Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
CCXT cryptocurrency exchange library for Go developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors in Go projects. Use when working with crypto exchanges in Go applications, microservices, or trading systems
Look up the public API of any JVM dependency (Scala 3, Scala 2, Java) from the terminal — type signatures, members, docs, and source as Markdown, no JAR unpacking needed. Use this skill whenever you need to call an unfamiliar library method, explore a package's types, or check a dependency's API. Prefer cellar over Metals MCP only for looking up external dependency APIs (`cellar get-external` vs Metals `inspect`/`get-docs`) — cellar needs no project import and queries any published Maven artifact.
Complete AI agent operating system with Kanban task management, multi-agent coordination, human approval gates, and autonomous task discovery via heartbeat polling. Use when setting up multi-agent coordination, task tracking, or configuring an agent team. Includes theme selection (DBZ, One Piece, Marvel, etc.), workflow enforcement (all tasks through board), browser setup, GitHub integration, and memory enhancement (Supermemory, QMD).
Turn photos, videos, and Live Photos into a black-and-white to color reveal clip (单彩渐变 + 动感模糊 + 丁达尔旋焦). The frame starts monochrome and spun, color sweeps in from the left under a horizontal motion blur, and the spin settles from the center outward into a softly glowing full-color frame. Use when users ask for 上色效果, 黑白变彩色, 丁达尔旋焦, 旋焦上色, 剪映上色特效, color reveal, colorize transition, or want this effect on images, iPhone Live Photos (HEIC/JPG + MOV), Android motion photos, or video clips. Outputs H.264 MP4.
Domain model maintenance. Triggers: recording decisions, adding terms, splitting contexts, maintaining CONTEXT/ADR. Do not use for feature implementation (cs-feat), external documentation (cs-docs), breaking down large requirements (cs-epic), or requirements clarification and capability docs (cs-req).
Route loader option, loaderDeps for cache keys, staleTime/gcTime/defaultPreloadStaleTime SWR caching, pendingComponent/pendingMs/pendingMinMs, errorComponent/onError/onCatch, beforeLoad, router context and createRootRouteWithContext DI pattern, router.invalidate, Await component, deferred data loading with unawaited promises
A-share sector research: computes board-wide Top N gainers, cross-checks week/month announcement windows across two sources, and grades market-sentiment evidence (L1–L3), via parallel Agent Team execution with fresh-context adversarial verification. Use for 「XX 行业 Top N/Top 10 标的」, 「这些标的最近一周/一个月发过哪些公告」, 「判断 XX 行业/板块现在的市场情绪」, or 「用 Agent Team 做行业投研」/对抗验证行业研究结论。
Foundational design context skill. Establishes brand identity, color system, typography, design style, and audience preferences, saved to .agents/design-context.md for every other design skill to reuse. Trigger phrases: "set up design context", "define brand style", "style guide setup", "initialize design", "set brand colors", "use our brand". To build a full token system and components use design-system; to generate a palette use color-palette; to create a logo and identity use brand-identity.
Use Bright Data's Discover API for intent-ranked, AI-relevance-scored web search at scale, not keyword SERP. Trigger a discovery job and retrieve ranked results (link, title, description, relevance_score) with optional parsed page content. Use for semantic or intent-based web search, finding pages about a topic that match a goal, web-grounded retrieval for an LLM, or results filtered by relevance rather than raw keyword rank. Covers the REST API (POST/GET /discover), the CLI (`bdata discover`), and the Python/JS SDKs (`client.discover`), including the standard/zeroRanking/deep/fast modes. This is the foundation skill for `live-research` and `rag-pipeline`. For keyword SERP use `search`; for structured platform data use `data-feeds`.
Use when the user asks for an Azure architecture diagram — VNet/networking, App Service, AKS, landing zone, multi-region, or any diagram built with Azure service icons. Builds with the declarative layout engine using ground-truth Azure stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Create a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped context. Use when the user asks to create a CLAUDE.md for a folder, write folder instructions, or add agent context to a directory.
Emulated GitHub REST API for local development and testing. Use when the user needs to interact with GitHub API endpoints locally, test GitHub integrations, emulate repos/issues/PRs, set up GitHub OAuth flows, configure GitHub Apps, test webhooks, or work with actions/checks without hitting the real GitHub API. Triggers include "GitHub API", "emulate GitHub", "mock GitHub", "test GitHub OAuth", "GitHub App JWT", "local GitHub", or any task requiring a local GitHub API.
Detect performance anti-patterns and apply optimization techniques in Go. Covers allocations, benchmarks and benchstat, pprof and traces, GC and GOMEMLIMIT tuning, PGO, and HTTP client reuse. Use when checking performance, finding slow code, reducing allocations, profiling, or reviewing hot paths. Trigger examples: "check performance", "find slow code", "reduce allocations", "benchmark this", "profile", "optimize Go code". Not for: concurrency correctness (go-concurrency-review) or general style (go-coding-standards).
