Topic · Writing & Content
Best summarization skills for Claude Code, Codex and other agents.
- skills
- 240
- official
- 12
Summarization skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams. | bytedance/ | 84k | 4 repos | ~1.3k | Automated safety check: Pass | MIT | today |
| 2 | Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project. | karpathy/ | 59k | 1 repo | ~494 | Automated safety check: Pass | MIT | 1 mo ago |
| 3 | This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve… | guanyang/ | 977 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | yesterday |
| 4 | Explains a whole book to someone who has not read it, keeping its specific content and showing how its threads connect, and saves the result as an Org note. | lijigang/ | 7.5k | — | ~1k | Automated safety check: Pass | MIT | yesterday |
| 5 | Fetches web pages and PDFs and returns a source-grounded summary, clean Markdown, quotes or citations, routing each kind of link to a suitable fetch method. | tw93/ | 7.2k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 6 | Fetches Hacker News top stories, a chosen story with its comment thread and the linked article through the official APIs, then summarizes them. | ykdojo/ | 10k | — | ~942 | Automated safety check: Pass | Unknown | 14 days ago |
| 7 | Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub, arXiv, Hugging Face Papers, AIHOT, TLDR… | cclank/ | 1.3k | — | ~2.1k | Automated safety check: Pass | No licence | 4 mo ago |
| 8 | Batch-triage and act on a set of node-redis PRs (or issues) by filter — fan out the maintainer-review methodology across them, present a one-word verdict plus a tldr to the user one at a time for… | redis/ | 18k | — | ~1.9k | Automated safety check: Pass | MIT | yesterday |
| 9 | Diagnose and configure MemSearch memory behavior. An agent skill from zilliztech/memsearch. | zilliztech/ | 2.7k | — | ~2.9k | Automated safety check: Pass | MIT | 15 days ago |
| 10 | Rewrite engineer-to-engineer content for engineering-org leadership (VPs, directors, PMs, release managers, execs in an engineering-savvy company) and shape it for the channel it is going to — JIRA… | thananon/ | 3.2k | — | ~3.2k | Automated safety check: Pass | No licence | 3 mo ago |
| 11 | Fetches AI news from smol.ai RSS and generates structured markdown with intelligent summarization and categorization. | geekjourneyx/ | 235 | — | ~2.3k | Automated safety check: Pass | No licence | today |
| 12 | A skill your agent uses when a user wants to search archived VSS video or ingest or delete a source for search. | NVIDIA-AI-Blueprints/ | 1.9k | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Fetches the transcript of a YouTube video through TranscriptAPI.com so the agent can summarize, quote, translate or fact-check what was said. | ZeroPointRepo/ | 1k | 1 repo | ~1.1k | Automated safety check: Pass | MIT | 2 days ago |
| 14 | Quick reference for wdoc, a command-line and Python tool that summarizes, searches and answers questions over documents of many file types. | thiswillbeyourgithub/ | 545 | — | ~1.1k | Automated safety check: Pass | AGPL-3.0 | 1 mo ago |
| 15 | Collects technical documents from URLs, files, wikis or APIs, filters them by role or technical direction, and writes a structured report on architecture, algorithms and design decisions. | yaofeino1/ | 144 | — | ~1.2k | Automated safety check: Pass | No licence | 6 mo ago |
| 16 | Answers questions about recent AI news by querying AIHOT's Chinese-language agent API live, covering daily highlights, search, hot events and the daily digest. | KKKKhazix/ | 21k | — | ~461 | Automated safety check: Pass | MIT | 8 days ago |
| 17 | 17.Qwen Agent Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the claude-9arm command instead of burning Claude tokens/quota. | thananon/ | 3.2k | — | ~1.5k | Automated safety check: Pass | No licence | 3 mo ago |
| 18 | Plan, triage, and write academic rebuttals and review responses. | M1n-n9/ | 692 | — | ~1.9k | Automated safety check: Pass | No licence | 3 mo ago |
