SkillAtlasSkill 详情

latchshot-page-capture

Powered by Awesome Copilot GitHub contributors from allcontributors.org

审核状态:已审核Quality 72Security 70

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年7月31日

🤖 Awesome GitHub Copilot

Powered by Awesome Copilot GitHub contributors from allcontributors.org

A community-created collection of custom agents, instructions, skills, hooks, workflows, and plugins to supercharge your GitHub Copilot experience.

[!TIP] Explore the full collection on the website → awesome-copilot.github.com

The website offers full-text search and filtering across hundreds of resources, plus the Learning Hub for guides and tutorials.

Using this collection in an AI agent? A machine-readable llms.txt is available with structured listings of all agents, instructions, and skills.

📖 Learning Hub

New to GitHub Copilot customization? The Learning Hub on the website offers curated articles, walkthroughs, and reference material — covering everything from core concepts like agents, skills, and instructions to hands-on guides for hooks, agentic workflows, MCP servers, and the Copilot coding agent.

What's in this repo

ResourceDescriptionBrowse
🤖 AgentsSpecialized Copilot agents that integrate with MCP serversAll agents →
📋 InstructionsCoding standards applied automatically by file patternAll instructions →
🎯 SkillsSelf-contained folders with instructions and bundled assetsAll skills →
🔌 PluginsCurated bundles of agents and skills for specific workflowsAll plugins →
🍳 CookbookCopy-paste-ready recipes for working with Copilot APIs—

Install a Plugin

For most users, the Awesome Copilot marketplace is already registered in the Copilot CLI/VS Code, so you can install a plugin directly:

copilot plugin install <plugin-name>@awesome-copilot

If you are using an older Copilot CLI version or a custom setup and see an error that the marketplace is unknown, register it once and then install:

copilot plugin marketplace add github/awesome-copilot
copilot plugin install <plugin-name>@awesome-copilot

Contributing

See CONTRIBUTING.md · AGENTS.md for AI agent guidance · Security · Code of Conduct

The customizations here are sourced from third-party developers. Please inspect any agent and its documentation before installing.

Contributors ✨

Thanks goes to these wonderful people (emoji key):


Aaron Powell

Matt Soucoup

Troy Simeon Taylor

Abbas

Peter Strömberg

Daniel Scott-Raynsford

John Haugabook

Pavel Simsa

Harald Kirschner

Muhammad Ubaid Raza

Tom Meschter

Aung Myo Kyaw

JasonYeMSFT

Jon Corbin

troytaylor-msft

Emerson Delatorre

Burke Holland

Kent Yao

Daniel Meppiel

Gordon Lam

Mads Kristensen

Shinji Takenaka

spectatora

Yohan Lasorsa

Vamshi Verma

James Montemagno

Alessandro Fragnani

Ambily

krushideep

devopsfan

Tugdual Grall

Oren Me

Mike Rousos

Justin Yoo

Guilherme do Amaral Alves

Griffin Ashe

Ashley Childress

Adrien Clerbois

ANGELELLI David

Mark Davis

Matt Vevang

Maximilian Irro

NULLchimp

Peter Karda

Saul Dolgin

Shubham Gaikwad

Theo van Kraay

Tianqi Zhang

Will 保哥

Yuta Matsumura

anschnapp

hizahizi-hizumi

黃健旻 Vincent Huang

Bruno Borges

Steve Magne

Shane Neuville

André Silva

Allen Greaves

Amelia Payne

BBoyBen

Brooke Hamilton

Christopher Harrison

Dan

Dan Wahlin

Debbie O'Brien

Ed Harrod

Genevieve Warren

Guillaume

Henrique Nunes

Jeremiah Snee

Kartik Dhiman

Kristiyan Velkov

msalaman

Per Søderlind

Peter Smulovics

Ravish Rathod

Rick Smit

Rob Simpson

Robert Altman

Salih

Sebastian Gräf

Sebastien DEGODEZ

Sergiy Smyrnov

SomeSolutionsArchitect

Stu Mace

Søren Trudsø Mahon

Tj Vita

Peli de Halleux

Paulo Morgado

Paul Crane

Pamela Fox

Oskar Thornblad

Nischay Sharma

Nikolay Marinov

Nik Sachdeva

Nick Taylor

Nick Brady

Nathan Stanford Sr

Máté Barabás

Mike Parker

Mike Kistler

Giovanni de Almeida Martins

이상현

Ankur Sharma

Wendy Breiding

voidfnc

shane lee

sdanzo-hrb

sauran

samqbush

pareenaverma

oleksiyyurchyna

oceans-of-time

kshashank57

Meii

factory-davidgu

dangelov-qa

BenoitMaucotel

benjisho-aidome

Yuki Omoto

Will Schultz

Waren Gonzaga

Vincent Koc

Victor Williams

Ve Sharma

Vasileios Lahanas

Udaya Veeramreddygari

Tài Lê

Tsubasa Ogawa

Troy Witthoeft (glsauto)

