Agent skills for Gemini CLI

Use when implementing navigation patterns, choosing between NavigationStack and NavigationSplitView, handling deep links, adopting…

Extract pixel-level data from an image of a chart or graph and produce a structured data table.

This skill should be used when the user wants to visualize data.

Implement or extend the opt-in Codex/T3-like chat-first shell.

Automate Chatbotkit tasks via Rube MCP (Composio).

Upload local files to a ChatGPT conversation through the Codex in-app browser without using the native file picker.

Transcribe a local audio/video file using ChatGPT's own voice-to-text (gpt-4o-transcribe) via your logged-in browser session — no API key…

Chatwoot integration. Manage data, records, and automate workflows. Use when the user wants to interact with Chatwoot data.

Automate Chatwork tasks via Rube MCP (Composio).

Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up…

Once-per-machine setup for cheap-scout. Use when the user runs /cheap-scout-setup, first install, "set up cheap scout", or…

Use when someone asks "does this sound AI?", "check if this is AI-written", "what gives this away as AI", "run check on this", or "score…

Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.

Run compile and type-check commands and report failures

Probe MCP auth for GitLab, GitHub, Jira, and Notion, verify CLI tools (gh, glab, argocd), and emit a simple connection report for Cursor…

Generate daily overview (TODAY.md) with calendar, tasks, weather, and motivational content.

Push unpushed commits across all repositories in the workspace

Examines obligations and legal protection in nitrate-polluted or eutrophic areas according to the Fertiliser Act, the Fertiliser Ordinance…

System architecture and API design with multi-AI consensus — use for design reviews and new subsystems

Concentrated liquidity AMM on Solana — swap tokens and query pools via the Whirlpools CLMM program.

Compare a pull request's implementation against spec context in spec_context.md and feed any material mismatches into review.json.