| 19 | Briefs you on what just happened around a named topic and maps public opinion on X, using the host's native X search tools only. | kunchenguid/ | 231 | — | ~2.1k | Automated safety check: Pass | MIT | 2 mo ago |
| 20 | Toolkit for generating PowerToys release notes from GitHub milestone PRs or commit ranges. | smith-chem-wisc/ | 109 | — | ~1.4k | Automated safety check: Pass | MIT | 2 days ago |
| 21 | Pulls YouTube transcripts, searches videos and channels and browses playlists through the TranscriptAPI service with a single API key. | ZeroPointRepo/ | 1k | 1 repo | ~3k | Automated safety check: Pass | MIT | 2 days ago |
| 22 | Finds recent arXiv and bioRxiv papers on a topic, narrows them in stages to one pick per field, and writes bilingual Chinese and English summaries. | Galaxy-Dawn/ | 5.7k | — | ~1k | Automated safety check: Pass | MIT | 16 days ago |
| 23 | 23.Analyzer Content Analyzer — any content (URL, text, transcript) into structured analysis report with actionable insights. | iBigQiang/ | 614 | — | ~1k | Automated safety check: Pass | MIT | 1 mo ago |
| 24 | Condenses a lecture PDF into an exam-focused LaTeX cheat sheet and compiled PDF with page citations, bilingual terms, formulas and only the diagrams that help. | Li-Baichuan-James/ | 312 | — | ~6.7k | Automated safety check: Pass | MIT | 5 mo ago |
| 25 | Use iDeer as a daily paper-reading workflow for chatbot-first users such as Codex, Gemini, or ChatGPT. | AI45Lab/ | 416 | — | ~3k | Automated safety check: Notes | AGPL-3.0 | 2 mo ago |
| 26 | Fetches YouTube transcripts through TranscriptAPI.com so an agent can summarize, quote or translate a video from a link or ID. | ZeroPointRepo/ | 1k | 1 repo | ~1.1k | Automated safety check: Pass | MIT | 2 days ago |
| 27 | Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded… | microsoft/ | 18k | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 28 | 28.HTML Summary Convert a stakeholder summary markdown file into a single self-contained HTML executive report — bottom line and decision asks up front, supporting detail later — styled with a Test Double-derived… | testdouble/ | 279 | — | ~2.9k | Automated safety check: Pass | MIT | 8 days ago |
| 29 | A skill your agent uses when a user asks how many tokens (or how much context/cost) ContextPilot has saved, or wants a ContextPilot savings status/summary inside Hermes Agent — e.g. | EfficientContext/ | 140 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 30 | Add agent-ready vision capabilities — dense captioning, detection, search, alerting, summarization — to an agent or application through a customizable, self-contained vision stack built on the… | NVIDIA-AI-Blueprints/ | 1.9k | — | ~15k | Automated safety check: Notes | Apache-2.0 | today |
| 31 | Converts a report or other document into a business story and then an infographic image, pausing for your review after each step. | TyrealQ/ | 108 | — | ~814 | Automated safety check: Notes | MIT | 15 days ago |
| 32 | Fetches YouTube transcripts, video metadata, channel info, search results and playlists through the TranscriptAPI.com service, with no Google API quota or OAuth setup. | ZeroPointRepo/ | 1k | 1 repo | ~2.3k | Automated safety check: Pass | MIT | 2 days ago |
| 33 | Edits a video transcript or long text into a self-contained HTML reading report, organized by what the content is about instead of a fixed outline. | imexlovery/ | 193 | — | ~1.9k | Automated safety check: Pass | No licence | 7 days ago |
| 34 | 34.Open PR Open a pull request on the Kiln repo for a human to complete. | Kiln-AI/ | 5.2k | — | ~6.1k | Automated safety check: Pass | Unknown | today |
| 35 | Fetches a YouTube transcript with a helper script and reshapes it into chapters, summaries, X threads, blog posts or timestamped quotes. | Prismer-AI/ | 1.6k | 2 repos | ~905 | Automated safety check: Pass | MIT | 9 days ago |