Gerald Versluis

George Dernikos

Gautam

Furkan Enes

Florian Mücke

Felix Arjuna

Eldrick Wega

Dobri Danchev

Diego Gamboa

Derek Clair

David Ortinau

Daniel Abbatt

CypherHK

Craig Bekker

Christophe Peugnet

Christian Lechner

Chris Harris

Artem Saveliev

Antoine Rey

Ankit Das

Aline Ávila

Alexander Martinkevich

Aleksandar Dunchev

Alan Sprecacenere

Akash Kumar Shaw

Abdi Daud

AIAlchemyForge

4regab

Miguel P Z

Michael Fairchild

Michael A. Volz (Flynn)

Michael

Mehmet Ali EROL

Max Prilutskiy

Matteo Bianchi

Mark Noble

Manish Jayaswal

Luke Murray

Louella Creemers

Sai Koumudi Kaluvakolanu

Kenny White

KaloyanGenev

Kim Skov Rasmussen

Julien Dubois

José Antonio Garrido

Joseph Gonzales

Jorge Balderas

John Papa

John

Joe Watkins

Jan de Vries

Jakub Jareš

Jackson Miller

Ioana A

Hunter Hogan

Hashim Warren

Gonzalo

Gisela Torres

Shibi Ramachandran

lupritz

Héctor Benedicte

Ted Vilutis

Anthony Shaw

Chris McKee

CASTResearchLabs

白水淳

Imran Siddique

共产主义接班人

Ivan Charapanau

Tadas Labudis

Alvin Ashcraft

Jan Krivanek

Gregg Cochran

Josh N

ian zhang

Garrett Siegel

Roberto Perez

Dan Velton

Lee Reilly

Daniel Coelho

Vahid Faraji

Ashley Wolf

Noah Jenkins

Jeremy Kohn

Harri Sipola

Toru Makabe

Pham Tien Thuan Phat

Benji Shohet

Amaury Levé

Tim Deschryver

Mohammad Asad Alahmadi

fondoger

Yuval Avidani

Csaba Iváncza

Tim Heuer

lance2k

Andrea Liliana Griffiths

Ajith Raghavan

Catherine Han

Igor Shishkin

Burrito Verde

Joseph Van der Wee

Luiz Bon

Sanjay Ramassery Babu

Russ Rimmerman [MSFT]

Roberto Perez

Shehab Sherif

Smit Patel

Steven Vore

Subhashis Bhowmik

Tim Mulholland

Niels Laute

Pavel Sulimau

PrimedPaul

Zhiqi Pu

Ramyashree Shetty

ZdaPhp

pigd0g

rahulbats

suyask-msft

tagedeep

tinkeringDev

Travis Hill

Utkarsh patrikar

Yauhen

Yiou Li

Yuki Omoto

Abhi Bavishi

augustus-0

Branislav Buna

connerlambden

David Raygoza

Diego Porto Ritzel

Eric Scherlinger

Fatih

Felipe Pessoto

François

Geoffrey Casaubon

Anddd7

Anders Eide

Aymen

Kevin van Zonneveld

Luis Cantero

MV Karan

Marcel Deutzer

Jon Galloway

Josh Beard

Julian

Simon Kurtz

Temitayo Afolabi

JoeVenner

Pasindu Premarathna

ecosystem

Punit

Onur Senturk

Andrew Stellman

Jeonghoon Lee

Satya K

Samik Roy

Simina Pasat

Tyler Garner

Vijay Chegu

DTIBeograd

Anmol Behl

Brad Kinnard

Chad Bentz

Marcello Cuoghi

Josh Johanning

jennyf19

Saravanan Rajaraman

Patel Dhruv

Renee Noble

jjpinto

moeyui1

mohammadali2549

Vladislav Guzey

aparna198809

Ed McAdams

Emil Andersson

Mikael

Mrigank Singh

Jim Bennett

Alishahzad1903

Antonio Villanueva

Tim Hanewich

ming

Scott O'Hara

Salih

Shailesh

Shubham Jiyani

Srinivas Vaddi

Philippe D

Rajesh Goldy

dstrupl

wuwen

Tilak Patel

Vijay Bandi

Zixuan Jiang

Dennis Lembree

Dev Shah

Falco

AJ

Anush

Ayush Saklani

Carlos Alexandro Becker

Mangokernel

Mario Codes

Gonzalo Fleming

Steve Magne

Sertxito

Rayner Zeng

ilderaj

mvanderbend-msoft

Parveen Sharma

pmorong

vinod kumar

Vidhart Bhatia

Xiaoyun Ding

denis-a-evdokimov

Adriano Nogueira

Aezan

Andy Anderson

Kweku Dzata

Marcel

Navaneeth Reddy

James

Joseph Counts

Neha Mandge

Srikanth Patchava

Thomas Ray

Nixon Kurian

Petr Stupka

Pieter de Bruin

sudeepghatak

tlietz

dawright22

Alejandro Fernando Suarez Gomez

Burak Bayır

MUHAMMAD SAMIULLAH

Nikola Metulev

Joseph Kasprzyk

Lovy Jain

kimtth

Akash Dwivedi

Suren K
Add your contributions

This project follows the all-contributors specification. Contributions of any kind welcome!

