frontend-slides
A skill that builds animation-rich HTML presentations from scratch or converts PowerPoint files to web slides. Useful for anyone turning a deck into a web presentation.
4,248 plugins. 79,851 skills, agents, commands and MCP servers. 99 get Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how →.
A skill that builds animation-rich HTML presentations from scratch or converts PowerPoint files to web slides. Useful for anyone turning a deck into a web presentation.
Google Workspace Admin SDK: Audit logs and usage reports.
Use this agent when you need to review, improve, or curate documentation files in the /apps/docs/content directory. This includes…
Search past session observations and lessons for relevant context. Wrap the `memory_smart_search` and `memory_lesson_recall` MCP…
Looks up guidance in the documentation of an open-source framework for building LLM-powered applications and agents.
Skills for configuring and troubleshooting Turborepo monorepos, covering turbo.json task pipelines, caching, Remote Cache, the turbo CLI, filtering, environment variables and package boundaries.
Clean up merged branches locally and on remote, keeping only main, dev, and gh-pages.
An open-source autonomous agent that researches a topic online and compiles findings into a cited report.
Searches local markdown notes, docs, and wikis on your device using keywords or natural language. Lets Claude Code find notes, retrieve documents, and answer from indexed markdown.
Build or improve an OpenCLI JS adapter using observed site behavior, existing adapters and browser API evidence. For ad-hoc…
Packs an entire code repository into a single AI-friendly file for feeding to language models.
A Claude Code plugin for editing videos from raw footage. You drop footage in a folder, chat with Claude Code, and get a final video back, suited to talking heads, tutorials, travel, interviews, and more. It also includes a skill for building Manim-based mathematical and technical animations.
生成横向翻页网页 PPT(单 HTML 文件),含 WebGL 背景、演讲者视图、观众屏同步、讲稿备注、章节幕封、数据大字报、图片网格等模板。提供两种风格:① "电子杂志 × 电子墨水"(衬线 + 流体背景 + 暖色) ② "瑞士国际主义"(无衬线 +…
Agent-readiness analyst. Explains the Lighthouse Agentic Browsing fraction and audits the accessibility tree for agents,…
Reclaim disk taken by tagged dev artifacts from `./scripts/reload.sh --tag <tag>`. Each tagged build is multi-GB of DerivedData…
Set up, check, change, preview, or report a problem with the claude-hud status line. Use when the user mentions the HUD or status…
بدء تخطيط الملفات بنمط Manus. إنشاء task_plan.md و findings.md و progress.md للمهام المعقدة.
Skills for the MLflow repository that analyze failed GitHub Actions jobs, review pull requests, triage issues, and enforce Python and workflow coding conventions.
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server…
Combines a real-time database with server logic for building multiplayer games and live apps.
Gives writers and publishers ready-made AI helpers for article work: adding illustrations, making cover images, turning ideas into knowledge comics, and shrinking images for the web.
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting…
Triage all open PRs with parallel agents, label, group, and review one-by-one
Skills for evaluating and red-teaming LLM apps with Promptfoo. Covers writing and running eval suites, connecting Promptfoo to models and APIs, and running and rerunning redteam security scans.
Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague,…
Explanations of common asynchronous patterns used in tursodb. Involves IOResult, state machines, re-entrancy pitfalls,…
Google cross-vendor agent named for the model it runs — Gemini 4 Argon, Google’s top reasoning model, via…
Write the GitHub release notes for a gpui-kit version in the established style
A toolchain for web projects, aimed to provide functionalities to maintain them. Biome offers formatter and linter, usable via CLI and LSP.
Read-only leaf worker for one bounded ARIS fan-out shard. Never delegates, writes files, or renders verdicts.
Run or manage the SkillOpt-Sleep self-evolution cycle (review past sessions, replay tasks through a selected backend, consolidate…
Lets you control Claude Code sessions remotely from a mobile app, with end-to-end encryption, push notifications and sync across devices. Open source under the MIT license.
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state…
Use this agent when you want a comprehensive code review of changes in the current branch compared to main. This includes…
Manage a single Paradev automation: edit its prompt in $EDITOR, view recent runs, or trigger a one-off run.
Skills for running several coding agents together: an advisor for a second opinion, a committee for root cause analysis and planning, handoffs with full context, help with the Paseo app, and building local plugins.
Bump Skyvern OSS version, build Python and TypeScript SDKs with Fern, and create release PR. Use when releasing a new version or…
Create an AI skill from any source (URL, repo, PDF, video, notebook, etc.)
Scans cloud accounts against security best practices and compliance benchmarks such as CIS.
Adds Magic UI animated React and Next.js components to a project, with guidance on choosing, installing via the shadcn registry, and customizing them. Built for design engineers who want copy-paste effects.
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain,…
Code quality check expert. Reviews code changes against specs and self-fixes issues.
