motion-video
Build a marketing or explainer video that is mostly RENDERED scenes - motion graphics, mocked or rebuilt product UI, data-driven animated charts, brand-matched title design - authored in Remotion and stitched around one real product-capture beat. Use whenever the user wants a marketing video, a brand film, a launch or website hero video, an animated explainer, motion graphics, a video with mocked/idealised UI or animated charts, or says "build the video in Remotion", or needs one film cut to the aspect ratios and UI safe zones each platform wants (Instagram Reels, TikTok, YouTube Shorts, 4:5 feed) for paid ads or organic posts. This is the marketing branch's build engine, the counterpart to demo-video (which films the REAL product to prove it). Not for - a screen recording or product walkthrough of the real app (demo-video), a pitch deck (pitch-deck), a live pitch or its script (pitch-package, pitch-craft), or editing footage that already exists.
pitch-craft
Write or fix any spoken script that has to hit a clock - demo-video voiceovers, deck walkthrough narration, and live pitch speeches. Use whenever the user asks for narration, a voiceover, a timestamp script, a pitch script, a speech that fits N minutes, wants it to "sell like Steve Jobs", or needs an existing script re-synced after a re-record or re-timed to a new slot, or says a script sounds AI-written, robotic, generic, or wants it de-slopped. This is also the engine the demo-video, pitch-deck, and pitch-package skills call for their scripts. Not for - written submission forms or essays (no clock), building deck HTML (pitch-deck), or recording video (demo-video).
pitch-deck
Build a pitch deck as one self-contained HTML file (keyboard and click navigation, staggered slide-entry animations, a persistent brand mark, cited numbers with real links), write its timed walkthrough narration, and optionally record the walkthrough as video parts that stitch around a demo film. Use whenever the user asks for a pitch deck, demo-day / hackathon / investor slides, a slide walkthrough video, deck narration, or wants an existing HTML deck polished, re-branded, or recorded. Not for - .pptx slide files (use a pptx skill), the product demo film itself (demo-video), or deciding overall pitch strategy and audience framing (pitch-package).
pitch-package
The step-back skill for pitching as a person - given an audience (hackathon judges, VCs, investors, customers) and a time slot, it budgets the slot, decides what to build or reuse (deck, demo video, live speech), and orchestrates the pitch-deck, demo-video, and pitch-craft skills into one rehearsed package with a stitch plan, Q&A prep, and a day-of checklist. Use whenever the user says they need to pitch, present, or demo at a hackathon or demo day, to investors or a customer, mentions an N-minute slot, or asks to "prepare the whole pitch" end to end. Not for - a single artifact in isolation (call pitch-deck, demo-video, or pitch-craft directly) or written-only submission forms.
project-showcase
Add a filterable, project-based showcase catalog to a personal or company site — the pattern where every project is one card that opens a detail page, and visitors filter by the KIND of project (a launched product vs a hackathon build vs an R&D experiment). Use when someone wants to build a portfolio / projects / "things I've built" page, a showcase grid with filters, or wants to add one new project to an existing showcase and isn't sure how to categorize or present it. Interviews you about your stack and what you already have before writing anything.
scribe
Turn meeting recordings into notes with an unbroken chain of custody from audio to claim. Use when the user has recordings or audio to transcribe or summarize, or when an existing transcript or auto-summary reads as garbled or untrustworthy.
secure-by-design
Run an enterprise security review of a system design or existing code before it ships. Use when the user says "security review", "secure by design", "threat model this", "is this design secure", "what security controls do we need", "audit this for security", "harden this system", "RBAC design", "review my auth", or "enterprise security checklist". Classifies assets and trust boundaries FIRST, then recommends only the controls that fit — grounded in battle-tested patterns. Right-sizes for team scale (bones now, ceremony later). Do NOT use for writing a specific exploit, penetration-testing a system the user does not own, or general non-security code review.
self-improving-systems
Decide whether your agent actually needs persistent memory, feedback loops, or closed-loop learning, then design the smallest thing that pays for itself. Use when the user says "add memory", "give my agent context management", "make my agent learn", "self-improving / closed-loop", "Reflexion / mem0 / Letta / MemGPT", "AriGraph", "agent memory architecture", "long-term memory for chatbot", "why does my agent keep forgetting / making the same mistake", "fine-tune from agent traces", or asks for a memory schema / experience store / reward model. Filters ruthlessly — most teams want a state cache, not memory + learning. Default position is scratchpad-only with a stateless agent shipped first.
