Build a Chrome MV3 extension that runs inside WebToApp's MV3 runtime

Build a new holaOS app using @holaboss/app-builder-sdk (5 backend primitives + optional shadcn dashboard UI). The canonical path for vibe-coded apps — integration modules AND dashboard apps both live here.

多源内容智能处理器：支持微信公众号、网页、YouTube、播客（小宇宙/喜马拉雅）、PDF、Markdown等，自动上传到NotebookLM并生成播客/PPT/思维导图等多种格式。支持深度分析模式和飞书文档自动创建

Access local system resources including Calendar on macOS and Windows. Use this skill when you need to manage user's schedule directly on their device.

Copy-paste detector for 220+ languages. Detect duplicated code and measure duplication percentages.

Create a proto-persona from current research, market signals, and team knowledge. Use when you need a working customer profile before deeper validation.

Run an end-to-end product strategy session across positioning, discovery, and roadmap planning. Use when a team needs validated direction before committing to execution.

飞书日历与日程管理工具集。包含日历管理、日程管理、参会人管理、忙闲查询。

Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.

Map paper claims to available BibTeX citation keys before section drafting.

Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skill_exec when a meta-skill needs local image files and structured IMAGE_READY records without spawning an LLM agent.

Sonos control: search, queue, playlists, rooms/groups, volume, YouTube.

Mac fleet upkeep: global packages, safe repo sync, Xcode, disk, Trash, and health.

Codex 1M context: direct OpenAI Responses API inference, safe Sol/Terra/Luna input headroom, Keychain delivery, and Mac fleet rollout.

Claude Code-only work routing: delegate implementation, fixing, exploratory subagents, rebasing, and PR merging/landing to Codex CLI while Claude specifies, decides, reviews, and verifies. Direct hands-on delegation requires ANTHROPIC_BASE_URL to be unset or neither loopback nor gorillaclaw.sheep-coho.ts.net. Codex-backed autoreview is always allowed and preferred, independent of environment.

Hosted-gateway LLM router — save 67% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 55+ models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 8 free NVIDIA models included. Also exposes realtime market data (global stocks, crypto, FX, commodities), Twitter/X intelligence, prediction-market data across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + UMA oracle resolution + wallet identity & clustering, phone-number intelligence (carrier + SIM-swap fraud detection) plus AI-powered outbound voice calls (Twilio + Bland.ai), AND the Surf unified crypto data API (84 endpoints — CEX/DEX, on-chain SQL over 80+ ClickHouse tables, 100M+ labeled wallets, prediction markets, social/CT mindshare, news, VC fund intel) as built-in agent tools. Not a local-inference tool — prompts are sent to the blockrun.ai gateway.

Ensures codebase deliverables are properly exported as ZIP archives through a dedicated finalization step

Create or edit Excel workbooks with openpyxl-specific pitfall handling, anchored preflight audit, and deterministic post-write proof that every criterion is satisfied

Create structured medical SOAP notes by writing comprehensive content to a file in one iteration

Recover from execute_code_sandbox failures by writing Python scripts to files and executing via run_shell