Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when the user says 'figma to bricks', 'build this figma design in bricks', or hands over a Figma frame to rebuild on a Bricks Builder site. Maps the Figma node tree to native Bricks elements with BEM global classes, imports the frame's palette into the Bricks design system, and writes to a draft, so nothing live is touched.
AI screenplay/script writer for film and video. Use when: writing scripts, screenplays, dialogue, scenes, story beats, character development. Generates production-ready scripts. Keywords: script, screenplay, writing, dialogue, scenes.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues
Selects a base model and fine-tuning technique (SFT, DPO, or RLVR) for the user's use case by querying SageMaker Hub. Use when the user asks which model or technique to use, wants to start fine-tuning, or mentions a model name or family (e.g., "Llama", "Mistral") — always activate even for known model names because the exact Hub model ID must be resolved. Queries available models, validates technique compatibility, and confirms selections.
Any live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site URLs, bulk extraction, downloading a site, change alerts, or pages needing clicks/login — web only; local files route to firecrawl-parse. For US legal or regulatory questions use gov; for papers use firecrawl-research-index; for library, API, error, or bug questions use firecrawl-developer-index.
Verify rendered Flutter interfaces through screenshots, golden tests, breakpoint comparisons, state matrices, and structured visual critique. Use when asked to compare designs, inspect polish, validate responsive or theme behavior, diagnose visual regressions, or confirm implementation quality after UI changes.
Futu OpenAPI trading and market data assistant. Query quotes, K-lines, prices, snapshots, order books, tick-by-tick trades, and intraday data; search securities and news; parse option codes and query option chains, expiry dates, IV, and exercise probability; place buy/sell orders, cancel and modify orders; query positions, funds, accounts, and orders; subscribe to real-time pushes; cryptocurrency (BTC/ETH) quotes and trading; prediction markets (Event Contract, Combo quote requests); indicator lists and calculations (MA/MACD/RSI/KDJ/BOLL); quick API reference. Use automatically when the user mentions quotes, prices, K-lines, snapshots, order books, order book display, trades, intraday, search, news, announcements, buy, sell, place order, cancel order, trade, positions, funds, account, orders, entrust, futu, API, stock screening, sectors, options, option chain, strike price, expiry date, Call, Put, call, put, cryptocurrency, BTC, ETH, earnings, results, income statement, balance sheet, cash flow, revenue breakdown, analyst ratings, target price, Morningstar report, valuation, PE, PB, PS, dividends, payout, buyback, share split/consolidation, shareholders, holding changes, increase holdings, decrease holdings, institutional holdings, insider trading, company profile, executive information, operating efficiency, top ten brokers, short selling, short interest, implied volatility, IV, option exercise probability, event contracts, prediction markets, EC, pred_side, amount, quote_id, combo quote requests, request_combo_quotes, Kalshi, indicators, technical indicators, indicator.
Use Chrome DevTools Protocol to allow the AI to "ask Gemini" or "research with Gemini" directly. This uses the user's logged-in Chrome session, bypassing API limits and leveraging the web interface's reasoning capabilities.
Convert genomic intervals between coordinate conventions, normalise and compare variant representations, and detect assembly or contig-naming mismatches before they corrupt an analysis. Use whenever coordinates cross a format, tool, or assembly boundary - converting between BED, GFF/GTF, VCF, SAM/BAM, WIG, PSL, genePred, Picard interval_list, or region strings; reconciling 0-based half-open with 1-based inclusive; left-aligning or trimming indels; checking whether two variant records describe the same change; mapping genomic to transcript, CDS, or protein positions; auditing a BED/GTF/VCF for convention violations; or diagnosing GRCh37 vs hg19 vs GRCh38 vs T2T, chr-prefix, and liftover problems. Triggers include "off by one", "0-based", "1-based", "half-open", "coordinate system", "left-align", "normalize variant", "bcftools norm", "chr prefix", "wrong genome build", "liftover", "REF mismatch", and "HGVS".
Provides geospatial and Earth observation workflows using GeoPandas, Rasterio, GDAL, Xarray, Shapely, Laspy, PDAL, Google Earth Engine, and STAC/Planetary Computer, covering Sentinel, Landsat, MODIS, SAR and hyperspectral imagery, spectral indices, terrain and network analysis, point clouds, COGs, CRS handling, and spatial ML, with code in Python, R, Julia, JavaScript, C++, Java, Go, and Rust. Use when computing NDVI or other indices from satellite imagery, when running vector overlays, reprojection, or spatial statistics on shapefiles, GeoJSON, or GeoPackage data, when searching STAC catalogs and reading cloud-optimized GeoTIFFs, when classifying land cover or training ML models on Earth observation data, or when doing terrain, hydrology, or point cloud analysis. Not for general non-spatial data analysis or tabular ML.