List this machine's Claude Code and Codex subscription accounts, set the default account for new sessions, and move a session to…
Helps you turn an idea into working code by pairing with an AI, using skills for Claude API integration, Claude Code tutorials, skill authoring, and crypto market data or trading APIs.
When you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take…
Gives Claude Code access to a local Screenpipe install, which continuously records screen activity so you can query that history through its REST API, manage scheduled AI automations called pipes, and check the health of the Screenpipe process.
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when…
Content Page Generator. Generate EXACTLY the content slide. REQUIRED inputs: font family, color palette, slide index, slide…
Approve synthesis findings and create implementation tickets from discovery
Skills for building GraalVM native images of Java applications with Gradle or Maven, covering build configuration, CLI options, native tests, and troubleshooting build or runtime issues.
Turn the current project website into a short, polished, shareable launch video using Hyperframes. Use when someone says "/brag",…
Inspect or update Inbox Zero rules and analytics through the public API CLI. Use when tasks involve rules, stats, or API-driven…
Rebuild the object in a reference image as a code-only, procedural Three.js model. Quality-gated, animation-ready, and deliberately token-efficient, reconstruction-by-code, not photogrammetry, mesh extraction, or downloaded art packs.
Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from…
MemOS backend / library implementation sub-agent. Writes code under src/memos/ within the task boundary, strictly TDD, then…
A platform for hosting, sharing and running open-source machine learning models, datasets and demos.
Installs and operates Google NotebookLM through a Python CLI and typed async API, covering notebooks, sources, grounded chat, research, and artifacts. Built for developers and AI agents such as Claude Code.
The daily routine of a daily.dev for Startups company. Sets up a daily scheduled run, then each day reports how the company page…
Compare two or more options side by side, recommend one, and let the reader pick in the page
Build HTML email templates with React components, render them to HTML, add a visual email editor to an application, and send them with Resend.
Chat SDK renderer for json-render that turns JSON specs into native chat cards (Block Kit on Slack, Adaptive Cards on Teams, and…
Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes.
Skills for evaluating AI agents, RAG pipelines and LLM apps with DeepEval metrics, and for tracing those apps with OpenTelemetry or DeepEval tracing into Confident AI.
GEO specialist analyzing AI search visibility: citability scoring, AI crawler access, llms.txt compliance, and brand mention…
A skill that removes predictable AI writing patterns from prose. Use it when drafting, editing, or reviewing text to make it read less like machine-generated writing.
This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric…
Periodic consolidation pass — fold narrow agent-created skills into class-level umbrellas. Proposes intents only, never writes to…
Browse all 150 shots in the Gallery · Watch the Showcase.
Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia()…
Command-line tool for working with Lark and Feishu from a terminal, with skills for approvals, attendance, Base tables and Miaoda apps. Usable by people and AI agents.
Agent-native memory for OpenClaw that structures memory from agent trace, execution history, decisions, tool calls, and…
An MCP server and skill that lets an AI assistant publish to Xiaohongshu (小红书), either as an image-and-text post or as a long-form article, using content you supply or extracted from a web page URL.
Operate FrontendExtension (FE) resources in frontend-forge: create, update, rebuild, inspect package artifacts, download…
Sweep the googleapis/mcp-toolbox docs for broken and non-canonical links, report each finding with its cause, and apply the safe…
Skills for building durable background tasks, scheduled jobs, and AI chat agents with Trigger.dev. Covers task design, span timeline events, error API testing, and Drizzle ORM work in the Trigger.dev repo.
Hand off a model from Blender (via BlenderMCP) into Unity (via MCP for Unity) — export the current Blender model, import it…
A skill that writes optimized prompts for AI tools such as LLMs, Cursor, Midjourney, and image or video generators. It activates only when you explicitly ask to write, fix, improve, or adapt a prompt for a specific tool.
Use to review code changes with a two-stage process - first checking spec/requirements compliance, then code quality. Works on…
A desktop workbench for Claude Code that runs many sessions side by side, with global search, branch and worktree launch, diff review, a built-in browser preview, and graphical approval of permissions. You can also choose the model and generate images from within it.
把用户提供的素材(网页 URL / PDF / DOCX / Markdown / 纯文本 / 截图 / 粘贴材料)编辑、设计成一篇美丽的、可离线打开和分享的**单文件 HTML 网页文章**。基于 reacticle 组件协议:不手写裸…
Direct actions on one Orchestrator session or PR: stop or interrupt, resume, merge a PR, start a review, screenshot a session's…
Installs or uninstalls memU, a personal memory system shared across agents, by identifying the host agent and wiring in recording and memory injection. Useful for Claude Code users who want their agents to remember across sessions.
Direct and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g. Impasto Oil…
Style React fast with 100% parity on React Native, an optional UI kit, and optimizing compiler.
Use when an agent needs to build or operate the embedded KrillinAI CLI, choose a supported command, or interpret its JSON,…
PHP Static Analysis Tool - discover bugs in your code without running it!