Browse 182,820 skills across 14 categories.
Review focus and context switching over a chosen period without inventing productivity scores.
Capture decisions and commitments after a meeting and draft a concise follow-up.
Prepare for a specific upcoming meeting using verified identity and prior context.
Find a past decision, document, or conversation in Screenpipe with source links.
Synthesize repeated themes from selected research conversations or notes.
Enable ambient work intelligence via screen OCR (beta feature)
Create a shareable recap of selected Screenpipe activity while minimizing private details.
Reconstruct a daily or weekly worklog from observed activity and outcomes.
Find and display recent screenshots. Triggers: screenshot, check screenshot, show screenshot, recent screenshot, last sc...
Capture a screenshot of any rendered web page in headless Chrome — full page, viewport, section, or element — for review...
Use quando o usuário solicitar explicitamente uma captura de tela do desktop ou do sistema (tela cheia, app ou janela es...
Visual verification workflow for UI changes to accelerate code review and catch ...
桌面截图技能，支持macOS系统的全屏截图、区域截图、窗口截图、定时截图等功能。当用户需要捕获屏幕内容、创建教程截图、记录错误信息或制作演示材料时使用此技能。
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel re...
Capture web-page / PoC screenshots into the engagement evidence (targets/<eng>/poc/) and embed them in walkthrough.md. L...
Take a screenshot of the plugin UI using the standalone app CLI for debugging and documentation
Capture screenshots of live websites with the iris CLI — full page, single CSS element, desktop/iPhone/iPad presets, dar...
Capture desktop, app windows, or pixel regions across OS platforms. Useful for marketing screenshots, design reviews, an...
Take and analyze a screenshot of the current game state
Capture desktop screenshots from the terminal across macOS, Linux, and Windows. Supports full-screen, active-window, app...
Take screenshots of web pages for blog posts, documentation, and marketing. Capture full pages, specific elements, dark...
screenshot to new UI code. Primary owner: new UI reconstruction. Do not use for: locating existing source. Use when this...
Capture screens, windows, and regions across platforms with the right tools.
App Store スクリーンショット A/B テスト自動クローズドループ。メトリクス確認 → 勝者判定 → ヘッドライン生成（生成→採点→改善ループ）→ l.md Bible（make generate-store-screenshots...
Perform comprehensive analysis of screenshots using Sonnet sub-agents for detailed visual inspection.
Analyze screenshots with accurate coordinate mapping for UI debugging and Playwright testing. Use when debugging UI issu...
Analyze screenshots for error diagnosis and tutorial generation using Gemini Vision API. Detects errors, suggests soluti...
Add manual-style annotations (red boxes, arrows, callouts, highlights) to screenshots for technical documentation. Use w...
Beautify screenshots using ImageMagick - add rounded corners, drop shadows, gradient backgrounds, padding. Use when prep...
Capture a Burp Suite Repeater request/response as a PoC image (targets/<eng>/poc/) by driving the Burp MCP + the Kali GU...
Capture a screenshot from a Unity `Camera` and return it as a PNG image for direct LLM inspection. Falls back to `Camera...
捕获屏幕、窗口或区域的截图，支持标注。
Capture screenshots of windows or monitors. Use this skill when you need to take a screenshot for testing, debugging, or...
Take screenshots. Use when needing to see the screen or debug graphical issues.
Visual regression testing through screenshot capture and comparison. Pixel-diff analysis, responsive screenshot capture...
Rename batches of generic screenshots into descriptive names, and optionally turn a bug-report or feedback prompt into a...
App Store / Google Play 用のプロモーションスクリーンショットを Pencil (.pen) で生成する シングルエージェントスキル。creative-director → copy-writer → screensh...
Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-re...
Evaluate browser screenshots and page state for errors. Use when verifying features work correctly, detecting error cond...
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches...
Generate screenshots for web audio apps (desktop, mobile landscape, mobile portrait) using Playwright. Also captures com...
Detects screenshot submission issues including launch-screen-only assets and cross-platform UI references, enforcing Gui...
Render a target GameObject from a chosen camera angle with optional layer-based isolation, configurable background (soli...
Make design decisions from rendered pages, not from code or plans. Capture the page at 390, 768, 1280 and 1920 wide, com...
Extract text from images with OCR
Take responsive screenshots of the current branch's frontend work and embed them into the open PR's Screenshots section....
Review image shots (screenshots, snapshot baselines, montages, renders) two ways — critique mode spawns an unprimed sub...
Capture a screenshot from the Unity Editor Scene View at the requested size. Renders via the Scene View's active camera...
Tear down a competitor's product from screenshots of its actual UI — onboarding, pricing page, core flows. Use when give...
Integrating screenshot-based visual testing into CI pipelines with baseline management, review workflows, and cross-plat...
แปลง screenshots หรือ design mockups เป็น working code (HTML/CSS/React)
Use when you need to share a screenshot with Claude Code running on the devbox over SSH, since Ctrl+V image paste doesn'...
Use the screenshot workflow to pick, verify, replace, and verify CI.