This skill should be used when the user asks to "test for HTML injection", "inject HTML into web pages", "perform HTML injection attacks", "deface web applications", or "test content injection vulnerabilities". It provides comprehensive HTML injection attack techniques and testing methodologies.
Build single-purpose, throwaway HTML editors for one specific piece of data — drag-and-drop boards, form-based config editors, side-by-side prompt tuners, dataset curators, annotation tools. Always end with a Submit button (calls `submitToClaude`) so the result can be sent back to the agent. Secret values (API keys, tokens, passwords) are never embedded verbatim — they are masked to references; the artifact and submit payload carry key names and masked previews only.
Publish user's work to the Huawei Cloud University Operations Platform (华为云高校运营平台/作品陈列馆). Use this skill whenever the user wants to publish, submit, or upload a project/work to the gallery or an activity (活动) on the platform — including casual phrasings like "把作品发布上去", "投稿到陈列馆", "传作品到平台", "提交作品/项目", "报名发布作品", as well as formal ones like "publish to work gallery", "submit to an activity", "upload work to the platform". Do NOT use for general dev questions, git push to GitCode alone, or platform browsing without publishing intent. Triggers include: "把作品发布上去", "投稿到陈列馆", "传作品到平台", "提交作品/项目", "报名发布作品", "publish to work gallery", "submit to an activity", "upload work to the platform"
Generates Karma test runner configurations for browser-based JavaScript testing. Works with Jasmine, Mocha, or QUnit. Use when user mentions “Karma”, “karma.conf.js”, “browser test runner”. Triggers on: “Karma”, “karma.conf”, “karma test runner”, “browser-based JS test”
Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn't yet exist, and run a GPU smoke test inside the container. Every other kermt-* skill depends on this; invoke it first.
Answer specific life decisions using the text of 《高性价比人生指南》(github.com/eternity4719/HowToLiveBetter): whether to do something, whether it’s worth it, how to choose, what to do first when something goes wrong, what benefits can be claimed, and whether an action is legal. Find relevant entries before answering, rank them by cost (money/time/perseverance), scale of benefit, and evidence grade A/B/C, and cite the section and item number for each. Triggers: should I, is it worth it, do I need to, is it worthwhile, how to choose, help me decide, is this legal, what can I claim, what should I do first, value for money.
Designs and audits macOS launchd watchdogs: LaunchAgent/LaunchDaemon setup, plist edits, scheduled self-healing, repeated notifications, apps reopening after quit, crash/repair loops, Script Editor alerts, stop/disable/restart, cooldown/backoff, notification throttling, alert decisions, schedule readback, WatchPaths/FSEvents event triggers. Supports periodic observers. launchd daemons, persistent tasks, startup launch, background monitoring, scheduled self-healing, notification-source troubleshooting, event-driven monitoring.
When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' 'consumer behavior,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' or 'nudge.' Use this whenever someone wants to understand or leverage how people think and make decisions in a marketing context.
Plan and evaluate mesh generation for numerical simulations — estimate grid resolution from physics scales (interface width, boundary layers, wavelengths), check aspect ratios and skewness against quality thresholds, choose between structured, unstructured, and adaptive mesh refinement strategies, and compute grid sizing for 1D/2D/3D domains. Use when setting up a new mesh, diagnosing poor solver convergence caused by mesh quality, deciding how many points to place across a phase-field interface or boundary layer, or preparing a mesh convergence study, even if the user only asks "what resolution do I need" or "why is my solver failing."
Use this skill when users need to scope an MVP, define minimum viable features, plan early product development, or determine what to build first. Activates for “what should my MVP include,” “scope my MVP,” “what to build first,” or product scoping questions.
Turn attention into conviction with evergreen email sequences that move leads from curiosity → trust → booked call, based on Lasse Flagstad’s Marketing Swarm A5 methodology. Use when: creating evergreen sequences with automated emails that run indefinitely; reactivating a cold list without spamming dormant leads; structuring post-lead-magnet nurturing; defining segments and triggers. HOT...
Bootstrap, configure, extend, and operate ObjectStack runtimes. Covers project setup (`defineStack`, drivers, scaffolding), declaring platform capabilities (`requires:` — which service plugins boot), plugin and service development (PluginContext, DI, kernel hooks like `kernel:ready`), and operations (CLI commands, migrations, deployment, test harnesses via LiteKernel). Use when the user is writing `objectstack.config.ts`, building a plugin or driver, turning a platform capability on, mounting the Hono HTTP layer, running `os` CLI commands, or planning deployment. Do not use for data schema design (see objectstack-data) or query patterns (see objectstack-query); data lifecycle hooks (beforeInsert / afterUpdate) belong in objectstack-data — only kernel / service-level events live here
Deauthentication and disassociation attacks against 802.11 networks — targeted single-client deauth for handshake capture, broadcast deauth for DoS (with authorization), action-frame attacks bypassing 802.11w (PMF), beacon flooding, mdk4 / aireplay-ng tooling, and rate-limit / PMF-aware operation. Use to coerce client reconnection (handshake capture, evil-twin roaming), as targeted DoS, or to test PMF posture.
