给你的 AI 助手 装上 专业技能

examples-run-analysis

Analyze logs and source from a completed repository example run. Never execute or control examples.

docs-sync

Audit or update authored English SDK documentation within a requested topic or diff using implementation evidence.

code-change-verification

Run the required final install, build, type, lint, test, and format checks after eligible SDK changes pass review.

开发工程师

Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifying PR changeset compliance and bump level.

miniapp-dev

Generate, operate, and refine OpenBitFun MiniApps. Use when the user wants a new MiniApp, asks the Agent to inspect or operate a running MiniApp, or wants an existing MiniApp redesigned or extended. Typical triggers: "做一个小应用", "操作这个 MiniApp", "查看小应用当前状态", "改造 mini app".

openbitfun-frontend-dev

Safely customize the running packaged OpenBitFun desktop frontend through a draft, a provisional hot apply, and a 15-second user-confirmed rollback window. Use only in OpenBitFun Creative mode when the user asks to change OpenBitFun's own client UI.

前端开发

create-agent

Create or update OpenBitFun custom modes and subagents. Turn the user's needs into a role prompt and a suitable tool selection, then save an agent definition. Use for reusable roles, not ordinary delegation to an existing subagent.

Skill与智能体开发

plan

Research and write an actionable implementation plan without implementing it. Use when the user asks to plan, design an approach, or inspect a change before coding; stop applying the planning restriction once the user explicitly asks to implement.

find-skills

Discover and install reusable agent skills when users ask for capabilities, workflows, or domain-specific help that may already exist as an installable skill.

Skill与智能体开发

debug

Use this skill to locate a runtime bug. Add targeted instrumentation, collect reproduction evidence, and confirm the root cause before changing code.

开发工程师

builtin

Synthetic built-in skill that must never be migrated.

commit-push-pr

Commit selected local changes, push the branch, and create or update a GitHub pull request with OpenBitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from OpenBitFun.

multitask

Coordinate multi-part work through parallel subagents when two or more workstreams can proceed independently. Use for decomposable tasks where concurrency materially reduces the critical path; skip for trivial or tightly sequential work.

user-skill

Synthetic user skill used by migration tests.

Skill与智能体开发

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

内容创作者测试与质量写作与文案

miniapp-dev

Maintain MiniApp framework code in this repository, or find the canonical built-in MiniApp authoring guide and examples.

generate-image

Generate photos, illustrations, posters, and project assets through OpenBitFun's configured default image model. Shape prompts, inspect results, and make targeted refinements using generate_image. Not for image analysis, prompt-only discussions, or edits that must preserve an existing image.

图像与多媒体Skill与智能体开发

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer OpenBitFun's ControlHub browser domain for web automation when it is available; use agent-browser only when ControlHub is unavailable or for supported Electron automation, and use OpenBitFun ComputerUse for native desktop UI that agent-browser cannot reach.

测试与质量Skill与智能体开发