Geospatial vector analysis extending pandas. Read/write spatial formats (Shapefile, GeoJSON, GeoPackage, Parquet, PostGIS), CRS handling, geometric ops (buffer, simplify, centroid, affine), spatial analysis (joins, overlays, dissolve, clipping, distance), visualization (choropleth, interactive maps, basemaps). Use for spatial joins, overlays, CRS transforms, area/distance, maps.
GSLIB-inspired geostatistics library for variogram analysis, kriging, and simulation. Use when the agent needs to: (1) Calculate experimental variograms, (2) Fit variogram models, (3) Perform simple/ordinary kriging, (4) Run sequential Gaussian simulation (SGSIM), (5) Apply normal score transforms, (6) Decluster spatial data, (7) Generate multiple realizations for uncertainty.
Create high-quality git commits: review/stage the intended changes, split them into logical commits, and write clear commit messages (following the Conventional Commits spec, with Emoji support). Use this skill when the user asks to commit code, write commit messages, stage changes, or split work into multiple commits. When the user mentions the 【breaking change】 keyword, you must write the commit message using the exclamation mark format per this skill's BREAKING CHANGE spec. Prefer committing the files in the git staging area (staged); only consider the entire working tree when the staging area is empty. When the user mentions the 【categorize】 keyword, you must carefully split multiple commits along this skill's multi-commit split spec, across the four dimensions of file type, business module, change type, and change scope.
Use the GLM vision MCP for image understanding and analysis. Trigger conditions: (1) the user asks to analyze an image, understand an image, or describe image content (2) objects, text, or scenes in an image need to be recognized (3) the GLM visual understanding capability is to be used
Extract text from images using GLM-OCR API. Supports images and PDFs with high accuracy OCR, table recognition, formula extraction, and handwriting recognition. Use this skill whenever the user wants to extract text from images, perform OCR on pictures, scan documents, convert images to text, or process any image files to get their textual content.
Google-grounded SEO/GEO implementation for Search, AI Overviews, AI Mode, crawlability, indexability, snippets, structured data, ecommerce/local details, and agent browsing. Do NOT use for paid ads, rank tracking, non-Google directory tactics, or link schemes.
Evaluates GraphRAG systems across knowledge graph completeness, retrieval relevance, answer correctness, reasoning depth, and hallucination prevention. Provides structured evaluation frameworks, metric selection guidance, and testing protocols. Use when evaluating GraphRAG quality, benchmarking multi-step reasoning, measuring hallucination reduction, or when user mentions evaluate GraphRAG, quality metrics, answer correctness, test my GraphRAG, or measure RAG performance.
Stress-test a plan through questions while recording the resulting domain terms and lasting architectural decisions. Use when the user asks to grill a plan with docs, or to record its terms and decisions while questioning it. For questions alone, use `grilling`.
Full grouchygiraffe ingestion workflow — given a grouchygiraffe media file path, a loose image such as a pasted or screenshotted thumbnail, or a recipe URL (YouTube, Instagram, or any recipe page), identify the recipe, upload the thumbnail to Imgur where applicable, and write a cleaned recipe note to the vault.
Turn hand-made first-50 traction into self-reinforcing acquisition loops, so the next 5,000 users come from usage, not founder hours. Use when growth stalls the moment the user stops pushing, every signup traces back to a DM or one launch spike, or they're reaching for "more channels" when the real gap is that using the product creates no new users.
Build or review Astro animation: GSAP page transitions, ClientRouter swap hooks, persisted islands, repeated setup, and cleanup. Use for missing or duplicated motion after navigation and choosing transition:animate versus GSAP. Without ClientRouter, use gsap-vanilla. Also covers hidden-content recovery and first-load performance. Not for standalone island frameworks or isolated GSAP API questions.
Fast-track GTM value preview for new users. Runs gtm-analytics-audit and gtm-strategy back to back and outputs the top 5 tracking opportunities with business rationale and effort estimates. No implementation, no DOM changes. Just a clear answer to "what should I track and why". Trigger on - "quickstart", "what should I track", "show me tracking opportunities", "quick GTM overview", "I'm new to GTM", "where do I start".
Generate, refactor, run, and review HALCON HDevelop (`.hdev`) and HDevelopEVO (`.hscript`) programs with accurate operator usage, parameter defaults, value ranges, and practical vision pipelines. Use when the user asks for HDevelop or HScript code, operator selection, debugging logic, converting requirements into vision scripts, or building reusable procedures.
