Agent Skills

Use this when a user wants to write Instagram content (Reel scripts, opening hooks, captions, carousels, Stories, a weekly posting plan, comment and DM replies), or wants to turn a video, podcast or article into Instagram content. Built on the open-source instagram-agent-skill (13 /ig-* skills plus 5 local helper tools). It checks the installation and voice file automatically, picks the right command, and after writing, scores the hooks and strips AI-sounding phrasing with local tools. Write only: no logging in, no posting, no made-up data. Use case: Have an agent help you write Instagram Reel scripts, captions and a weekly posting plan, then copy and post them yourself.

Use when a user wants to know the probability of events such as political elections, stocks, cryptocurrencies, or sports, mentions Polymarket, prediction markets, or odds, or wants to track and evaluate a batch of predictions. Use the official CLI for read-only queries; it is free and needs no wallet. Form your own judgment first, then compare it with market prices, record it in predictions.csv, and calculate the Brier score after settlement. Do not place orders, do not touch private keys, and do not give buy or sell advice. Use case: Let the agent use Polymarket's free interface to check odds and trends, give its own probability and record it, then score it after settlement.

Use when the user wants answers to AI agent learning questions that come from CWYZ course content and include sources. Calls the CWYZ Q&A API with an API Key: it first classifies the question, then finds answers in the matching site sections and returns source links. Free accounts get 1 question per day, members get 30 per day. Use case: Let your agent ask CWYZ questions directly and get answers based on course content, with source links.

Use when the user wants voiceover, text-to-speech, a new custom voice, or to clone their own voice. Uses the open-source VoxCPM2 to generate 48kHz speech locally, supports voice design from a one-sentence description and cloning from a short recording, Apache-2.0 licensed and free for commercial use. Requires an NVIDIA GPU; only clone your own voice or voices whose owners have consented. Use case: Generate voiceovers locally for free: type text to speech, design a voice from one sentence, or clone a voice from the user's own recording.

Use this when a user wants AI to work in Blender through natural language for 3D modeling, scene building, or object editing, or asks how to connect Blender to MCP. BlenderMCP exposes Blender as an interactive environment via the Model Context Protocol, so clients like Claude can talk to Blender and the result is an editable scene. Before using it in a real production pipeline, still check the Blender version, plugin permissions, file paths, and output quality. Use case: Use natural language to have AI model, build scenes, and edit 3D objects in Blender, producing editable scenes.

Turn Remotion talking-head video production from a one-shot gamble on the final cut into a controlled Codex workflow with preview, frame-level edits, and acceptance: asset check → real transcription → proxy development → style keyframes → semantic storyboard → Studio preview → frame-level revision → quality review → export only after approval. Multi-file repo, installed via git clone. Use case: Use Remotion to turn talking-head footage into controlled videos that can be previewed, edited frame by frame, and exported only after approval.

A general-purpose skill for Codex and local creative workflows that turns a product brief, reviewed narration, digital human or real-person on-camera speech, real product footage, and motion graphics into a deliverable video with review gates. It is not tied to any brand or script; product facts, copy, media, and vendor parameters live in the project directory. Multi-file repository, installed via git clone. Use case: Combines a product brief, narration, and digital human on-camera speech into a deliverable product video with review gates.

Turns an SRT subtitle file into a whiteboard hand-drawn animation on a warm cream paper background: subtitles drive elements to appear one by one in narrative order, with zone-mask layout and continuous strokes (outline first, then color), outputting MP4 and saving you from frame-by-frame manual whiteboard animation. Multi-file repo, installed via git clone. Use case: Turn an SRT subtitle file into a subtitle-driven whiteboard hand-drawn animation video with continuous strokes.

Automatically detects, tracks and obscures faces in video, with mosaic, blur or solid black masks, preserving the original motion and audio. Processes locally and outputs Telegram-compatible H.264 MP4. SCRFD suits small distant faces in groups; YuNet is faster. Use case: Automatically blur faces in video (mosaic, blur or solid black), keep the audio, process locally.

