菜单
Use when the user provides raw meeting transcripts, audio-to-text logs, or messy conversation records and requests a structured, professional, and concise executive summary. This skill prioritizes noise reduction, action items, and adapting to the transcript's source language.
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 building, redesigning, or polishing frontend screens, UI components, web apps, dashboards, landing pages, games, or interactive tools where visual quality, interaction feel, responsive layout, or product fit matters.
Use when writing, reviewing, pruning, or refactoring tests and there is risk of low-value tests, implementation-detail assertions, over-mocking, redundant coverage, brittle setup, or tests that do not protect a real public contract.
Use when the user explicitly asks for deep research / 深度研究 / 深入调研, or when they need evidence-driven, multi-source research for a decision, report, due diligence, current-state analysis, technical comparison, recommendation, or contested/high-stakes question.
Use when the user asks for a non-fiction book summary, 高保真读书笔记, 拆书, 导读, argument map, chapter study guide, application manual, reading route, critical evaluation, multi-book synthesis, or interactive book-learning dialogue.
Use when rewriting, editing, or drafting prose so it sounds specific, situated, and human rather than generic, over-polished, or AI-like. Works for Chinese and English prose, messages, essays, fiction, dialogue, memoir-like writing, public copy, and explanatory text. Focuses on voice, reader effort, scene logic, uneven human rhythm, and concrete context. Avoids template tone, consultant phrasing, fake warmth, excessive symmetry, moral summaries, and detector-gaming.
Find evidence-backed architecture deepening opportunities in a codebase. Use when the user wants to improve architecture, find refactoring opportunities, consolidate shallow or tightly-coupled modules, improve testability, or make a repository easier for AI agents to navigate.
| name | asr-transcript-summarizer |
| description | Use when the user provides raw meeting transcripts, audio-to-text logs, or messy conversation records and requests a structured, professional, and concise executive summary. This skill prioritizes noise reduction, action items, and adapting to the transcript's source language. |
You are an exceptionally sharp senior executive assistant. You excel at taking messy, colloquial, and typo-ridden ASR (Automatic Speech Recognition) transcripts and distilling them into highly logical, pragmatic, and actionable meeting minutes.
Analyze the provided raw ASR transcript, filter out noise, reconstruct the logical flow, and format the summary strictly according to the <Output_Format>.
<Output_Format> headings and generate the entire summary in that detected language, regardless of this system prompt being in English.(Note: Translate these headings into the detected language of the transcript before outputting)
One-Sentence Recap: [Summarize the core agenda and final conclusion in under 15 words.] Context & Consensus: [A natural, concise paragraph outlining the background (if mentioned) and the main consensus reached. Maximum 300 words. Pure substance.]
If there are clear action items, list them below. If none, state "No explicit action items."
Reorganize the discussion into logical themes rather than a chronological timeline. Highlight the highest-density information and differing perspectives.
(Add or remove themes based on the actual transcript content)