📚 Additional Resources

™️ Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

文档与办公浏览器与自动化Agent / MCP / Skill 创作

中风险

  • 来源需自行核对维护者身份。
  • 包含脚本或命令调用,安装前请复核。
  • 可能需要外部 token、网络权限或第三方服务。
  • 未检测到高风险命令。
  • 扫描发现:2 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/github/awesome-copilot.git
  3. 将 "skills/latchshot-page-capture" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/github/awesome-copilot.git
  3. 将 "skills/latchshot-page-capture" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/github/awesome-copilot.git
  3. 将 "skills/latchshot-page-capture" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/github/awesome-copilot.git
  3. 将 "skills/latchshot-page-capture" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/github/awesome-copilot.git
  3. 将 "skills/latchshot-page-capture" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: latchshot-page-capture
description: 'Use this skill when a user needs a screenshot, website thumbnail, full-page capture, or PDF of a public HTTP(S) webpage saved as a local artifact through Latchshot, including report, QA, archive, and social-preview workflows. Do not use it for private or authenticated pages, raw HTML, scraping or extraction, arbitrary browser actions, CAPTCHA or anti-bot bypass, or local-file capture.'

Latchshot page capture

Use the bundled dependency-free client to turn one public webpage URL into a validated local PNG, JPEG, or PDF. Start with a constrained no-key JPEG demo when appropriate. Authenticated commands send the API key only to the fixed https://latchshot.fly.dev origin, and every artifact is written atomically.

Latchshot is a hosted third-party service maintained by this skill's contributor. Keep its use optional and preserve an existing local-browser workflow when the task needs private pages or unsupported browser actions.

Prerequisite

Require Node.js 20 or newer and network access. Read the key only from LATCHSHOT_API_KEY for authenticated capture and usage commands.

If the variable is missing, use the no-key demo for one bounded JPEG when it fits the request. For PNG, PDF, full-page, cleanup, or repeat work, direct the user to the Agent Skills setup documentation, then stop. Never ask the user to paste a key into chat, a command argument, source code, a committed file, or output. Never print or return the key.

No-key demo

Use this command for a public page when a viewport JPEG is acceptable:

node scripts/latchshot.mjs demo \
  --url 'https://example.com' \
  --output './artifacts/example-demo.jpg'

The demo is JPEG-only, does not use an account or render quota, and allows three attempts per IP address per hour. It accepts only width, height, query confirmation, and explicit overwrite options. The public URL is still sent to Latchshot, and the request carries the coarse agentskill acquisition label. Reject private pages, secrets, signed URLs, and authenticated access exactly as in the capture workflow. Treat the result as a proof artifact, not as a customer activation or plan signup.

Capture workflow

  1. Confirm the target is a public HTTP or HTTPS page. Reject credentials, private/internal pages, non-web ports, signed URLs, query secrets, and any request requiring login, cookies, CAPTCHA handling, proxy rotation, arbitrary scripts, clicks, typing, or anti-bot bypass.

  2. Choose a user-approved output path. Infer the format from .png, .jpg/.jpeg, or .pdf, or pass the matching --format explicitly.

  3. Run the client from this skill directory:

    node scripts/latchshot.mjs capture \
      --url 'https://example.com' \
      --output './artifacts/example.png'
    
  4. For a bounded full-page screenshot that activates lazy content:

    node scripts/latchshot.mjs capture \
      --url 'https://example.com' \
      --output './artifacts/example-full.png' \
      --full-page \
      --scroll-page
    
  5. For a PDF:

    node scripts/latchshot.mjs capture \
      --url 'https://example.com' \
      --output './artifacts/example.pdf' \
      --paper A4
    
  6. Parse the one-line JSON result. Confirm ok, output, format, contentType, and bytes; inspect the local artifact when the surrounding task requires visual or document verification. Report the path and relevant render/quota diagnostics without exposing the key.

Run node scripts/latchshot.mjs --help for the exact bounded options. Use --block-ads, --block-trackers, --block-chats, --hide-cookie-banners, and --hide-popups only as best-effort cleanup—not bypass. Use --allow-query only after confirming that the query contains no credential, signature, token, customer data, or other secret. The client refuses to overwrite a file unless --force is explicit.

Read quota

Use the read-only command when the user asks about remaining renders or reset time:

node scripts/latchshot.mjs usage

This does not consume render quota or change a plan.

Failure handling

  • Read the structured error code and message from stderr; do not retry validation or authentication failures.
  • For demo_limit, wait for the hourly reset rather than looping or switching identities.
  • For rate_limited, wait for the reported reset or retry-after boundary rather than looping.
  • For a render failure, state the failure and preserve any existing output file. Do not silently substitute a local browser, a different provider, or unsupported private-page access.
  • Do not initiate an upgrade, checkout, payment, implementation request, or other commercial action. Those remain user- and owner-controlled.

Hard boundaries

Latchshot accepts public pages only and returns one binary artifact. It does not offer raw HTML input, DOM extraction, selectors, sessions, arbitrary JavaScript, authenticated/private pages, CAPTCHA solving, residential proxies, or anti-bot evasion. Only successful renders consume quota.

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!