LLM & Agents

Render A2UI JSON as native Castella widgets. Parse A2UI messages, handle actions, progressive rendering, data binding, and connect to A2UI-enabled agents.

Build chat interfaces and agent management UIs with Castella. Create chat components, display tool calls, manage multiple agents, and build agent hubs.

Processes and guardrails for recruiting, scheduling, consent, and incentive fulfillment.

Format code and keep style consistent using the repository’s canonical formatting/lint commands from `AGENTS.md`. Use after implementing changes or when formatting drift causes noisy diffs; keep formatting changes intentional and verified with build/tests.

Create, update, and validate repository skills under your agent’s skills directory (Codex: `.codex/skills/`, Claude: `.claude/skills/`) so they match the real codebase and `AGENTS.md` rules; tune YAML `description` triggers, apply feedback, and generate `<available_skills>` metadata blocks.

Get Codex's review of Claude's implementation plans. Trigger when user wants a second opinion on a plan ("have Codex review this plan", "get second opinion from Codex", "critique this plan with Codex"), or after Claude creates a plan file that needs validation before implementation.

Get Gemini's review of Claude's implementation plans. Trigger when user wants a second opinion on a plan ("have Gemini review this plan", "get second opinion", "critique this plan"), or after Claude creates a plan file that needs validation before implementation.

Use to run day-to-day loyalty reward catalog management and fulfillment.

Persona + messaging framework for K-12, higher-ed, and workforce enrollment campaigns.

Comprehensive Supabase expert with access to 2,616 official documentation files covering PostgreSQL database, authentication, real-time subscriptions, storage, edge functions, vector embeddings, and all platform features. Invoke when user mentions Supabase, PostgreSQL, database, auth, real-time, storage, edge functions, backend-as-a-service, or pgvector.

Use to enforce cadence rules, timezone coverage, and operational controls on social calendars.

Connect to A2A protocol agents from Castella. Communicate with agents, display agent cards, send messages, handle responses, and stream results.

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, keyword triggers, hook mechanisms (UserPromptSubmit), session tracking, and the 500-line rule.

Editing mode for clarity and semantic density; use for prompts, docs, specs, emails, and naming.

Orchestrate multi-agent swarms with agentic-flow (roles, topology, modes, shared state, resiliency).

使用 git worktree + 背景代理会话管理大型任务（默认启动 Claude Code；可用 --codex 快速切到 Codex CLI，或通过 --agent-cmd 指定任意命令）。适合用户希望在不阻塞当前会话的情况下执行大型或多步骤任务。

Prioritizes tests based on ROI and critical user journeys. Use when: deciding test coverage, selecting test types, or budgeting effort.

Retrieval-augmented generation (RAG) skill for the D&D 5e System Reference Document (SRD). Use when answering questions about D&D 5e core rules, spells, combat, equipment, conditions, monsters, and other SRD content. This skill provides agentic search-based access to the SRD split into page-range markdown files.

Testing commands and patterns for Oak AI project including running Jest unit tests, E2E tests with Playwright, coverage reports, and filtering tests. Use when writing tests, running test suites, or debugging test failures.

This skill refines rough ideas into fully-formed designs through collaborative questioning and exploration. Triggers: "help me brainstorm", "let's think through", "explore options", "what are some approaches", "help me design", "think through this with me", "ideate on", "what are my options". Use before writing code or plans when the approach is unclear. Not for mechanical/routine tasks where the solution is already known.