Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
All
GEO-first SEO analysis tool. Optimizes websites for AI-powered search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) while maintaining traditional SEO foundations. Performs full GEO audits, citability scoring, AI crawler analysis, llms.txt generation, brand mention scanning, platform-specific optimization, schema markup, technical SEO, content quality (E-E-A-T), and client-ready GEO report generation. Use when user says "geo", "seo", "audit", "AI search", "AI visibility", "optimize", "citability", "llms.txt", "schema", "brand mentions", "GEO report", or any URL for analysis.
Guides the agent through Ionic Framework development with React — project structure, React-specific Ionic components, IonReactRouter and navigation patterns, Ionic lifecycle hooks (useIonViewWillEnter, useIonViewDidEnter, useIonViewWillLeave, useIonViewDidLeave), state management integration, and React-specific best practices for Ionic apps. Do not use for plain Capacitor React apps without Ionic (use capacitor-react), Ionic with Angular or Vue, creating a new Ionic app (use ionic-app-creation), upgrading Ionic to a newer version (use ionic-app-upgrades), or general Ionic component usage without React-specific context (use ionic-app-development).
Focused interactive tutor for the Reverse Engineering path in AI Engineering from Scratch. Start or resume this route when a learner wants to read a compiled program: file formats, disassembly, control flow, lifting, evidence, proof, calling conventions, compiler idioms, linking, types, debugging, bytecode, diffing, symbolic execution, and AI-assisted analysis. Teaches one lesson per invocation and records evidence in REVERSE-ENGINEERING-LEARNING.md.
Run a self-refinement loop when a Blender result is subpar, user expectations are not met, validation fails, or repeated issues reveal missing skill depth. The loop diagnoses the gap, decides whether to repair the artifact or acquire/refine a generic skill, sanitizes lessons for reusable publication, updates docs/versioning, validates, and prepares stage/commit/push when explicitly requested.
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
Create AI-powered podcasts with text-to-speech, music, and audio editing. Tools: Kokoro TTS, DIA TTS, Chatterbox, AI music generation, ffmpeg for audio assembly. Capabilities: multi-voice conversations, background music, intro/outro, full episodes. Use for: podcast production, audiobooks, voice content, audio newsletters. Triggers: podcast, ai podcast, text to speech podcast, audio content, voice over, ai audiobook, multi voice, conversation ai, notebooklm alternative, audio generation, podcast automation, ai narrator, voice content, audio newsletter, podcast maker
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", \"make a driver skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.
Animation skill for Motion (prev Framer Motion) and CSS animation. Provides: animation best practices (including specific advice for vanilla JS, React, Vue, Base UI and Radix), documentation and example search, CSS spring and bounce generation, MotionScore code and runtime performance audits with Performance Doctor fixes, and the visual transition editor. Use when writing animations, working with Motion (motion, motion/react, motion-v, framer-motion), animating a UI, writing CSS linear() springs, auditing or fixing slow animations, performance, jank or layout thrash via code or runtime, searching Motion docs or examples, adding, inserting or building a Motion component or Motion UI section, or upgrading between Motion versions.
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.
Consolidates redundant documentation while preserving all valuable content; keeps a doc set truthful after things change. Modes: (1) POST-CHANGE GOVERNANCE — when code, scripts, config, env vars, ports, paths, deployment, auth, tests, or a documented procedure changed; also "which docs are now wrong", "check docs for inconsistencies", "过时的命令/路径", "文档同步". Use it even when the user mentions only the change and never the docs — updating them is part of the change, not optional cleanup. (2) CONSOLIDATION — "clean up docs", "documentation bloat", "reduce documentation sprawl", "consolidate documentation", "too many doc files", "merge redundant docs", "merge these docs", "文档太多/太乱", multiple files covering the same topic, or documentation exceeding 500 lines across multiple files on similar topics. Finds stale copies of a fact changed in only one place, values that should never have been persisted (counts, totals, "N items", restated summaries), rival definitions that drift apart, and orphaned cross-references.
Integrate the Dynatrace Flutter Plugin into a Flutter project — dependency setup, config, SDK bootstrap, navigation tracking, Session Replay, and verification. Trigger: "add Dynatrace to Flutter", "Flutter plugin setup", "instrument Flutter app", "integrate Dynatrace Flutter", "mobile observability Flutter", "dynatrace_flutter_plugin", "Flutter session replay", "dynatrace_flutter_plugin_replay". Do NOT use for: querying Flutter RUM data (use dt-obs-frontends), non-Flutter mobile setups, or Dynatrace server-side configuration.
