Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
P3 phase skill for Headless Ghidra metadata discovery. Use after P2, or after a P4 batch exposes missing context, to enrich function names, signatures, types, constants, strings, and hotpath metadata in YAML before serialized CLI apply.
Write less code and say less about it. Applies YAGNI and stdlib/native-first so the agent writes the minimum code that needs to exist, and responds tersely — stripping filler, hedging, and pleasantries while keeping code, identifiers, and technical terms exact. Use whenever writing, modifying, refactoring, reviewing, or explaining code, or any response where output volume drives token cost — even if the user never says "minimal" or "concise". Especially in agentic coding, where the volume of generated code and prose runs up the bill.
Use this skill to track institutional investor ownership changes and portfolio flows using 13F filings data. Analyzes hedge funds, mutual funds, and other institutional holders to identify stocks with significant smart money accumulation or distribution. Helps discover stocks before major moves by following where sophisticated investors are deploying capital
End-to-end Jira bug-fix workflow (stages 0-10), driven by a single Jira link, from intake through PR/MR merge and Jira writeback. Manual mode (default) pauses for confirmation between stages; auto/force modes run end-to-end; ai-proxy overlay (thin freeze then occupy) is available independently. Triggers — 「修复这个 bug [URL]」「帮我修复 [URL]」「jira-fix [URL]」「自动修复 [URL]」「强制修复 [URL]」「继续修复」「从上次继续」；「ai-proxy 模式」「AI 代理模式」「切换 ai-proxy」 / fix this bug, jira-fix, auto fix, force fix, resume fix, ai-proxy mode, switch to ai-proxy. Do NOT use for batch fixes across multiple issues — use jira-fix-queue instead (it enqueues into goal-driven-queue; confirm, then run the queue).
Test/validate a Juspay payment integration after jp-executor has built it. Detects the repo's existing test stack and replicates it (Playwright, Cypress, Jest, Vitest, pytest, supertest, …), falling back to inline curl/bash when none exists. Risk-prioritized coverage of order/session creation, server-to-server status reconciliation, webhook signature + idempotency, per-method process payloads, constraint boundaries and error-code paths — backend and frontend/SDK as the built surface dictates. Ends with a traceability matrix, a PASS/CONCERNS/FAIL quality gate, and a written test report. Use after jp-executor, or standalone against an already-built integration.
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
Operate the joelclaw Kubernetes cluster — Talos Linux on Colima (Mac Mini). Deploy services, check health, debug pods, recover from restarts, add ports, manage Helm releases, inspect logs, fix networking. Triggers on: 'kubectl', 'pods', 'deploy to k8s', 'cluster health', 'restart pod', 'helm install', 'talosctl', 'colima', 'nodeport', 'flannel', 'port mapping', 'k8s down', 'cluster not working', 'add a port', 'PVC', 'storage', any k8s/Talos/Colima infrastructure task. Also triggers on service-specific deploy: 'deploy redis', 'redeploy inngest', 'livekit helm', 'pds not responding'.
Upgrade Laravel applications one major version at a time (9→10, 10→11, 11→12). Use when user wants to upgrade their Laravel framework version. Auto-detects current version from composer.json, identifies breaking changes, and applies necessary code fixes.
Interact with the Last.fm music data API: lookup user listening history, get artist/album/track metadata, discover similar music via collaborative filtering, explore global and per-country charts, search by artist/album/track, manage tags, and scrobble listening events. Use when the user asks about music data, listening statistics, music recommendations, similar artists, charts, or wants to scrobble or love tracks. Do not use this skill for unrelated requests; route to the nearest named specialist.
Lead qualification engine with conversational intake. Asks structured questions to understand your qualification criteria, generates a reusable qualification prompt, then batch-enriches leads via Apify LinkedIn scraping and scores them with parallel processing. Outputs qualified/disqualified verdicts with confidence scores and reasoning to Google Sheets (via Rube) or CSV. Supports calibration mode for prompt refinement.
Cognitive science-based AI tutor that won't let you fake understanding. Implements a full teaching loop (Explain→Example→Check→Evaluate→Practice), concept-level mastery tracking with FSRS spaced repetition, learning profile diagnostics, and zero-hint quizzes. Reads source material (PDFs, docs, code, URLs) to teach from specific content, or teaches from AI knowledge. Use this skill when the user says /learn, "teach me X", "quiz me", "review my concepts", "what should I study", "test my knowledge", "learning dashboard", "how well do I know X", or wants to systematically learn any topic. Also triggers on "let's study", "drill me on", "what's due for review", requests for structured learning with progress tracking, or any context where the user wants to actually understand (not just read about) a topic.