| 36 | Convert quantitative research report PDFs to markdown, then extract structured knowledge (paperId, title, year, source, keywords, tldr, abstract, strategy, method, experiment, result) into JSONL… | CamusGIT/ | 151 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 37 | 37.Tldr Summarize the current conversation into a TLDR note and save it to your notes folder. | earlyaidopters/ | 173 | — | ~953 | Automated safety check: Pass | No licence | 5 mo ago |
| 38 | Summarizes recent agent sessions for the current project by date, with each session's title, status, observation count and top highlights from memory. | rohitg00/ | 29k | — | ~510 | Automated safety check: Pass | Apache-2.0 | today |
| 39 | Researches a topic and drafts a ready-to-send newsletter in Markdown, such as a weekly roundup, daily digest or industry briefing, with curated links and commentary. | bytedance/ | 84k | 1 repo | ~3.2k | Automated safety check: Pass | MIT | today |
| 40 | Scaffolds and wires a new NestJS service/module for the Video Search & Summarization sample app's pipeline-manager using the repo's real conventions. | open-edge-platform/ | 169 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | today |
| 41 | MBB-level management consultant with mastery over structured thinking, frameworks, guesstimation, industry analysis, and executive-grade deliverables. | DogInfantry/ | 132 | — | ~14k | Automated safety check: Pass | Unknown | 18 days ago |
| 42 | Turns recent Claude Code, Codex or opencode work into Japanese daily reports, reflections, reviews and trend summaries saved in a reports folder. | nwiizo/ | 180 | — | ~2.3k | Automated safety check: Pass | MIT | 8 days ago |
| 43 | 当用户想获取、查看、汇总、分析或本地过滤 AI 最相关的最新信息时使用本 Skill;只要请求有哪怕 1% 与 AI 最新动态、技术趋势、开源热榜、社区讨论或工程实践相关,就必须优先调用本 Skill。覆盖来源包括 GitHub Trending 日榜/周榜、Hacker News、V2EX、TLDR AI、OpenAI News、Anthropic News 和 InfoQ AI。本… | wenbochang888/ | 160 | — | ~703 | Automated safety check: Pass | MIT | 3 days ago |
| 44 | 44.Rundown Answer in the Rundown briefing style (TL;DR + checklist + numbered choices). | alexgreensh/ | 1.4k | — | ~677 | Automated safety check: Pass | AGPL-3.0 | 1 mo ago |
| 45 | Evidence-based security report generation for firmware assessments. | OrbitCurve/ | 215 | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 46 | Run a selected coding-agent CLI programmatically, with latency, error, usage, cost, and trace logging. | swyxio/ | 175 | — | ~2.2k | Automated safety check: Pass | MIT | 4 days ago |
| 47 | 中文论文深读、总结/TL;DR、工程拆解、按论文实现/复现、比较与证据审计。用户给出论文 PDF、链接、标题、摘要、正文或图表,或明确要读论文时使用。只有论文锚点且无附言时澄清阅读目标;只有阅读意图时问哪篇。已有论文时,“看看这篇”直接深读。不用于仅翻译、解释单个术语、生成 BibTeX、找或下载论文。 | MrGeDiao/ | 103 | — | ~1.3k | Automated safety check: Pass | MIT | 6 days ago |
| 48 | 48.Tldr Deep Full 5-layer analysis of a specific function. An agent skill from parcadei/Continuous-Claude-v3. | parcadei/ | 3.9k | 1 repo | ~677 | Automated safety check: Pass | MIT | 8 mo ago |
Questions, answered from the data.
What is the best summarization skill?
GitHub Deep Research from bytedance/deer-flow ranks first of the 240 summarization skills listed here, with the highest score: its repository has 84k GitHub stars, 4 other GitHub owners carry a copy, its SKILL.md loads about 1.3k tokens and it passes the automated safety check with no findings. Next come Read arXiv Paper and Context Compression.
Which summarization skills are official?
12 of the 240 summarization skills are official, published by the vendor's own GitHub organization: Maintainer Triage, Report, Hugging Face Paper Pages, Prd, Create Tldr Page and 7 more.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.
Explore related skills
Category
More topics in Writing & Content
- Translation702
- Brand voice and tone522
- Social media posts513
- Plain language and style rules422
- Content strategy358
- Blog and article writing342
- Copywriting335
- Creative writing and fiction328
- Humanizing AI text316
- Newsletters222
- Technical writing187
- Copy editing and proofreading152
- Content repurposing151
- Storytelling144
- Internal communications87
- Email writing61
- Talk and speech writing18