熱門 Agent Skills
2094 個技能Create AI avatar and talking head videos via the inference.sh CLI, with models such as P-Video-Avatar, OmniHuman, Fabric, and PixVerse, plus audio options including Inworld TTS-2, ElevenLabs, and Kokoro.
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via the inference.sh CLI.
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via the inference.sh CLI.
Create AI avatar and talking head videos via the inference.sh CLI, with models including P-Video-Avatar, OmniHuman, Fabric, and PixVerse, plus Inworld TTS-2, ElevenLabs, and Kokoro audio.
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via the inference.sh CLI.
Automate Twitter/X posting, engagement, and user management via the inference.sh CLI with apps such as x/post-tweet, x/post-create, x/post-like, x/post-retweet, x/dm-send, and x/user-follow.
Author a HyperFrames slideshow with discrete slides, fragment reveals, branching, hotspot navigation, and presenter mode with speaker notes, or convert an existing page into a deck.
The grill-me skill sharpens a plan or design through relentless questioning.
The grilling skill relentlessly interviews the user about a plan, decision, or idea until a shared understanding is reached.
Ports an existing Remotion (React) composition's source one-way into HyperFrames HTML, only when an explicit Remotion migration is requested.
Anti-slop frontend skill for landing pages, portfolios, and redesigns, using design inference and strict pre-flight checks to ship non-templated interfaces.
Import Figma content into a HyperFrames composition, including rendered assets, brand tokens, components, storyboard sections, and reconstructed motion.
The grill-with-docs skill sharpens a plan or design through relentless questioning while generating ADRs and a glossary.
Build and sharpen a project's domain model when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
This skill provides a reference for test-driven development, covering the red-green loop, test seams, anti-patterns, and rules of the loop.
Compact the current conversation into a handoff document for another agent to pick up.
Review changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards and Spec, running parallel sub-agents and reporting side by side.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
A disciplined diagnosis loop for hard bugs and performance regressions, used when the user asks to diagnose or debug, or reports something broken, throwing, failing, or slow.
This skill provides shared vocabulary for designing deep modules, helping improve module interfaces, find deepening opportunities, decide seam placement, and make code more testable and AI-navigable.
This skill exports a Remotion video, still, or selected frames using the Remotion CLI.
Instructions for creating a new Remotion video project and composition, covering scaffolding, preview startup, and video design workflow.
This skill covers transcribing, displaying, and animating captions in Remotion, with all captions processed as JSON using the Caption type.
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker.
Configure this repo for the engineering skills by setting up its issue tracker, triage label vocabulary, and domain doc layout.
The remotion-markup skill provides best practices for content, animation, and effects when writing Remotion React markup.
The remotion-studio skill starts Remotion Studio and opens its preview when creating or editing a video so users can watch changes and steer.
This skill explains how to find Remotion documentation through the Algolia search API and fetch documentation pages as Markdown.
This skill covers using the Mediabunny multimedia library in the browser to get audio duration, video dimensions, and video duration.
This skill upgrades Remotion and related packages to the latest stable version and updates installed Remotion skills.
Explains how to structure Remotion markup so Remotion Studio can recognize the code structure and make it interactive.
remotion-maps provides Remotion map animation knowledge covering static maps, Mapbox, MapLibre, MapTiler, and CesiumJS techniques.
Build a throwaway prototype to answer a design question, validating state models or UI appearance.
Build apps with Remotion, covering template selection, embedding the Player component, rendering options, and Vue, Angular, and Svelte integration.
Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
The teach skill helps users learn new skills or concepts within a workspace, tracking progress through structured files and lessons.
The wayfinder skill plans a large chunk of work as a shared map of decision tickets on your issue tracker, resolving them one at a time until the way to the destination is clear.
Non-animation creative direction for HyperFrames videos, covering design spec handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand or style decisions.
Prisma Client API reference covering model queries, filters, operators, and client methods.
This skill moves issues and external PRs through a state machine of triage roles, categorises, verifies, grills if needed, and writes agent-ready briefs.
A guide to writing documents for agents, covering skills, AGENTS.md, and CLAUDE.md.
Prisma ORM 7 CLI reference covering prisma init, generate, migrate, db, dev, studio, and mcp for existing Prisma 7 applications or explicitly selected Prisma 7 workflows.
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
Provides guides for configuring Prisma ORM with various database providers (PostgreSQL, MySQL, SQLite, MongoDB, etc.), covering new project setup, switching databases, and troubleshooting connection issues.
Browser automation for AI agents via inference.sh, enabling web navigation, element interaction, screenshots, and video recording.