Use to pull many structured records from ONE known listing page — team directories, product/pricing catalogs, job listings, conference speakers, paginated lists. ALSO read this when writing code that integrates the /v1/extract endpoint (schema, async polling, NDJSON results). Uses Linkup's async /v1/extract REST endpoint and returns NDJSON rows. Requires LINKUP_API_KEY. For a single page's prose use linkup-fetch; for web discovery use linkup-search.
Symfony UX LiveComponent for reactive server-rendered UI -- components that re-render via AJAX on user interaction, zero JavaScript required. Use when building live search, real-time filtering, dynamic forms, inline validation, dependent selects, auto-save, polling, deferred/lazy rendering, or any UI that updates itself based on user input. Code triggers: AsLiveComponent, LiveProp, LiveAction, data-model, data-loading, data-live-action-url, ComponentWithFormTrait, LiveListener, emit, defer, lazy, polling. Also trigger when the user asks "how to build a search that filters as I type", "how to validate a form in real-time", "how to make a reactive component in PHP", "how to build dependent selects", "how to defer component rendering", "how to communicate between components via emit", "how to bind a form to a LiveComponent". Do NOT trigger for static reusable UI without reactivity (use twig-component), pure client-side JS behavior (use stimulus), or page-level navigation (use turbo).
Complete Love2D game development from prototype to polished release. Covers core architecture, graphics, animation, tiles, collision, audio, and iOS deployment. Use when building Love2D games, implementing game mechanics, or deploying to mobile platforms.
Convert text content into polished magazine-style HTML pages, with support for professional typography and multiple visual styles. Trigger scenarios: (1) the user wants to convert text/an article into magazine-style HTML, (2) the user mentions "magazine typography," "magazine design," "article layout," "professional typesetting," "text beautification," or "magazine layout," (3) the user needs an elegantly typeset HTML page, (4) the user needs to export the designed content to PDF. Supports 12 distinct visual styles and uses Tailwind CSS.
Makes a 3D map animation for a reel. A clean white city with parks and a river, a coloured route that draws itself from start to destination while the camera follows, a red pin that drops with a bounce, an ETA card that counts down and a destination card. Use when the user runs /map-route or asks for an animated route, a "from A to B" map, a journey or a commute animation.
Use when optimizing conversion rates, designing A/B tests, or improving landing pages. Covers A/B testing methodology, landing page optimization, form design, statistical significance, funnel analysis, and CRO prioritization frameworks.
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.
Design, redesign, review, or implement user interfaces using Google Material Design 3 (M3), Material You, and optional Material 3 Expressive principles. Use for UI/UX screens, app flows, design systems, component selection, theming, responsive/adaptive layouts, accessibility audits, Figma-ready specifications, or developer handoff where Material Design 3 is required.
Comprehensive reference for LINE Messaging API — webhook setup, message sending, Flex Message design, Rich Menu management, audience targeting, insights, coupons, and channel access tokens. This skill should be used when the user asks to "build a LINE Bot", "set up a webhook", "send a push message", "design a Flex Message", "create a Rich Menu", "manage audience targeting", "get messaging insights", "create a coupon campaign", "debug webhook signature verification", or mentions LINE Messaging API, LINE OA chatbot, reply/push/multicast/narrowcast/broadcast, Flex Message JSON, Rich Menu, group chat bot, channel access token, or URL schemes. Always use this skill whenever the user mentions LINE bots, chatbots, LINE OA, or any messaging-related LINE integration, even if they don't explicitly say "Messaging API".
End-to-end Meta Ads campaign builder for Facebook and Instagram. Takes ICP + objective, generates audience targeting recommendations, ad set structure, copy framework per placement, and exports as a campaign brief or structured CSV. Focused on campaign architecture, not creative generation.
Propose and generate a React Native app's design system - semantic color tokens (light + dark), type scale with Dynamic Type bounds, radius/elevation/spacing scales, haptics and motion posture - as a SAFE/RISK proposal, then write the actual theme files (NativeWind config or StyleSheet tokens) and MOBILE-DESIGN.md. Use when starting an app's visual identity, when asked for a theme/palette/design tokens, or when an app has inline styles and needs a token system. For building screens with the system use mobile-taste; for auditing an existing app use mobile-design-review.