Hike Capital file publishing CLI: turn local HTML pages (including images on the page) into publicly accessible URLs (h.hikecapital.com)—the goal is a public link, not a chat attachment. Use this skill to upload to h.hikecapital.com whenever the user wants to publish, launch, host, upload, or send an .html file; asks for “a clickable link” or “send me a URL”; or wants to share a webpage link with LPs or investors. Also covers three management operations: ① re-upload and overwrite an updated file (“the link must not change,” “upload it again”; overwriting a file with the same name keeps the URL unchanged, so existing links remain valid); ② list or query files they have published; ③ delete published files. Call it as usual even if public sharing has not been confirmed—the skill’s own workflow handles confirmation before publishing. Boundary: use lark-drive to send a file as an attachment to a Feishu group or person; do not use this skill just to create or edit HTML without a request for a public link (but if the generated HTML is to be published publicly, use this skill for the publishing step).
Design, update, and refactor Home Assistant Lovelace dashboards (YAML views/partials) with a constrained, machine-safe design system: button-card-first structure, minimal card-mod styling, optional flex-horseshoe + mini-graph telemetry, strict grid/vertical-stack layout rules, centralized templates, deterministic ordering, and config validation. Use for Home Assistant dashboard work (especially config/dashboards/**), when refactoring views, adding infra/home/energy/environment panels, or translating Stitch design inspiration into safe Lovelace YAML.
Create attention-grabbing hooks and headlines using 15 proven formulas, sticky techniques, and the 4 U's test. This skill provides systematic frameworks for generating volume (10+ options) and selecting the best performers. Use for newsletter subject lines, social media hooks, blog headlines, or any content that needs to stop the scroll.
Removes the AI flavor from Chinese text so it reads like it was written by a human. Use when editing, reviewing or rewriting Chinese content. A Chinese localization of blader/humanizer (Wikipedia "Signs of AI writing"), combined with Chinese community discussions, AIGC detection research (CCL 2023 and others) and a practical word list. Identifies and fixes Chinese-specific AI writing patterns: grand openings, uplifting endings, lecture-style signpost words, the "not X but Y" binary construction, piled-up parallelism and antithesis, internet jargon, Europeanized translationese, dash abuse, overly dense punchlines, templated paragraphs and more.
Provides cryptocurrency trading data analytics including smart money tracking, whale monitoring, market data queries, and trader statistics. Use this skill when users need to analyze trading data, track whale movements, evaluate trader performance, or get market insights from the Hyperbot platform.
Interactive Brokers — global stocks/forex/futures via a LOCAL TWS/IB Gateway, not cloud. Covers stocks, ETFs, forex, futures; account, positions, orders, quotes, history, order placement. Use when the user wants to check or trade an Interactive Brokers account (e.g. "IBKR positions", "buy 10 AAPL on IBKR paper", "my IB account net liq"). Requires a running TWS / IB Gateway — NOT a cloud key.
Build, validate, or expand your ICP (Ideal Customer Profile) using the GAP method, SPICED framework, and customer interview pipeline. Triggers on 'build your ICP,' 'check your ICP,' 'ICP validation,' 'ICP quality,' 'you don't have an ICP,' 'ICP is too broad,' 'who should we sell to,' 'segment our market,' 'ICP workshop,' 'customer interviews for ICP,' 'GAP method,' 'ICP expansion,' 'Goldilocks zone,' 'tier our customers,' 'A/B/C segmentation,' 'are we targeting the right customers,' 'segmentation check,' 'ICP review,' 'who are we actually selling to,' 'score our accounts,' 'ICP scoring,' 'fit score,' 'TAM list,' 'target list,' 'build our market list,' or any situation where your ICP is missing, broken, or needs validation. This skill covers the full ICP lifecycle: validate what exists, build from scratch, score every company 0-100 on fit, produce and maintain the TAM list, refine with interviews, and plan expansion. BOUNDARY: For positioning/messaging (step AFTER ICP), see positioning-messaging-designer.
Generate a weekly Instagram content plan from a theme, audience, and content pillars. Produces a per-day mix of Reels, carousels, single images, and stories, each with a hook formula, angle, posting time, and primary goal, plus a weekly saves-and-shares goal (the 2026 lever), a story cadence, and a balance check across saves, shares, comments, and follows. Use to plan a week instead of ad-hoc posting. Not for drafting one caption (use ig-caption-writer) or one carousel (use ig-carousel-planner).
Master router for immersive visual experiences combining React Three Fiber, shaders, particles, post-processing, GSAP animation, and audio. Use when building 3D web experiences, visualizers, creative coding projects, interactive installations, or any project requiring multiple visual technologies. Dispatches to 6 specialized domain routers covering 29 total skills.
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.