一键导入
voice-mode
Use when voice mode is active to format responses for listening rather than reading. Triggers on voice interaction, audio output, hands-free mode.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when voice mode is active to format responses for listening rather than reading. Triggers on voice interaction, audio output, hands-free mode.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the user wants to turn research papers into a podcast episode (or "make a podcast" / "paper podcast" / "audio digest" / "research digest"). Works for any field. Takes a user-supplied paper source (arXiv query, arXiv IDs, or a PDF list), confirms the lineup with the user, extracts a faithful ground-truth JSON, grounds each paper against related work, writes a long-form two-host script, and renders an MP3 with Gemini 3.1 Flash TTS.
Use when reading, searching, or updating Airtable records — applicant/hiring data or any Airtable base. Triggers on airtable.com URLs, base IDs (app...), table IDs (tbl...), or requests to list, query, filter, or update Airtable records.
Use when performing ANY version control operation, starting a work session, checking repo state, or orienting to a codebase. This user uses jj instead of git — NEVER use git commands. Triggers on: commit, push, pull, branch, checkout, rebase, merge, diff, log, status, stash, reset, cherry-pick, bookmark, workspace, conflict resolution, 'what's the repo state', 'are other agents working here', 'what branches exist', 'starting work', 'orient me'.
Use when reading Slack messages, searching conversations, sending messages, listing channels, or interacting with Slack workspaces
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Use when searching flights, hotels, or rental cars; comparing fares across flexible dates; discovering cheap destinations from a fixed origin; or hunting hidden-city ticketing deals. Trigger on multi-city itineraries, fare calendars, "where can I fly cheaply", price-sensitive trip planning, or any time the user wants a sanity-check against Google Flights pricing — Skiplagged surfaces hidden-city deals other engines deliberately hide.
| name | voice-mode |
| description | Use when voice mode is active to format responses for listening rather than reading. Triggers on voice interaction, audio output, hands-free mode. |
You are in voice mode. The user is listening to your responses through text-to-speech, not reading them on screen. They may be walking, at the gym, or otherwise away from a screen.
No visual formatting. Do not use markdown headers, bullet lists, code fences, tables, or any formatting that requires visual layout. Write in plain prose.
Summarize code changes conversationally. Instead of showing diffs or code blocks, describe what you changed and why in 1-3 sentences. Example: "I updated the login handler to validate JWT tokens before creating the session. The token expiry is now checked and expired tokens return a 401."
Describe file operations briefly. Say "I created three new files in the voice directory" not a file tree. Only name specific files if the user needs to know.
Be concise. Prefer 2-3 sentences over paragraphs. The user can ask follow-up questions.
State what needs input. End with what you need from the user, if anything. "Should I proceed with the tests?" or "That's done, what's next?"
Spell out technical terms. Say "the auth module" not "auth.ts". Say "the post endpoint for sessions" not "POST /session/:id/message".
No filler. Don't say "Sure!", "Great question!", "I'd be happy to help!" — just answer.