review-skills

Base44 entities: the JSON-schema data models under base44/entities/, the entity SDK, and row-level security (RLS) rules. Use when adding or changing stored data, queries, or per-user access rules in a Base44 app.

Troubleshoot production issues using backend function logs and workflow run history. Use when investigating app errors, debugging function calls, diagnosing why a scheduled job or automation failed, or diagnosing production problems in Base44 apps.

The base44 SDK is the library to communicate with base44 services. In projects, you use it to communicate with remote resources (entities, backend functions, realtime actors, ai agents, and the AI gateway for code agents, image, video, and speech generation, and AI decisions) and to write backend functions and actors. This skill is the place for learning about available modules and types, including actors — the realtime/WebSocket primitive for multiplayer, collaborative boards, presence and live cursors, in-room chat, and live auctions. When you plan or implement a feature, you must learn this skill

Develop a Base44 app remotely inside Base44's cloud sandbox using your own agent — no local checkout and no deploy/push commands. The implementation is remote: writing a resource file into the sandbox is what ships it (backend functions, realtime actors, entities, and agents all auto-sync from the file you write), and OAuth connectors are set up against the remote app via MCP tools or the projectless `base44 connectors` CLI. This skill is the place for learning what you can author in the sandbox, how backend functions, actors, entities, and agents are structured, and how to connect a connector without a local filesystem. Triggers on 'develop my Base44 app remotely', 'no local files', 'cloud sandbox', 'create an entity/agent remotely', 'add realtime/multiplayer/presence remotely', 'connect a connector remotely', 'bring my own agent', or any work editing a Base44 app inside a sandbox.

Develop a Base44 app remotely from your own coding agent (Claude Code, claude.ai, or any MCP client) by connecting it to the Base44 sandbox. Cloud agents connect over MCP; local agents can connect over MCP or drive the same sandbox with the `base44 sandbox` CLI subcommands (the CLI uses shorter names — e.g. read_file is `sandbox read`, list_directory is `sandbox ls`, run_command is `sandbox run`). Covers connecting/ authenticating, the available sandbox tools (run_command, read_file, write_file, edit_file, grep, list_directory, create_checkpoint, list_user_apps, and the connector tools list_connectors / initiate_connector_connection), the edit→preview→verify loop, how changes persist, builder/external-agent concurrency, the in-editor "Send to Coding Agent" button + onboarding README URLs, and tips like reading the Vite dev-server logs. Triggers on "develop my Base44 app remotely", "connect Claude Code to Base44", "bring my own agent", "edit a Base44 app over MCP", "Base44 sandbox MCP", or "Send to Coding Agent".

Base44 workflows: trigger-driven automated processes defined as CNCF Serverless Workflow files under base44/workflows/ (scheduled, entity, connector, in-app agent, auth, publish and payment triggers; call, wait and switch steps; jq expressions), with the full authoring guide, plus the legacy automations pipeline for apps that predate workflows. Use for any 'when X happens, do Y' or 'every N hours, do Y'.

Base44 platform concepts for a web or native mobile app: entities, backend functions or server code, workflows, pages and layouts, the project file structure, authentication (platform login vs the custom-auth boilerplate), user invites and the GitHub features. Read first when starting work on a Base44 app.

Base44 built-in integrations on the SDK client: InvokeLLM, SendEmail, file uploads (public and private), signed URLs, data extraction and image generation, with every Core endpoint's input schema, plus analytics event tracking. Use when a feature needs AI, email, files or analytics without a third-party service.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to generate or edit music.

创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。