Edits a talking-head take end to end into a paper-style motion design short (1080x1920, also 1:1 and 16:9) with its own render engine (Node + Chrome + ffmpeg, free, offline). Use when the user says edit, cut, captions, subtitles, motion design, montage, "make it a short", render, or gives a recording from video-agent/takes/. Transcribes locally with word timings (whisper.cpp, or ElevenLabs when a key is set), cuts every silence, lays the boards on a textured paper above the camera card (counters, terminals, logos, trees, real screens, HTML motion components), word-by-word captions, a calm music bed, a few designed hits, -14 LUFS, and writes the mp4, an .srt and the post copy.
Draft anonymous one-page company teasers for sell-side M&A processes. Creates a compelling summary without revealing the company's identity, designed to gauge buyer interest before NDA execution. Triggers on “teaser,” “blind teaser,” “anonymous profile,” “one-pager for process,” or “draft teaser for sell-side.”
Secures and rate limits backend services behind Google Cloud API Gateway across OpenAPI 2.0 and OpenAPI 3.0.x API configurations, including MCP-enabled gateways. Use when configuring API key or JWT authentication, locking down Cloud Run or Cloud Run functions backends with a gateway service account, reading authenticated claims from X-Apigateway-Api-Userinfo, setting per-project request quotas, or diagnosing HTTP 429 and HTTP 500 Service Control Quota errors. Do not use for Apigee, GKE Gateway API, Cloud Load Balancing custom domain setup, or LLM model routing.
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously, build all pages of a site, generate multiple pages in sequence, or run a 'design loop' / 'baton loop' / 'autonomous site build' — even if they say 'just keep going' or 'build the next page' or 'next page' mid-flow.
Discover and launch the Excel CLI for ordinary Excel workbook requests on Windows, including reads, writes, formulas, data refreshes, and workbook automation. Use the installed excel-cli plugin's npx launcher and native help to find commands; report presentation conventions are a separate optional skill.
The narrative-craft layer -- apply story structure (tension, transformation, resolution) to make any social content stick and travel. Use when someone wants to tell their brand/founder/customer story, make a flat post land, build an emotional or narrative-driven piece, or structure a story across formats. Uses the BEATS framework. Reads brand-profile + voice-builder first. The agent finds the real story, structures the arc (setup -> turning point -> payoff; audience = hero, brand = guide), anchors concrete specifics, and shapes it to the format. Feeds the format writers (reels-script, carousel-writer, linkedin-post-writer, thread-writer, caption-writer) and hook-writer; serialized arcs map into content-calendar; WoopSocial publishes. NOT the IG/FB Stories format (that's story-writer). Never fabricates a customer story or testimonial; never guarantees virality. Distinct from story-writer, hook-writer (the opening it pairs with), the format writers, and campaign-and-launch-planning.
Use to develop a deep, usable understanding of who a brand creates content for — sharp enough that every content skill resonates with them specifically. Run when the user says "who's my audience", "audience research", "target audience", "build a persona", "customer profile", "ideal customer profile" / "ICP", "who am I talking to", "understand my followers", or before content work that needs more audience depth than the brand-profile sketch. Reads brand-profile first and goes deeper: jobs-to-be-done, pains, objections, and the audience's ACTUAL language (voice-of-customer), grounded in real sources where possible — never demographic theater. Produces an audience.md that content-pillars, batch-content-plan, and the content skills read. Works for any business.
Track multiple live deals with milestones, deadlines, action items, and status updates. Maintains a deal pipeline view and surfaces upcoming deadlines and overdue items. Use when managing a book of business, tracking process milestones, or preparing for weekly deal reviews. Triggers on “deal tracker,” “deal status,” “where are we on,” “process update,” “deal pipeline,” or “weekly deal review.”
Single entry point for all AEM as a Cloud Service Dispatcher skills. Covers config authoring, technical advisory, incident response, performance tuning, security hardening, and full lifecycle orchestration for the Adobe Dispatcher Apache HTTP Server module and its HTTPD/dispatcher configuration.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
Creates and improves portable Agent Skills with a validator, routing scenarios, and evidence-based keep, cut, merge, or retire decisions. Use when asked to “write a skill”, “update all skills”, “audit my SKILL.md”, “remove redundant instructions”, or fix skill triggering.
