Ada Member

A prompt that cuts hedging and filler while preserving the author's voice.

Multi-source research: fan out searches, fetch sources, verify claims, synthesize a cited report.

A long-context workflow that chunks, maps, and reduces a huge document into a structured brief with Kimi.

Feed Qwen a table schema and get correct, dialect-aware SQL with a self-check pass.

A template that translates while preserving tone, formatting, and domain terminology with GLM.

Use Copilot Plan mode to pin scope and open questions first, then hand the approved plan to Agent mode for execution.

Upload a CSV or spreadsheet to ChatGPT, sanity-check the data, and only then ask for charts and conclusions.

A starter AGENTS.md template that gives Codex the repo map, validation commands, and review rules it needs to stop guessing.

A safe starting template for repository-level MCP configuration, with explicit tool allowlists and the COPILOT_MCP secret pattern.

Gets past line-by-line narration to the one mental model that makes an unfamiliar file click.

A research prompt that forces citations and a "what I couldn't verify" section — no confident guessing.

Describe a wireframe in text form.

Return to an earlier point in the conversation.

Toggle fast mode on or off.

Toggle sandbox mode on supported platforms.

List background terminals and show recent output lines for each.

Summarize with the emphasis on what matters most.

Reset the working context.

Rename the current chat session.

Create a structured implementation plan before starting code changes.

Continue the current session in the Claude Code Desktop app.

Rename the current session and show the name on the prompt bar.

Attach a file or folder to the conversation so follow-up turns use it directly.

Turn the answer into numbered, sequential steps.

Self-critique the answer after generating it.

Switch to planning mode, or submit a prompt within it.

Summarize the conversation so it uses less of the model's context window.

Alias for /usage: show session cost and plan usage.

Generate a one-line summary of the current session on demand.

Produce a process or concept diagram.

Browse available local skills and inject one into the current task.

OpenAI's local coding agent for inspecting repos, editing files, and running commands from your terminal.

An answer engine that cites its sources for grounded research.