agenta

Helps add announcement cards to the sidebar banner system. Use when adding changelog entries, feature announcements, updates, or promotional banners to the Agenta sidebar. Handles both simple changelog entries and complex custom banners.

How to give the person a small interactive page in the drive: a board, checklist, queue, form, table or dashboard. Read it when the ask is for something to look at and touch rather than a reply. Covers picking a starter with create_app, the app folder layout, and the window.agenta bridge for hand-written apps.

Where to put frontend code (package vs the web/mobile app layer) and how to use the @agenta/* packages. Use when authoring or moving code in web/packages, choosing which @agenta/* package owns something (ui, entities, entity-ui, shared, chat, sessions, playground, the *-ui domain packages, ...), using molecules, the loadable bridge, the EntityPicker, or writing package unit tests.

Run the agent release gate — a portable, wire-level QA harness for the agent runtime. Drives the same product endpoint the playground drives and asserts on the SSE frame stream and real side effects, never on model prose, so it works against any deployment (cloud or self-hosted) from three env vars. Use before an agent-workflows release, or after changing the runner, the SDK agent adapters, the runner Docker images, or the agent service. Triggers: "run the release gate", "QA the agent runtime", "does the agent still work end to end", "pre-release agent QA".

Use this skill to create and publish changelog announcements for new features, improvements, or bug fixes. This skill handles the complete workflow - creating detailed changelog documentation pages, adding sidebar announcement cards, and ensuring everything follows project standards. Use when the user mentions adding changelog entries, documenting new features, creating release notes, or announcing product updates.

Use find_capabilities to discover the right Agenta tools for an agent you are building, report what each integration needs to connect, and wire the tools into the new agent's config. Use when a setup/builder agent must turn a plain-language task ("post to Slack and open GitHub issues") into attached, connected, ready-to-run tools.

Hard-won GitButler mechanics for multi-lane work in this repo — committing to a specific lane in a stack, spreading a pile of edits back across an existing stack, ordering a stack and setting PR bases, and recovering from a scrambled workspace. Use when working with stacked branches, when `but rub`/`but absorb`/`but commit --only` mis-routes a change, when a stack collapses or a commit lands on the wrong lane, or when a hunk gets dropped. Not needed for ordinary single-lane work.

Drive a researched and planned feature to a landed, tested change. Use after plan-feature has produced a docs/design/<project>/ workspace and the user says "implement it", "build the plan", "run the plan", or "let's ship this". Orchestrates refresh-plan, implement, review, a debug-local-deployment loop, and a test loop across the daytona / local-pi / claude x SDK / UI matrix, then documentation and a GitButler stacked branch. The orchestrator stays in the loop and spins narrow subagents for each phase.

Feature-folder layout, states/ convention, and data-flow rules for the Agenta mobile app (web/mobile). Use when creating or moving files under web/mobile, deciding where a component lives, adding a new feature or screen, or wiring data into mobile components.

Motion design rules for the Agenta mobile app (web/mobile) — the shared presets in src/lib/motion, when to animate, and reduced-motion requirements. Use when adding any animation or transition under web/mobile, animating navigation, sheets, skeletons, or list/chat surfaces.

How the Agenta mobile app (web/mobile) installs and extends shadcn/ui registry components, themes them via the palette token bridge, and builds chat UI on @agenta/chat. Use when adding UI components under web/mobile, changing theme colors, editing components.json or globals.css, or building chat UI.

Create a plan for a feature, and the files required to continue working on it. Use when the user asks for research for a feature or a plan to run it.

Resolve findings by implementing the chosen fix path in code, tests, or docs. Accept optional `path` and a `priority` selector; by default resolve only the next highest remaining priority bucket, in order `P0`, `P1`, `P2`, `P3`. Also accept explicit levels or `all`. Default to `path=infer`. Confirm effective variables before starting.

Perform a fresh-context scan of code and docs that turns verification observations and missing-test gaps into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.

Sync the findings record against local review artifacts and optionally a GitHub PR. Accept optional `path` and GitHub PR `url`; when `url` is provided, sync against both remote PR state and local state, otherwise default to local-only sync. Default to `path=infer`. Confirm effective variables before starting.

Refresh Agenta's harness catalogs, provider model lists, recommended defaults, and provider-supplied display names. Use for new OpenAI, Anthropic, Codex, Pi, or OpenRouter models and before releases that need current model choices.

Run or inspect the relevant validation paths and turn failures, regressions, or missing coverage into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.

Coordinate findings work with the user, decide whether scan, test, or sync should run, and turn the current findings set into a ready plan. Accept optional `path` and GitHub PR `url`; default to `path=infer`. Confirm effective variables before starting.

Update the API reference documentation by downloading the latest OpenAPI spec from production and regenerating the Docusaurus API docs

Audit and update the supported LLM model list in assets.py against litellm's registry (models.litellm.ai). Use when adding new models, pruning outdated ones, or verifying the list is correct.