Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Guidelines and best practices for creating draw.io diagrams with proper formatting, font handling, and layout rules. Use when creating or editing .drawio files, generating architecture diagrams, or working with draw.io XML format. Ensures high-quality PNG output with correct Japanese text rendering and professional appearance.
Edit a raw talking-head video through transcription, silence trimming, mistake review, visual storytelling, motion graphics, and verified HyperFrames rendering. Use for a complete edit; route a single requested operation directly to its specialist skill.
Complete GSAP (GreenSock Animation Platform) reference for elite web animations. Covers ScrollTrigger, SplitText, Flip, MorphSVG, DrawSVG, MotionPath, Observer, Draggable, timelines, Lenis smooth scroll, and framework integration. 2026 UPDATE: All GSAP plugins are now 100% FREE (Webflow acquisition). Use when asked about: GSAP, gsap, GreenSock, ScrollTrigger, scroll animations, SplitText, text animations, Flip plugin, layout animations, MorphSVG, DrawSVG, SVG animations, complex animations, animation library, pinned sections, horizontal scroll, parallax effects, smooth scroll, Lenis, or any sophisticated web animation needs. IMPORTANT: Always load elite-accessibility alongside this skill for reduced-motion patterns. References elite-design-core for design tokens.
How to work the user's email through the Spark CLI and the Gmail connector: which tool to pick, how to list, search, and read mail, and how to mark it done, label, pin, and save drafts. It reads mail only for an email task the user asked for, keeps a plain draft in chat, archives freely, makes any other change only when asked, and never sends. Use when the user asks for an email task, such as finding, reading, tidying, or drafting mail, or when this email setup needs configuring or checking. A task that could merely use mail as context is not an email task.
Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.
Systematic claim-by-claim verification for any content before it ships. Modeled on professional fact-checking desks (The New Yorker, ProPublica, IFCN standards): extract every verifiable claim, check each against live citable sources (never training data), assign a 6-level confidence status, apply corrections, and produce a scored pass/fail report. Includes a data-derived-claims gate for outputs produced FROM the brain or a database: PRODUCER ≠ VERIFIER (re-derive each claim via a different query path) and AFFILIATION ≠ AUTHORSHIP (person→thing claims resolve through typed edges), with delivery hard-blocked on unsupported claims.
Complete fal.ai audio system. PROACTIVELY activate for: (1) Whisper speech-to-text, (2) Transcription with timestamps, (3) Translation to English, (4) F5-TTS voice cloning, (5) ElevenLabs premium TTS, (6) Kokoro multi-language TTS, (7) XTTS open-source cloning, (8) Subtitle generation (SRT), (9) Audio file formats. Provides: STT/TTS endpoints, language codes, voice cloning setup, timestamp formatting. Ensures accurate transcription and natural speech synthesis.
Complete fal.ai model selection system. PROACTIVELY activate for: (1) Choosing image generation models (FLUX, SDXL), (2) Choosing video models (Kling, Sora, LTX), (3) Choosing audio models (Whisper, ElevenLabs), (4) Model quality vs speed comparison, (5) Cost optimization by model tier, (6) 3D generation models, (7) Model-specific parameters, (8) Development vs production model selection. Provides: Model comparison tables, decision trees, pricing tiers, performance benchmarks. Ensures optimal model selection for quality, speed, and cost.
Analyze app or collection feedback over a window — KPIs with prev-window deltas, rating/volume/sentiment trends, anomaly callouts, and ranked top bugs and feature requests — then emit a structured findings.json plus a self-contained HTML report. Read-only (never writes). Trigger on “feedback report”, “how are our reviews”, “what are users complaining about”, “review trends for <app>”, or “what are our testers saying” (Google Play testing feedback).
Retrieve the pre-aggregated digest of World Monitor's curated news feeds, bucketed by category, with per-article threat classification and alert flags. Use when the user asks what's in the news right now, wants headlines by topic, or needs a current-events sweep.
Complete CI/CD video processing system. PROACTIVELY activate for: (1) GitHub Actions FFmpeg setup, (2) GitLab CI video pipelines, (3) Jenkins declarative pipelines, (4) FFmpeg caching strategies, (5) Windows runner workarounds, (6) GPU-enabled self-hosted runners, (7) Matrix builds for multi-format, (8) Artifact upload/download, (9) Video validation workflows, (10) BtbN/FFmpeg-Builds integration. Provides: YAML workflow examples, Docker container patterns, caching configuration, platform-specific solutions, debugging guides. Ensures: Fast, reliable video processing in CI/CD pipelines.
Identify, measure, and exclude bot / crawler / AI-agent traffic in PostHog web and product analytics using the traffic classification surface (the isLikelyBot / getTrafficType HogQL functions and the $virt_* virtual properties). Use when the user asks to "exclude bots", "filter out crawlers", "remove bot traffic from my numbers", "how much of my traffic is bots / AI crawlers", "is GPTBot / ChatGPT / Claude hitting my site", "break down traffic by human vs bot", or wants clean human-only counts in an insight or dashboard. For the real-time Live tab bot tiles, use exploring-live-traffic instead.
