Total 50,817 skills, AI & Machine Learning has 8500 skills
Showing 12 of 8500 skills
Craft high-quality natural-language image prompts for any modern text-to-image or image-edit model that accepts flowing English. Trigger when the user wants help writing, rewriting, improving, or translating an English natural-language image prompt — including "write me an image prompt", "improve this image prompt", "describe this scene for an image model", or "convert these tags into a natural language prompt". Do NOT trigger for requests that are purely about dispatching to an image API, choosing samplers/schedulers, picking LoRAs, or setting up ControlNet — those belong to a runtime skill.
Create `AGENTS.md` file for a project. Use when the user wants to set up custom instructions, configure AI coding assistant behavior, or create project-specific coding guidelines for AI agents.
Three modes. Session mode (default): extracts generalizable lessons from RESEARCH.md and git history at session end; lessons that imply a new or significantly changed skill are handed off to skill-creator. Personalize mode: searches the skills registry via `npx skills find`, reads the target skill(s), checks compatibility and scope overlap against installed skills, interviews the user to understand what they want and what to skip, then creates or improves skills using skill-creator. Registry mode: curates `skillpacks/skill_dictionary.yaml` and `skillpacks/presets/*.yaml` by assessing external packs, judging necessity/compatibility, and recommending subsets. Create mode: designs a brand- new skill from scratch using skill-creator. Never edits SKILL.md directly — all changes go through skill-creator's draft→test→iterate loop, human merges. Trigger phrases: "end session", "extract lessons", "personalize my skills", "integrate this skill", "update skillpack", "find a skill for", "create a skill", "improve skill", "refresh the skillpack registry", "assess this skill pack", "update skill_dictionary.yaml", "update index.yaml".
Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform the fixed fair SGLang/vLLM/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches SGLang code, optionally uses ncu-report-skill for kernel evidence, and revalidates until SGLang matches or beats the best observed framework under the same workload and SLA.
Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.
Rewrite AI-generated text to sound natural and human-written. Removes LLM tells — cliché phrases, predictable structure, inflated language, and robotic patterns. Use when editing drafts, emails, articles, or any text that reads like it was written by AI.
Turn a vague, messy, or multi-part user ask into a clean, self-contained prompt that a fresh agent could execute without further questions. Interview the user one question at a time — walking down the decision tree, branching on each answer — until the prompt is tight, then output the final prompt as the deliverable. Trigger eagerly: any voice-dictated input, filler-heavy prose, underspecified references ("the thing", "that script"), multi-part requests, or any plan the user wants stress-tested. The skill itself can be skipped for trivial one-line requests where producing a prompt artifact would be pure ceremony — but once invoked, always produce the prompt, even if execution looks trivial.
Automated content pipeline from research to video generation using Claude/OpenAI, web scraping, and Remotion rendering
The Oracle. Anticipates your next moves, predicts market shifts, and tells you what you will ask for next based on current codebase context and open files.
Generate a 65-second founder-style product video from a product URL + user-supplied imagery. Output is a 16:9 1080p MP4 — 4 × 15s SeeDance acts of a talking founder + 5s branded end card + background music. The user's actual product screenshots appear on the founder's phone in reveal shots, so on-screen UI is real, not AI-imagined. Triggers — "founder video", "product video", "60s pitch video", "make a video of [founder] for [URL]", "talking founder explainer". Requires Pika MCP. Uses a supplied brand kit folder (`brand.json` or an exported build-a-brand kit with `brand.md`, tokens, logo assets); if no kit exists, run build-a-brand first.
Generate cinematic 1080p iOS app teaser videos from real App Store screenshots, with a GPT-image-2 enhancement pass on each selected screen before generation. Output is a beat-driven cinematic teaser built from GPT-enhanced screenshots, ending with the brand logo/icon plus a deterministic `COMING SOON` overlay. Screens sourced from Pika MCP App Store fetch, a live website (auto-captured), user-supplied files, or URLs. Starts by sourcing real screens and brand assets before any generation. Triggers on: app sizzle, app teaser, app promo, iOS app promo video, app video, app product video, coming soon, seedance, motion graphics, make a promo for my app, make a video for [app], gpt enhance promo. NOT for: short-form consumer content like GRWM, vlogs, UGC, or non-app product ads (use content-video); app-sizzle is specifically for iOS app teaser videos sourced from App Store screens or real app UI.
Diagnose why a GAIA question failed — extract trace, classify failure mode, and propose a fix