fallback paths in Jido, or when it needs to turn sparse behavior-tree docs into a concrete runnable example without inventing unsupported runtime features.

Builder-oriented guidance for the upstream `jido_browser` package. Use when Codex needs to build browser-backed Jido automations, wrap navigation or extraction flows in actions, turn browser docs into runnable examples, or review `jido_browser` boundaries versus `req_llm` and app-specific scraping code.

Builder-oriented guidance for the upstream `jido_memory` package. Use when Codex needs to add memory spaces, retrieval flows, summarization or recall hooks, or review memory boundaries in Jido applications that also use `jido`, `jido_ai`, and external storage backends.

Builder-oriented guidance for the upstream `jido_messaging` package. Use when Codex needs to plan or review messaging adapters, bridge Jido signals onto external transports, or keep delivery semantics, retries, and routing boundaries explicit for Jido-based systems.

Builder-oriented guidance for the upstream `jido_otel` package. Use when Codex needs to add OpenTelemetry tracing to Jido applications, implement a tracer backend for Jido observability hooks, or review how spans, correlation ids, and exported telemetry should cross package boundaries.

Builder-oriented guidance for the upstream `jido_signal` package. Use when Codex needs to define signal schemas, route or dispatch events, bridge Jido signals to buses or transports, or review `jido_signal` boundaries versus `jido`, `jido_messaging`, and application code.

Guide human-in-the-loop Hex package releases for AgentJido repositories. Use when preparing, validating, dry-running, publishing, tagging, or dispatching a Hex release workflow.

Build and maintain composable Jido actions with validated inputs, explicit outputs, predictable errors, and AI-tool compatibility. Use when defining actions, schemas, action chains, or action execution behavior.

Build and maintain Jido agent modules, schemas, command handling, plugins, directives, and runtime wiring. Use when creating agents, changing agent behavior, or working with AgentServer-style runtime integration.

Integrate AI and LLM behavior into Jido systems using local jido_ai and req_llm conventions. Use when adding providers, model aliases, AI agents, tool calling, streaming, structured output, or skill prompt composition.

Provide Jido ecosystem context, package roles, conventions, and foundational patterns. Use before Jido agent, action, AI, testing, docs, or package work when the local repo needs shared Jido guidance.

Test Jido agents, actions, plugins, signals, directives, and AI integrations with focused unit and runtime coverage. Use when adding tests, fixing test gaps, or validating Jido behavior.

Harden a pull request by fixing blocking review findings, strengthening regression tests, validating locally, pushing to the PR branch, and updating AgentJido review-state labels. Use only when explicitly asked to fix a PR.

Review pull requests for correctness, tests, merge readiness, CI status, conflicts, and AgentJido review-state labels. Use when asked to review a PR, check if it is ready to merge, or provide PR feedback without editing code.

Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.

Structured code review for bugs, regressions, tests, and standards. Use before PRs or when asked for review; interactive mode can fix locally, while mode:agent reports only for pipeline callers.

Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.

Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.

Create structured plans for multi-step tasks -- software features, research workflows, events, study plans, or any goal that benefits from breakdown. Also deepens existing plans with interactive sub-agent review. Use when the user says 'plan this', 'create a plan', 'how should we build', 'break this down', or when a brainstorm doc is ready for planning. Use 'deepen the plan' or 'deepening pass' for the deepening flow. For exploratory requests, prefer ce-brainstorm first.

Diagnose and configure compound-engineering environment. Checks CLI dependencies, plugin version, and repo-local config. Offers guided installation for missing tools. Use when troubleshooting missing tools, verifying setup, or before onboarding.

Create or maintain STRATEGY.md - the product's target problem, approach, users, key metrics, and tracks of work. Use when starting a new product, updating direction, or when prompts like 'write our strategy', 'update the roadmap', 'what are we working on', or 'set up the strategy doc' come up. Also triggers when ce-ideate, ce-brainstorm, or ce-plan need upstream grounding and no strategy doc exists yet.

Execute work efficiently while maintaining quality and finishing features

Use this skill working with Ash Framework or any of its extensions. Always consult this when making any domain changes, features or fixes.

Use this skill working with Phoenix Framework. Consult this when working with the web layer, controllers, views, liveviews etc.

Review code changes for regressions, correctness, and missing tests.

Guides interactive Hex package release for AgentJido repos. Supports automated (GitHub Actions workflow_dispatch) and manual release flows. Uses git_ops for version bumping and changelog generation. Triggers on: release, hex publish, bump version, new release, publish package.

Review a Pull Request for code quality, tests, merge conflicts, and readiness to merge.

Take a pull request labeled needs_work, address blocking review findings, strengthen test coverage, rerun validation, and flip it to ready_to_merge when it is clean.

Review a Pull Request for code quality, tests, and merge readiness. Use when reviewing PRs, checking for merge conflicts, or providing feedback before merging.

Reviews code changes for quality, security, and best practices.

Converts between common units of measurement including temperature, distance, and weight.

Verify and update one LLM provider's llm_db metadata against that provider's public documentation, public model API data, and cached upstream source data, then prepare a PR. Use when asked to audit, check, confirm, validate, fix, or update provider model metadata such as model IDs, endpoints, limits, prices, modalities, capabilities, lifecycle/deprecation status, aliases, release dates, source mappings, or provider docs for this repository.

Review a Pull Request by analyzing code quality, tests, merge conflicts with main, and providing feedback on readiness to merge.

Review Pull Requests for code quality, tests, and merge readiness. Use when asked to review a PR, check a pull request, or analyze changes in a PR. Triggers on: review PR, check pull request, PR feedback, is this ready to merge.

Guides interactive Hex package release for AgentJido repos. Supports automated (GitHub Actions workflow_dispatch) and manual release flows. Uses git_ops for version bumping and changelog generation. Triggers on: release, hex publish, bump version, new release, publish package.

Guides manual Hex release prep for jido_runic. Uses the current version in mix.exs, the workflow_dispatch release workflow, and GitHub release notes instead of a local changelog. Triggers on: release, hex publish, bump version, new release, publish package.