Use the published FinalRun CLI to install, configure, validate, run, troubleshoot, and inspect reports for repo-local mobile test workspaces. Trigger this skill for requests involving finalrun, check, test, suite, doctor, runs, start-server.
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
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.
Provides one-command project creation for Flutter including project initialization, configuration, and template generation. Use when the user asks about creating Flutter projects, needs to initialize a new Flutter project, or generate Flutter project structure.
Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, and academic research requiring U.S. and international economic indicators.
Create distinctive React and Tailwind interfaces with strong hierarchy and polished implementation. Use when building or redesigning pages, flows, or components, or when another better-react-web-ui skill needs shared design guidance. Pair with add-ui for direct implementation or requested alternatives.
Building modular, debuggable AI behaviors using behavior trees for game NPCs and agentsUse when "behavior tree, bt, npc ai, ai behavior, game ai, decision tree, blackboard, ai, behavior-trees, npc, game-ai, decision-making, agents" mentioned.
Challenges an overly conservative, incremental, or compatibility-led proposal with a bold target model, a concrete kill/merge/split list, materially different options, and a falsifiable first proof point. Use when the user asks to think bigger, open the design space, or imagine the clean target without legacy constraints（打开格局、别太保守、不要被兼容绑架）. Use goudi to pressure-test how the chosen direction lands, and hai-idea to decide whether the idea deserves doing at all.
Visual and front-end development assistant powered by Google Gemini's multimodal models. Use for UI analysis, design comparison, accessibility audits, color palette extraction, screenshot-to-code conversion, generating UI assets, and text-based design assistance from briefs.
Refresh paper and concept indexes (maps of content). English triggers: “refresh indexes”, “update paper and concept indexes”, “refresh MOCs”. Regenerate the directory/navigation pages (MOC) in Obsidian. Use when the user says “更新索引”, “更新论文和概念目录”, “刷新论文和概念目录”, or “刷新MOC”.
Generate crisp, perfectly smooth MP4 videos from a web page or animated visualization by driving headless Chromium over the Chrome DevTools Protocol (CDP) with deterministic frame-stepping, then encoding with ffmpeg and (if remote) sharing via a cloudflared tunnel. Use when asked to make/generate a demo video, explainer clip, launch/marketing animation, social teaser, or any short rendered video from a web scene — especially animated stat/timeline/diagram visualizations — and when you need to iterate on it (tweak, re-render, compare). Solves the common "the recording has hitches / judder / dropped frames" problem.
Guidance and local audit CLIs for Python workflows using GeoPandas 1.1.4 GeoSeries and GeoDataFrame for planar vector data: CRS handling, geometry validity and repair, sjoin, overlay, clip, dissolve, union, GeoPackage, GeoParquet and PostGIS I/O, and plotting. Use when reprojecting or assigning a CRS, auditing invalid or empty geometries, running spatial joins and checking cardinality, exporting vector data with a reproducible contract, or migrating code from GeoPandas 0.14 to 1.x. Use when checking privacy risks in coordinate data. Do not use for raster data or geodesic-only calculations.
Master advanced Git workflows—including rebasing, cherry-picking, bisect, worktrees, and reflog—to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.
Implement GitOps workflows with ArgoCD and Flux for automated, declarative Kubernetes deployments with continuous reconciliation. Use when implementing GitOps practices, automating Kubernetes deployments, or setting up declarative infrastructure management.
Check package URLs against GitLab Dependency Firewall, run supported package managers through it, and inspect local firewall activity with glab. Use when checking an npm, PyPI, Maven, RubyGems, Cargo, or Go PURL; enforcing dependency policy for supported package-manager wrappers; summarizing CI logs; or troubleshooting Dependency Firewall exit codes. Triggers on dependency firewall, glab df, glab dependency-firewall, package URL, PURL, package policy, ci-summary, blocked package, flagged package
Generate adaptive Go coding exercises for developers who want broad practical Go fluency: writing correct programs, building backends, creating CLIs/tools, working with concurrency, and eventually building Kubernetes/CNCF ecosystem tooling. Use whenever the user wants to practice Go, learn Go concepts, review Go code, debug Go programs, build backend Go skills, prepare for Kubernetes ecosystem work, or mentions Go exercises, goroutines, channels, context, HTTP services, CLI tools, controllers, operators, cloud tooling, distributed systems, or CNCF projects. The skill tracks recurring mistakes and clarifying questions in /home/laborant/repos/go-practice/ learning-log.md so future exercise batches adapt to the user's actual learning pattern. Exercises must be created inside dated folders in the go-practice repo.
Designs and troubleshoots responsive Godot 4.x Control interfaces using anchors, containers, themes, focus navigation, keyboard and controller input, localization-safe sizing, and accessibility practices. Use when requests mention menus, HUDs, forms, responsive layouts, Control nodes, themes, focus, UI input, or accessible interaction.
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.