Development

This skill should be used when about to write Dart or Flutter code that calls into a pub package whose API is uncertain — the package is unfamiliar, or its version in pubspec.lock may be newer than training data. Also load when hitting an unexpected compile error or type mismatch on a package import. Skip for code that only uses the Dart SDK (dart:*) and packages already verified this session.

Automate web browsing tasks — navigate websites, click buttons, fill forms, extract data, handle logins. Use when asked to interact with any website or web application.

Trigger when building, designing, or validating UI/UX for web apps. Also trigger when asked to take screenshots of web pages, check if a UI looks correct, or navigate and inspect page structure.

You are investigating a production issue using CloudWatch Logs Insights. Follow the structured methodology below, adapting queries based on what you discover in each phase.

Use when a change request affects multiple services or needs cross-service coordination. Activates the Cascade orchestration workflow with dependency-aware propagation.

Use when verifying that a cross-service change was applied correctly. Checks for stale references, contract mismatches, uncommitted changes, and broken imports across all services.

Use when working with API contracts in a multi-service project. Ensures contracts stay in sync with implementations and downstream consumers are updated when APIs change.

This skill should be used when writing commits, PRs, or comments that will be visible to OSS maintainers — it covers the no-AI-attribution rule, AI-tell avoidance in writing, and the situations where a human contributor should respond instead of the AI tool. Sibling to oss-contribution and pr-etiquette.

This skill should be used when the user asks to "plan a feature", "what goes in the phase file", "which file owns this", "what evidence class is this", "how do I verify a claim no test can settle", "where should this doc go", or when writing, reading or updating any zforge feature document under docs/{feature}/. Provides the template structure, file ownership rules, the two-axis evidence scale for what was executed and what was judged, phase states, and naming conventions.

Report Codex CLI prerequisites and login status for image generation

Generate one or more images, optionally with reference images, through Codex CLI's built-in imagegen skill

This skill should be used when the user asks to "retro", "evaluate zforge", "review plugin performance", "score this session", or wants to assess how well zforge's workflow served a feature. Evaluates zforge's workflow scaffolding, not the project's technical decisions or LLM reasoning quality.

Edit an image through Codex CLI's built-in imagegen skill

This skill should be used when implementing or designing code with async data flows — "state management design", "async data flow", "stale data", "cache invalidation", "optimistic update", "init order", "race condition", "write then read", "data not updating", "cache not refreshing", "UI shows old data after save", "value doesn't update", "empty data on first load". Also applicable when working with caching layers, event-driven systems, or any code where write and read paths have different la...

Extract transcript or subtitles from a local video file. Use this skill whenever the user asks to transcribe a video, extract speech-to-text, get subtitles, or wants a text version of what's said in a video. Also trigger on "提取字幕", "视频转文字", "语音转文字", "transcribe", "extract audio text", or when the user references getting a script/transcript from any video file (mp4, mkv, mov, avi, webm). This skill is for LOCAL video files — for YouTube or other online URLs, use the download-video skill first ...

Generate professional voiceover narration for a video with audio-video sync using Azure TTS by default, or Gemini 3.1 Flash TTS when configured. Use this skill whenever the user wants to add narration, voiceover, commentary, or voice dubbing to any video file — even if they just say "add audio to this video" or "make a narrated version." Also trigger when the user has a screen recording, demo, tutorial, or presentation video that needs a voice track. Trigger on Chinese requests like "视频配音", "...

Download videos from 1000+ websites (YouTube, Bilibili, Twitter/X, TikTok, Vimeo, Instagram, Twitch, etc.) using yt-dlp. Use this skill whenever a user shares a video URL, asks to save or download a video, wants to extract audio from an online video, needs a specific quality like 1080p or 4K, or mentions downloading a playlist. Also trigger on "下载视频", "保存视频", "提取音频", or any URL from a supported video platform.

Install Snowflake CLI and Cortex Code CLI. Use when cortex is not installed, when the user asks to set up Cortex Code, or when routing fails because the CLI is missing. Triggers: setup cortex, install cortex, cortex not found, CLI not installed, set up snowflake.

ONLY load this skill when the user explicitly types $cortex-run or /cortex-run. NEVER load this skill from auto-routing hooks or keyword matching. For auto-routed prompts, use cortex-code:cortex-router instead.

Auto-routing skill loaded by the prompt filter hook. Routes Snowflake-related operations to Cortex Code CLI. Not for direct invocation — use $cortex-run instead.

Internal guidance for presenting Gemini helper output back to the user

SolidJS framework development skill for building reactive web applications with fine-grained reactivity. Use when working with SolidJS projects including: (1) Creating components with signals, stores, and effects, (2) Implementing reactive state management, (3) Using control flow components (Show, For, Switch/Match), (4) Setting up routing with Solid Router, (5) Building full-stack apps with SolidStart, (6) Data fetching with createResource, (7) Context API for shared state, (8) SSR/SSG confi...

Gemini model prompting guide for effective task delegation from Claude Code

Internal helper contract for calling the gemini-companion runtime from Claude Code