Generate, edit, and compose images using Gemini Nano Banana models via portable Python scripts. Handles authentication via API Key or Vertex AI environment variables. Available parameters: prompt, model, aspect-ratio, safety-filter-level. Always confirm parameters with the user or explicitly state defaults before running.
Remove code comments that explain or defend Remotion's own code, keeping only comments about external systems we cannot change (browser quirks, codec/FFmpeg behavior, third-party APIs, OS or platform bugs). Use when the user invokes /no-comments or asks to strip unnecessary comments from a diff or files.
Operate Notion from a terminal or agent: retrieve pages, query databases, search pages and databases, and update page properties — with a bundled notion-cli script that is read-only by default and gates every create or update behind a --dry-run/--yes confirmation. Use when an agent needs to read Notion content, answer questions from a team wiki or database, or make a confirmed edit. Do not use for building Notion integrations or block-level page composition beyond property updates (that is Notion API application development), or for other knowledge bases (that is their own tooling).
Generate images and content consistent with the Nous Research brand identity. Use when creating visuals in the Nous / Theia / Hermes ecosystem: a "cyber-classical" style blending neo-classical statuary, cyberpunk/industrial grunge, and retro anime illustration. Covers official brand color palette, typography (Inter/IBM Plex Sans, JetBrains Mono, heavy distressed display faces), the Nous Girl mascot, texture system, and image prompt construction. Ships reference images for palette, mascot, and brand collage that can be used as img2img inputs. Do not use this skill for unrelated requests; route to the nearest named specialist.
nuqs (type-safe URL query state) best practices for Next.js applications. This skill should be used when writing, reviewing, or refactoring code that uses nuqs for URL state management. Triggers on tasks involving useQueryState, useQueryStates, search params, URL state, query parameters, nuqs parsers, or Next.js routing with state.
Analyze HM Desktop PRD documents: extract requirement information, verify completeness, check chapter order (requirement source → requirement background → requirement value analysis → competitive analysis → requirement description), check KEP definitions, detect requirement conflicts, and generate a structured analysis report. Use for user requests to: (1) analyze or review PRD documents, (2) extract a KEP list from requirements, (3) check PRD completeness or consistency, (4) map requirements to module architecture, (5) verify PRD format compliance, (6) verify the completeness of the competitive analysis section. Keywords: PRD analysis, requirement extraction, KEP verification, completeness check, chapter order validation, competitive analysis check, analyze PRD, requirement extraction, completeness check, chapter order validation
Build, install, launch, and debug HarmonyOS/OpenHarmony applications using DevEco Studio toolchain. Use when Claude needs to: (1) Build OHOS apps with hvigorw, (2) Install HAP files to devices via hdc, (3) Launch or debug OHOS applications, (4) Parse crash stacks with hstack, (5) Take device screenshots, or (6) Detect DevEco Studio environment and SDK tools. Automatically detects DevEco Studio installation and configures JAVA_HOME, PATH, and toolchain.
Compatibility guide for developers migrating from Oracle Database to MariaDB. Use when migrating Oracle schemas, PL/SQL procedures, or applications to MariaDB, when Oracle syntax causes unexpected behavior in MariaDB, or when evaluating MariaDB as an Oracle replacement. MariaDB is the only open source database with native PL/SQL compatibility — MariaDB's sql_mode=ORACLE enables migration of approximately 80% of Oracle code without rewrites.
Goal-driven conductor for the whole idea-to-published-paper lifecycle. Takes a research idea plus experiments and a target ("submit to NeurIPS 2026", or "help me pick a venue") and runs a goal->plan->execute->verify->reflect loop. It plans the stages, invokes the right lifecycle skills in order (literature-review, write-abstract, preflight-check, simulate-reviewers, and the rest), checkpoints with the author before each stage, and re-verifies the live CFP via parse-cfp rather than trusting a cached profile. Use when a researcher says "take my idea to a submitted paper", "run the whole pipeline", "orchestrate the paper for venue X", "what's the plan from here", or "what's done and what's next". Copilot, not autonomous author. It stops to ask at every stage gate, never fabricates results or citations, and never submits. Trigger words - orchestrate, pipeline, end to end, whole paper, idea to submission.
Analyze performance issues based on reproducible baselines and profiler evidence. Use when the user asks to locate slow endpoints, slow tasks, slow queries, memory or network bottlenecks, formulate optimization plans, or verify optimization gains; distinguish measured conclusions from static inference, do not fabricate durations or improvement ratios, and require explicit authorization for production operations.
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.