Evil Twin / KARMA / Mana access point methodology — rogue AP construction with hostapd-mana / wifiphisher / airgeddon, KARMA universal probe response, Mana selective probe response, captive portal phishing, deauth-driven client coercion to attacker AP, MAC randomization defeat via PNL leak analysis, post-association MITM (DNS, ARP, transparent proxy), credential capture for portal/web/SMB, and detection-evasion tactics. Use to coerce client devices onto an attacker-controlled AP, intercept their traffic, harvest credentials, or deliver payloads via captive portal.
LoRaWAN and sub-GHz (433 / 868 / 915 MHz) attack methodology — LoRaWAN ABP/OTAA join attack, network/session key reuse, frame counter replay, downlink injection on TTN/Helium-style networks, sub-GHz protocol replay (KeeLoq garage doors, fixed-code remotes, TPMS spoofing, smart plug telemetry), HackRF / RTL-SDR / Flipper Zero workflows, signal analysis with Inspectrum / Universal Radio Hacker, and reconstruction of proprietary packet formats. Use for LoRaWAN deployments (smart cities, asset tracking, industrial telemetry), or any wireless device using the unlicensed 433/868/915 MHz bands (garage openers, doorbells, IoT sensors, RC equipment).
Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck', 'slides', 'presentation', 'pitch', or references a .pptx filename.
This skill should be used when the user asks to implement Phaser 4 game code, create or edit scenes, add players, enemies, scoring, collectibles, movement, shooting, animations, input, physics behavior, game objects, or complete gameplay features in TypeScript.
Use when an agent needs to interact with PolyBaskets prediction market baskets on Vara Network — create baskets, place bets, query state, claim payouts, or understand the protocol. Do not use for building Sails programs or general Vara development (use vara-skills for that).
Search for Japanese restaurants using the `hpp` CLI (HotPepper Gourmet API). Use when the user wants to find a restaurant, plan a dinner, search for izakayas, or book a group meal in Japan. Triggers on requests like "find a restaurant near Shibuya", "search for izakayas in 新宿", "restaurant for 10 people in 浜松町", "dinner spot near Tokyo station".
World-class Roblox game development - Lua scripting, Roblox Studio, game systems, monetization, and building experiences that millions play. Use when "roblox, roblox studio, lua scripting, roblox game, obby, simulator game, roblox experience, robux, devex, " mentioned.
Recommends which rocprofiler-systems runtime profiling preset (balanced, trace-gpu, trace-hpc, sys-trace, workload-trace, etc.) to pass to `rocprof-sys-run --preset=<name>` or `rocprof-sys-sample --preset=<name>` based on the user's workload and profiling goal, and returns the ready-to-run command. Use when the user asks "which preset should I use", describes a workload (GPU kernel, MPI, OpenMP, AI/ML training, production overview) and wants profiling guidance, or invokes `rocprof-sys-run`/`rocprof-sys-sample` without picking a preset. Do NOT use for CMake build presets (`cmake --preset debug|release|ci`) used to configure/compile rocprofiler-systems itself — that is a build-configuration concern, not a profiling-run concern.
Answers questions about what rocprofiler-systems configuration options exist and how to use them — e.g. "what hardware counters are available on my system", "what ROCm APIs can I trace", "what settings control sampling/output", "how do I persist my configuration" — by mapping the question to the right `rocprof-sys-avail` or `rocprof-sys-run --help=<topic>` command. Use when the user wants to discover or explore ROCPROFSYS_* settings, Timemory components, hardware counters, ROCm API tracing domains, or GPU metrics, rather than apply them. Do NOT use this for picking a starting --preset for a workload — that's `choosing-a-profiling-preset`.
Guides instrumentation with `rocprof-sys-instrument` - choosing runtime instrumentation vs binary rewrite (`-o`), including or excluding functions and modules with regex options, previewing what will be instrumented with a dry run (`--simulate`, `--dump-info`, `--print-*`), tuning granularity (`--min-instructions`, `--min-address-range`, `--instrument-loops`), rewriting libraries, and diagnosing why a function is missing from, or too numerous in, a trace. Use when the user asks about rocprof-sys-instrument, binary rewrite, instrumenting a shared library, function or module include/exclude regexes, dry runs, or the difference between a function and a module. Do NOT use to pick a `--preset` (use `choosing-a-profiling-preset`), to list settings, counters or ROCm domains (use `discovering-profiling-options`), or to attach to an already-running process (a separate tool, `rocprof-sys-attach`).
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.