Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Read how a game actually works so a mod can hook it. Decompile .NET/Mono (ILSpy), IL2CPP (Cpp2IL, Il2CppDumper), Java (Vineflower) and native code (Ghidra, IDA, via MCP servers); dump data and asset formats; reverse-engineer a binary file format and prove it with a round trip; read live memory (Cheat Engine, Frida, x64dbg); find render passes (RenderDoc). Use when a mod needs game internals, e.g. "how does the boss AI work", "find the damage function", "what format is this .sld/.pak/.dat", "where is the player position in memory".
When the user wants to audit, review, or diagnose SEO issues on their site. Uses live web data via the Bright Data CLI for accurate detection of JS-injected schema, hreflang, canonicals, and live SERP-based ranking checks. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For implementing structured data, see schema-markup. For AI search optimization, see ai-seo.
Query the user's LLM Wiki knowledge base (the LLM Wiki desktop app at 127.0.0.1:19828 — NOT Obsidian, Notion, Apple Notes, Logseq, or any other PKM tool). Trigger ONLY when the user explicitly names LLM Wiki, says 'my wiki', 'my 知识库 / 知识库 / knowledge base', or asks things like 'what does my wiki say about X', 'read wiki page Y', 'show my wiki graph / 知识图谱', 'search in my LLM Wiki project', 'rescan my wiki sources / 重新索引', or names a wiki project by ID. DO NOT trigger on generic 'search my notes', 'find in my notebook', 'check my Obsidian', etc. — those belong to other tools the user may have installed. Covers wiki page search, file listing, content read, knowledge graph navigation, and source rescan against the running LLM Wiki desktop app. Read-only except for source rescan.
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.
Generate Xiaohongshu (小红书) style cover images based on user topics. Use when the user wants to create a social media cover image in Xiaohongshu style, or mentions keywords like "小红书封面", "Xiaohongshu cover", "封面生成", or provides a topic for cover image generation. The generated image will be saved to the current project directory.
Critique a rendered screen’s density—cognitive load, content prioritisation, scanning patterns, and progressive disclosure. Use when a screen feels overwhelming. For the underlying choice-count principle, use `hicks-law` (interaction-design)
Diagnoses GKE HorizontalPodAutoscaler (HPA) failures — metrics showing as <unknown>, FailedGetResourceMetric / FailedGetScale / FailedComputeMetricsReplicas events, missing Pod resource requests, custom/external metrics-pipeline breakage (FailedGetExternalMetric / FailedGetCustomMetric, unavailable metrics adapter, control-plane firewall blocking the adapter), HPA that won't scale up or down (tolerance / stabilization window / unavailable rate metrics), scale-to/from-zero problems, and slow HPA reaction on large clusters. Use when an HPA isn't scaling a workload as expected or reports metric errors. Don't use for configuring or authoring new HPA/VPA objects or scaling best practices (see the gke-workload-scaling skill), or for Cluster Autoscaler / node-pool sizing.
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for activation memory OOMs or regressions involving recompute_granularity, recompute_num_layers, recompute_modules, recompute_method, selective recompute, full recompute, or activation checkpointing.
Push and publish custom AI models to Replicate, and set up CI/CD for safely releasing new model versions. Use when running cog push, deploying a model to Replicate, releasing a new version, validating a model with cog-safe-push before publishing, configuring a Replicate deployment, setting up GitHub Actions for model releases, or porting a community model to an official one. Trigger on phrases like "push a model to Replicate", "publish a model", "deploy a model", "release a new version", "cog push", "cog-safe-push", "model CI", "r8.im", or "schema compatibility", and when referencing github.com/replicate/cog-safe-push or github.com/replicate/model-ci-template. Covers cog push, the full cog-safe-push config (test cases, fuzz, deployment, official_model), GitHub Actions patterns, multi-model matrix pushes, and post-publish monitoring. Assumes you already have a working Cog project; see build-models if you need to package one first
Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video files, and RTSP streams, and chains to `vss-generate-video-calibration` when calibration is missing. Use `vss-deploy-profile` for the full warehouse blueprint and `vss-deploy-detection-tracking-2d` for single-camera 2D detection.