streak
Universal challenge tracker with flexible cadence, intelligent insights, and cross-challenge learning detection. Use when user wants to track any personal challenge - learning, habits, building, fitness, creative, or custom. Supports daily, weekly, or N-day check-ins with type-adaptive preferences, backlog, and context files.
uat-testing
End-to-end User Acceptance Testing for web applications. Analyzes branch changes and specs to generate exhaustive test cases, sets up the local environment, executes tests via Playwright browser automation, and produces a pass/fail results report with screenshots and fix documentation. Use when the user says "run UAT", "test this feature", "UAT testing", "acceptance test", "test my branch", "generate test cases", or wants to verify a feature branch against its spec before merge.
mvp-launch
Web app MVP launch checklist knowledge. Auto-triggered when conversation involves "launch readiness", "MVP checklist", "production ready", "go live", or pre-launch verification. Provides the 10-point criteria for what counts as "done" in each area. Based on "Realistic MVP Launch Checklist (from building 30+ apps)".
product-management
This skill should be used when the user asks to "analyze my product", "research competitors", "find feature gaps", "create feature request", "prioritize backlog", "generate PRD", "plan roadmap", "what should we build next", "competitive analysis", "gap analysis", "sync issues", or mentions product management workflows. Provides AI-native PM capabilities for startups with signal-based feature tracking, the WINNING prioritization filter, and GitHub Issues integration with deduplication.
excalidraw
Generate architecture diagrams as .excalidraw files from codebase analysis, with optional PNG/SVG export. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, generate excalidraw files, export excalidraw diagrams to PNG or SVG, or convert .excalidraw files to image formats.
aip
Google API Improvement Proposals (AIP) reference. Use BEFORE designing or reviewing APIs, protobuf definitions, or any work involving Google API design standards. Fetches relevant AIP rules from https://google.aip.dev for the task at hand.
gh-cli
GitHub CLI (gh) conventions and the inline PR review recipe. Use when working with GitHub repositories, PRs, issues, actions, `gh api`, or any GitHub operations from the command line.
git-commit
>-
neovim
Interact with the user's running Neovim instance via RPC. Use this skill when you need to execute Lua or Vimscript inside Neovim, query buffer state, send commands, or interact with the Neovim runtime in any way. Triggers when the user asks about their current Neovim session, wants to run something inside Neovim, or when you need to inspect Neovim state (buffers, windows, options, LSP, etc.). Also use when running inside a Neovim terminal and needing to communicate with the parent editor.
gh-pr
>-
nix-install
Install Nix in the Claude Code web sandbox (the cloud environment) as a general-purpose package installer, then install packages from the Nix binary cache with no GitHub access. Use whenever a web session needs a tool that isn't preinstalled and isn't in a language registry (npm/pypi/crates/go) — Neovim, ripgrep, a compiler, anything in nixpkgs. Installs nix-bin via apt, configures single-user mode, and installs packages via nix-env against the nixpkgs channel tarball. Web-sandbox only.
nvim-install
Install Neovim and stand up the nvim-fredrik config in the Claude Code web sandbox (the cloud environment), where no Neovim exists. Use this before testing any Neovim config change in a web session, e.g. checking out a PR branch that touches nvim-fredrik and observing its runtime behavior. Installs Neovim via Nix from the binary cache with no GitHub access, wires the repo's config into place, launches Neovim headless with a listen socket, and exports $NVIM so the `neovim` RPC skill can drive it. Web-sandbox only.
codebase-audit
>
plan-interview
Before creating a plan, interview the user
pr-style
>-
proof
Provide proof to your claim(s)
self-review
>-
nvim-config
>
remotion-ads
Professional video ad creation with Remotion — Instagram Reels (9:16), website explainers (16:9), and carousels (4:5). Use when creating video ads, animated social content, or educational explainer videos. Includes ElevenLabs voiceover with word-level captions, AI icon generation, background music, ad copywriting frameworks, and Meta campaign management. Also use when the user provides a URL and wants to create a video for that page.