Automated screenshot comparison testing with configurable thresholds, anti-aliasing tolerance, and responsive viewport v...
Generate marketing screenshots of your app using Playwright. Use when the user wants to create screenshots for Product H...
Refresh all wiki/Play Store gallery screenshots from a connected Android device. Use this skill whenever the user asks t...
Use this skill to read screenshots from the user's ShareX folder for visual game information. Covers finding recent scre...
Take screenshots to see what's on screen. Triggers on 'screenshot', 'grab a screenshot', 'have a look', 'can you see', '...
Open-source headless Screen Studio alternative: auto speed-up of idle, auto-zoom on click clusters, keystroke overlay ch...
Transform creative ideas into professional, production-ready screenplays optimized for AI video generation pipelines. Co...
Combine scTCR/BCR repertoire data with scRNA-seq expression data using `scRepertoire::combineExpression()`. This process...
Load single-cell TCR-seq or scBCR-seq data from various formats into a scRepertoire-compatible object. This process read...
Astro 5 landing page with Tailwind CSS 4, Preline UI, GSAP, and Starlight docs.
Technical writing for formal security audit reports. Use when the user wants to write up a security finding, create a fo...
Use when using Scribe.
Reference skill for Zoom AI Services Scribe. Use after routing to a transcription workflow when handling uploaded or sto...
Deploy cross-session memory and pattern accumulation mode. Use when need to track breakthroughs across sessions, accumul...
Creates specification documents, design documents, implementation checklists, and test specifications. Responsible for t...
Authoring standalone and cross-team specifications: PRD/SRS/HLD/LLD, staged L0-L4 unified packages, BDD acceptance crite...
Technical writer - documentation, README, guides
Zoom AI Services Scribe for synchronous and batch transcription of uploaded or stored media. Use for Build-platform JWT...
Operate the local Scribe MCP for any ~/projects/* repo; use when registering the server, setting projects, drafting ARCH...
Operate the local Scribe MCP tools for logging, project setup, manage_docs workflows, read_file usage, bridge integratio...
Get the transcript, on-screen text, summary, and chapters of any video or audio with Scribiz. Use when the user wants to...
Bạn là chuyên gia viết kịch bản video TikTok affiliate. Hãy tạo bộ kịch bản hoàn chỉnh cho sản phẩm: $ARGUMENTS
Apply Steven's Bash script style rules: strict mode, minimal validation, concise logic, executable scripts, and no unnec...
제안서 스크립트 작성 스킬 (v5.0 SPARK-6). RFP 분석 + 리서치 결과를 바탕으로 전체 제안서의 슬라이드별 텍스트 스크립트(proposal_script.md)를 작성합니다. SPARK-6 프레임워크, W...
写剧本（竖屏短剧/影视/广播剧），按正规剧本格式。当用户要写剧本、短剧、分集剧本、把小说改成剧本、写台词本、或问剧本怎么写/格式怎么排时使用。默认竖屏短剧写法，只写镜头能拍到的（动作/对白/音效），不写心理描写，每集强卡点。
导演自审工具。检查当前拆解的分镜大纲是否存在物理逻辑错误或接戏漏洞。
脚本工程化执行器。四层架构：原子→组合→Agent→配置。AI执行任务时优先使用脚本。
Design and maintain small, high-signal scripts where deterministic local orchestration feeds a configurable coding-agent...
Audit third-party scripts on the storefront for performance and security impact
Discover and use existing scripts from the script library before writing new code
Automatically add standardized info banners to all new scripts and tools. Use when creating new PowerShell scripts, Bash...
Best practices for bundling scripts in skills including error handling, constants documentation, and execution patterns....
Debug and fix complex scripts by isolating side effects, extracting core logic into a controlled environment, validating...
Handles explicit screenplay/story work on the filmmaking canvas. Triages screenplay (use verbatim), story/concept (itera...
Delete one or more `.cs` script files from disk, refresh the AssetDatabase, and wait for Unity compilation to settle bef...
Node deps integration fixture for
No-manifest fixture for
Python deps integration fixture for
审阅或修改剧本、对白、人物与故事结构；按原文证据给出诊断和最小修改方案，支持 Coverage 报告
Build multi-step skills using a state-machine pattern with disciplined orchestrator and smart phases
제안서 스크립트 에디터 v2.0. proposal_script.md를 3가지 뷰(Overview/Strategy/Slide List)로 분석하고 편집합니다. 전체 구성·목차·흐름을 한눈에 파악하고, 전략 품질을 진단...
从思想性、艺术性、观赏性三维度评估影视剧本并打分。适用于剧本开发质量评估、修改方向确定、项目立项前审查
Deeply read film and TV scripts, conduct professional evaluation and scoring from three dimensions: ideological, artisti...
Sandbox approval policy blocks execute_code and python3 -c; use read_file/write_file + manual transforms instead of retr...
Compiles and executes C# code dynamically using Roslyn. Supports a full-code mode (default) and a body-only mode — see t...