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Instruments an existing Android project (Kotlin or Java) with the Dynatrace Mobile Agent for basic monitoring. Covers zero-to-first-event setup only: Gradle plugin, agent config, and user privacy opt-in. Do not use for advanced Dynatrace configuration beyond initial instrumentation.
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Upgrade an existing EmDash project with upgrade-emdash, interpret .emdash/UPGRADE.md, apply required project changes, and verify the package, skill, and migration result. Use when asked to update or upgrade EmDash dependencies. Do not use for an unrelated schema change or a known database migration without a package upgrade.
Export Webflow Designer components to React/Next.js code for external projects. Configure devlink settings in webflow.json, sync design updates with devlink sync, validate generated code, show diffs, and provide integration examples. Use when building with Webflow designs in React/Next.js.
CloudBase auth provider configuration and login-readiness guide. This skill should be used when users need to inspect, enable, disable, or configure auth providers, publishable-key prerequisites, login methods, SMS/email sender setup, or other provider-side readiness before implementing a client or backend auth flow.
Set up the Dynatrace iOS SDK (OneAgent) in an iOS project using Swift Package Manager. Automates adding the SPM dependency, creating a Dynatrace.plist configuration file, adding the import statement, adding privacy opt-in code, and building the project. Use this skill when the user wants to integrate, install, add, or set up Dynatrace monitoring in their iOS app. Keywords: Dynatrace, iOS, SDK, OneAgent, setup, install, integrate, SPM, Swift Package Manager, Info.plist, DTXApplicationID, DTXBeaconURL, mobile monitoring, RUM.
Searches and recovers Claude Code JSONL history across all active config homes and archives registered in ~/.claude/history-sources.json. Use --all-projects when the project is unknown, --codex to include Codex rollout search, and --kimi to include Kimi CLI (kimi-code) session search. Uses internal timestamps and searches messages, thinking, tool inputs/results, queues, attachments, summaries, titles, and file-history paths. Recovers exact captured bytes from Claude file-history snapshots, including post-Write edits and binary files; otherwise labels Write checkpoints as lower fidelity. Use for keyword/date-bounded history search, prior-conversation forensics, deleted-file recovery, vanished ~/.claude/jobs artifacts, tool/file-operation analysis, or requests mentioning session history, find in history, previous conversation, or .claude/projects. For a recent Claude+Codex+Kimi CLI inventory, use local-conversation-history instead
Optimizes or restructures CLAUDE.md/AGENTS.md with progressive disclosure and zero information loss. Use when the user asks to optimize, audit, 精简/瘦身/重构, or split instruction files, asks for their best practices (最佳实践), sees Memory files taking a large share of /context, reports rules in instruction files being ignored, or a task starts moving instruction sections. Not for generic task drift unless instruction files are in scope; not for moving memory entries into docs (use claude-code-ops-router).
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Diagnose and resolve GKE TPU slice creation failures (SliceCreationFailed) caused by partition overlap conflicts where requested TPU partitions or their nodes are already used by another slice or JobSet. Use when diagnosing GKE TPU slice creation failures with SliceCreationFailed partition or node conflicts. Don't use for general slice lifecycle states or slice provisioning failures without node overlap (use gke-ai-troubleshooting-tpu-dynamic-slices-monitoring), quota exhaustion, or unresponsive TPU nodes.
A multi-directional md/html/docx/pdf/epub pipeline that enables “produce in md, consume across platforms.” Capabilities: convert any file (PDF/DOCX/PPTX/XLSX/images/audio/URL) into clean md; turn md into publication-quality html, docx, PDF (A4/A5/large 32mo), and EPUB3 with four curated templates. html and PDF also offer a designer mode that recommends three distinct visual directions after AI understands the content. SKIP: tasks that require generating new images or only compressing screenshots.
Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer. Given a model, framework, workload (TP/EP, concurrency, ISL/OSL, precision), an objective and a time budget, it explores per-workload which levers to pull (serving/config parameters and env, framework enablement and source patches, and hot GPU-kernel rewrites), benchmarks each candidate, and returns the optimization stack that produced the gain. Use when the user wants to make a model serve faster, raise tokens/sec or throughput, optimize or tune vLLM or SGLang on MI300X/MI325X/MI355X, run Hyperloom, run the kernel-agent, quantize-then-optimize with Quark, set up Hyperloom from scratch, or resume a Hyperloom session. Do not use to stand up a server for plain serving, diagnose a broken ROCm install, or run a one-off kernel/benchmark or trace analysis without the optimization loop.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
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.