ceo-skill
Intelligent project management dashboard - view all projects status, priorities, and todos from a CEO perspective
share-skill
Automatically share skills, migrate local skills to code repositories, open source skills, skill version management, configure git remote
skill-i18n
Translate SKILL.md and README.md files into multiple languages for sharing skills internationally
skill-permissions
Skill permission analysis, one-time authorization, analyze skill permissions, batch authorization
port-allocator
Automatically allocate and manage development server ports, avoiding port conflicts between multiple Claude Code instances
lark-mcp
飞书/Lark 官方 MCP 集成。支持发送消息、创建群组、操作多维表格（Bitable）、导入/搜索文档、知识库查询。触发词：飞书、Feishu、Lark、多维表格、bitable、飞书文档、飞书群。
repo2skill
Convert GitHub/GitLab/Gitee repositories into comprehensive OpenCode Skills using embedded LLM calls with multiple mirrors and rate limit handling
design-tokens
Expert in design tokens using the DTCG specification. Use this skill when users ask about design tokens, DTCG format, token validation, formatting, transformation, color spaces (sRGB, Display P3, OKLCH), references and aliasing, resolvers, theming with modifiers/contexts, multi-platform design systems, accessibility, or working with tools like jq, jsonata, and terrazzo. Helps with token file creation, resolver configuration, structure, naming conventions, and best practices.
brainstorming
在构建新功能、新组件或新系统之前，通过对话把想法收敛成一份设计规格。当用户描述想构建的东西且存在设计决策时使用；不用于 bug 修复、配置变更或实现路径已经显而易见的任务。
claude-skill
Delegate a task to the Claude Code CLI, typically a headless `claude -p` run. Use when the user wants the work executed through Claude Code rather than answered inline.
code-simplifier
Simplify existing code for clarity and maintainability without changing behavior. Use when asked to clean up or simplify code, especially recent changes.
github-fix-issue
Research and fix a GitHub issue in the current repository. Use when the user asks to fix, investigate, or work on an issue by number or URL.
github-review-pr
Review a GitHub pull request with evidence-backed, multi-angle analysis and false-positive filtering. Use when the user asks to review, inspect, or check a pull request by number or URL. Not for local uncommitted changes.
gpt-image-skill
Generate or edit images through the OpenAI GPT Image API. Use only when the user names OpenAI, GPT Image, or a `gpt-image-*` model for image work; for image requests with no provider named, use the default image skill instead.
grill-me
仅当用户显式调用 `$grill-me`，或明确要求"追问我""挑战这个方案""拷打这个设计"时使用。通过高强度逐问逐答检验方案，并同步沉淀术语表和 ADR。不要因普通设计讨论自动触发。
handoff
仅当用户显式调用 `$handoff`，或明确要求生成会话交接文档时使用。将当前对话压缩为脱敏、可执行的交接文档，供下一个 agent 接续工作；不要自动触发。
minimax-image-skill
Generate images through the MiniMax Image API. Use only when the user names MiniMax or a MiniMax image model such as `image-01` or `image-01-live`; for image requests with no provider named, use the default image skill instead.
nanobanana-skill
Generate, edit, or composite images with Gemini / Nanobanana models through the bundled CLI wrapper. This is the default image skill — use it for any image generation or editing request that does not name a different provider.
youtube-transcribe-skill
Extract subtitles or a transcript from a YouTube URL and save normalized timestamped text locally. Use when the user wants the spoken content of a YouTube video as text.
deep-research
把一个调研目标拆成可并行的子目标，用 Codex CLI 子进程分头取证，再聚合核验成一份带来源的报告。用于单轮检索撑不住、需要多个来源分头深挖的调研。
better-auth-python
Better Auth JWT verification for Python/FastAPI backends. Use when integrating Python APIs with a Better Auth TypeScript server via JWT tokens. Covers JWKS verification, FastAPI dependencies, SQLModel/SQLAlchemy integration, and protected routes.
better-auth-ts
Better Auth TypeScript/JavaScript authentication library. Use when implementing auth in Next.js, React, Express, or any TypeScript project. Covers email/password, OAuth, JWT, sessions, 2FA, magic links, social login with Next.js 16 proxy.ts patterns.
chatkit-js
Integrate OpenAI ChatKit React components into Next.js applications. Covers custom API backend configuration, theming, widget embedding, conversation history, and authentication integration.
Page 657 of 1647 · 82342 results