Shared knowledge base of standards, including writing guidelines for mathematical modeling competitions, quick reference for avoiding common problem-type errors, and chart standards. Other skills consult it as needed during execution; no separate trigger is required.
Use when the user wants to find patterns in what content works and what doesn’t. Also use when the user mentions “what’s working,” “content patterns,” “best topics,” “best format,” “best time to post,” “analyze my content,” “do more of,” “do less of,” or “what should I change.” For raw metrics, see performance-analyzer-sms. For audience-specific analysis, see audience-growth-tracker-sms. For actionable recommendations, see optimization-advisor-sms.
Design UIs in Pencil (.pen files) and generate production code from them. Use when working with .pen files, designing screens or components in Pencil, or generating code from Pencil designs. Triggers on tasks involving Pencil, .pen files, design-to-code workflows, or UI design with the Pencil MCP tools.
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocation
Pick, install and compose remocn components: ready-made Remotion animations, transitions, backgrounds, captions, UI primitives and video templates from a shadcn registry. Use when building a video or scene out of prebuilt parts (product demo, launch, changelog, intro, social clip), adding an animation, transition or background to a Remotion project, or choosing between components. Activate for polished Remotion video work even when remocn isn't named. Works alongside the Remotion skills: questions about the Remotion API itself (interpolate, spring, Sequence, rendering, config) belong to them, not to this skill.
Mod a PC game the user owns, taking an idea to working in the real game and recorded. It covers new items, weapons, enemies, bosses, units, civilizations, mechanics, art, sound, VR and cross-game mashups. Use when the user wants to mod, extend, hack on, reverse engineer or mash up a game (“add a nuke to Terraria”, “make a new civ for Age of Empires”, “put Minecraft inside X”, “can I mod this game?”). It covers recon (engine, loaders, anti-cheat), choosing the route, a safe lab, a first vertical slice, fal-generated assets, in-game verification and a showcase clip
Profile, audit, and optimize frontend page performance with emphasis on animation work, memory-leak risks, long-session slowdowns, CSS animations, canvas/WebGL requestAnimationFrame loops, marquees, skeletons, GSAP/Three/Matter effects, timers, listeners, and observers. Use when the user asks to make animations performant, pause offscreen animations, look for memory leaks, profile pages that slow the computer over time, fix janky scrolling, reduce CPU/GPU use, or repeat the "only play in view" optimization on React/Vite/Next/frontend pages using Codex Browser.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
When the user wants to reverse engineer how another company grew and copy what worked. Also use when the user mentions “reverse engineer,” “how did X grow,” “how does X get customers,” “growth teardown,” “marketing teardown,” “GTM teardown,” “growth blueprint,” “what is X doing for marketing,” “what made X take off,” “copy X's playbook,” “X's distribution strategy,” “what content works for X,” “funnel hack,” “map their funnel,” or “watch what X is doing.” Builds a dated log of a company's moves against its traffic curve from public data, sign-ups and demos, team interviews, and hidden signals (DNS, certificate logs, archives, sponsorships), compares it with the user's own data, and turns what lined up with growth into plays routed to the skill that runs each one. For a snapshot profile of a competitor's positioning, pricing, and features, see competitor-profiling. For comparison pages, see competitors. For why a single post went viral, see social.
Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM, embedding, or analytics — use the matching vss-* skill
Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown
Enumerate a username across hundreds of platforms with sherlock, maigret and WhatsMyName, then correlate and confirm which accounts genuinely belong to the same person. Use for username OSINT and handle enumeration, "find all accounts for this username", cross-platform account correlation, nickname and screen-name pivots, or turning a handle into a real name. Applies to fraud and synthetic-identity investigation, recruitment and marketplace scam checks, trust-and-safety enforcement, insider-threat work, and personal exposure audits. Reference at useosint.com/skills/hunt-a-handle.
Generate idiomatic Typst (.typ) code, edit and troubleshoot Typst documents and projects, and answer Typst syntax/reference questions. Use when working with .typ files or when the user explicitly asks for Typst document creation, editing, debugging, compilation, formatting, template work, or package usage.
Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, cover image, GitHub banner, Twitter header, or readme banner.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.