“summarization”

智能内容摘要与总结 (Use when: 需要总结长文档、提取要点、生成摘要).

Fetch and summarize a list of URLs (e.g.

When user asks to summarize text, articles, documents, meetings, emails, YouTube transcripts, books, PDFs, reports, conversations, or any long content.

MCP server for summarizer ai.

Generate a summary document from the current work session

Summarize CSV files into per-column stats (type, count, nulls, min/max/mean for numbers).

Summarize CSV files with statistics and previews.

Faithfully compress caller-selected documents, issues, code, topic packets, or explicit session batches for a declared reader and purpose.

Summarizes uncommitted changes and flags anything risky.

Summarize the current AI coding session and export it as an Obsidian note

Summarize the current git changes into a concise, reviewer-friendly overview grouped by theme.

Summarize pasted text or tool output into concise decisions, facts, and next steps.

Fetch a URL and turn it into a short, structured note.

No-confirmation fast path over summarize-event — compose the segment summary and submit it in one shot.

Summarize uncommitted changes and flag risks.

Compress a note significantly while preserving provenance markers

Summarize a single Outlook email in detail.

Summarize long text content using Tongyi Qwen (通义千问) via DashScope API.

Summarize a call, meeting, or recording transcript into a filtered Q&A document.

Summarize recent activity in a Slack channel

Loaded by the summarizer agent to supply operating protocol and invariants for structured markdown summary generation in the parity-test-c pipeline.

Fetch a URL and return a concise markdown summary of its content.

When a tool result exceeds a token threshold, save the full response to disk under the session dir, feed it to a cheap summarizer (Haiku) with an intent-aware…

总结 URL 网页、PDF 文件、文本文件的内容。提取正文后调用火山引擎大模型生成中文摘要。