Install Anthropic's community ELI5 skill: explain a concept or thing so a 5-year-old gets it, as a few-words, big-pictures, zero-barrier HTML page. It is really just one prompt, so there is no need to install it unless you use it often. Said to be a favorite of Anthropic's Thariq. Use case: Explain a concept so a 5-year-old gets it, as a few-words big-pictures HTML page.

Use this when a user has an audio recording they want to turn into a captioned short video, spoken-word clip, or social media short. The core is word-level timestamps: transcribe into word-by-word text, the user deletes words to cut the matching audio, AI marks key words for highlighting, and then it renders a vertical video with a black background, key words in gold, and captions that appear in sync with the sound. Use case: Turn an audio recording into a short social media video with key-word highlighting and captions synced to the sound.

Use when a user wants an AI assistant to control editing, color grading, media organization and rendering in DaVinci Resolve Studio using natural language, or asks how to connect DaVinci Resolve to MCP. Connects through the MCP server built into Studio 21.1; always back up first, work on a copy, and ask the user before deleting, overwriting, changing project settings, or batch rendering. Use case: Let an AI assistant directly control editing, color grading and rendering in DaVinci Resolve Studio using natural language.

Use when a user wants an AI agent to connect to Home Assistant, check device and sensor status, or control lights, switches, and scenes. Connects via Home Assistant's built-in REST API using a long-lived access token, verifies the connection first, then reads and controls devices. Security-sensitive actions such as door locks and alarms must always be confirmed with the user first. Use case: Connect your AI agent to Home Assistant to view and control your smart home.

Entry point and router for every public jqsp.com API — read this file first for short dramas, medium-length videos, single videos, talking-head videos, image generation, storyboard sheets and voice-over / text-to-speech. Uses the Drama Agent API (https://jqsp.com/api/v1/drama/**) to take a short drama from source text to finished episode; single videos go through the jqsp-video skill, talking-head videos through the jqsp-talking-head skill, images / Nano Banana / storyboard sheets through the images sub-skill, speech synthesis through the tts sub-skill, and balance, model prices and model availability through GET /api/v1/catalog and /api/v1/model-status. At the start of a session, offer the human a set of entry buttons (new drama, continue a project, add a character / scene / prop, shot-by-shot production, export, make a medium video, make a single video, generate images, voice-over, etc.); a click goes straight into that flow. Recommend that the human writes the script on the website (step 1); with several projects, ask which one to work on (step 2 — never pick yourself); then check whether the project already has a script / storyboard (step 0): projects already in production take "continue with new chapters", projects without a script or without any broken-down chapter take "build from scratch". Along the way, GET .../status's next.tool tells you which sub-skill to read (script / characters / scenes-props / voices / storyboard); medium videos (project mode = quick15) go straight to the quick sub-skill. Use for any request like "make me a short drama", "continue this project", "where is this drama stuck", "render chapter N", "make a 15-second video", "generate an image", "make a 9-panel storyboard sheet", "turn this text into speech", "check my balance / model prices / which models work". Use case: Let your AI agent make short dramas and mid-length videos, plus images, voice-overs and single clips. It quotes the credit cost and waits for your confirmation before every spend.

Companion for the lvruan software directory — search software and hand out download links, browse the newest software, categories and tags, publish your own software and follow its review, and answer questions with the site's articles. Use when the user mentions software, download, lvruan or 绿软, or asks which software does something, where to download a program, which AI software can be deployed locally, or wants to publish software. Use case: Give your AI agent the ability to search for software and find download links.

Canadian lottery companion for Lotto Max, Lotto 6/49 and Daily Grand — reads draw history and statistics, generates number sets with five generators through the max649 API, keeps the user's generated numbers and tells them when one comes up. Use when the user asks about these lotteries, past draws, hot/cold/overdue numbers, wants numbers picked, or asks whether they won. Use case: Give your AI agent the ability to generate and analyze lottery numbers. Works with Claude Code, Codex and other agents; new users who sign in with Google get 50 credits.

Use this when you need to design or review free quotas, sign-up bonuses, trials and rate limits for a product, so the platform can afford to give things away without being farmed to death. Covers identity and device identification, sign-up and login protection, human verification, and isolating quotas and model costs. Use case: Used to stop the platform from being mass-registered and farmed for free credits.