Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Use this skill for proactive backend health audits in an InsForge project — security misconfigurations, performance regressions, and system health issues surfaced by `diagnose advisor`, plus the backend-side deep-dives that pair with each advisor issue. Also use this skill when a user reports backend-wide performance degradation (high CPU/memory, all responses slow, connection pool exhaustion, lock contention) without a single failing request. Trigger on requests like "health check", "audit my backend", "review security", "check RLS policies", "find slow queries", "backend performance review", "high CPU/memory", "everything is slow", "EC2/database/system health", or pre-launch readiness audits. For reactive runtime errors with a single concrete failing request (SDK error objects, HTTP 4xx/5xx, function failures, deploy failures), use `insforge-debug` instead.
Extract content from news sites. Supports 12 platforms: WeChat Official Accounts, Toutiao, NetEase News, Sohu News, Tencent News, BBC News, CNN News, Twitter/X, Lenny's Newsletter, Naver Blog, Detik News, and Quora. Activate when the user needs to extract news content, scrape official account articles, crawl news, or obtain news in JSON/Markdown.
Configures the analytics side of a PostHog experiment — exposure criteria (server-resolved default exposure event vs custom exposure events), primary and secondary metrics, the supported metric types (count, sum, ratio with `math` and `math_property`, retention with `retention_window_start` and `start_handling`), multivariate user handling ("Exclude from analysis" vs "Use first seen variant"), and how to read results once the experiment is live. Use when the user adds or edits a primary or secondary metric (e.g. "add a secondary metric tracking 'downloaded_file' per user"), sets up a ratio metric (e.g. "revenue from purchase_completed / pageviews"), sets up a retention metric (e.g. "$pageview → uploaded_file, 7-day window"), configures custom exposure (e.g. "only count users who hit /checkout"), changes multivariate handling, or asks "who is in the analysis?", "how do I measure impact?", "is this winning?", "what's the confidence level?", or "should I ship?"
Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.
Web research skill using Tavily API for search, extract, crawl, map, and structured research tasks. Use when you need the latest information, to extract content from URLs, or to discover site structure. Triggers: tavily, web search, search web, latest info, extract, crawl, map, research, 搜索网页, 查资料, 最新
Multimodal product image similarity analysis and grouping. Trigger this skill when the user mentions product image similarity, visual grouping, finding visually similar products, image-based deduplication, competitor product matching, clustering identical products, grouping by appearance, image similarity, product image comparison, visual clustering, same-style recognition, appearance deduplication, or image grouping. Also trigger it even if the user does not explicitly say “image similarity” whenever their intent involves comparing product hero images, visual clustering, identifying visually identical or similar products, or post-processing product lists based on visual features such as appearance, color, or composition.
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization
Implement the Syncfusion Blazor Chart (SfChart) component for comprehensive data visualization. Use this when creating line charts, bar/column charts, area charts, financial charts, or statistical visualizations. This skill covers 30+ chart types, including scatter plots, bubble charts, candlestick charts, and specialized charts like waterfall, histogram, and polar charts for Blazor applications.
Authors Apache Airflow DAGs declaratively from dag-factory YAML configs. Use when building DAGs declaratively from YAML via dag-factory; creating/editing dag-factory templates/YAML configs,reating/editing dag-factory YAML configs, defaults, dynamic tasks, datasets, or callbacks; or validating dag-factory configurations; upgrading or re-pinning dag-factory.
Multi-omics integration — orchestrate per-layer analysis (transcriptomics, proteomics, epigenomics, genomics, metabolomics) then perform cross-omics correlation, multi-omics clustering, and pathway-level integration. Use for integrative systems-biology analysis, multi-modal disease characterization, and cross-omics biomarker discovery
Generate Power BI report visual design guidance before PBIR files are written. Use when the user wants to: (1) choose tone, signature, page archetypes, chart types, layout, color, typography, theme direction, or accessibility approach, (2) redesign/restyle an existing report, apply a brand, or critique chart/layout choices, (3) produce a design contract for `powerbi-report-authoring`. For end-to-end requirements, approval, and build sequencing, use `powerbi-report-planning`. Triggers: "design Power BI report", "make dashboard look professional", "choose chart type", "apply brand to report", "redesign report", "create design brief", "Power BI report design archetype".
Use when the user asks about token prices, charts, holders, trending tokens, pair data, wallets, balances, launchpads, token risk, liquidity locks, prediction markets, or any on-chain analytics from Codex. Also use when building GraphQL queries against https://graph.codex.io/graphql or migrating from Birdeye, Mobula, CoinGecko, Bitquery, Dune Sim, or Serialized. TRIGGERS: token price, token chart, OHLCV, trending tokens, token screener, pair data, holders, top holders, wallet PnL, wallet trades, wallet balances, portfolio, top traders, smart money, launchpad, pump.fun, bonding curve, graduation, new tokens, token risk, rug check, honeypot, buy tax, sell tax, liquidity locked, token categories, memecoins, AI tokens, prediction markets, Polymarket, Kalshi, event odds, prediction traders, trader leaderboard, trader PnL, prediction charts, outcome probability, open interest, prediction categories, betting markets, market resolution, prediction positions, prediction trades
Use this skill to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables. **Trigger when user asks to:** - Analyze database tables for hypertable conversion potential - Identify time-series or event tables in an existing schema - Evaluate if a table would benefit from Timescale/TimescaleDB - Audit PostgreSQL tables for migration to Timescale/TimescaleDB/TigerData - Score or rank tables for hypertable candidacy **Keywords:** hypertable candidate, table analysis, migration assessment, Timescale, TimescaleDB, time-series detection, insert-heavy tables, event logs, audit tables Provides SQL queries to analyze table statistics, index patterns, and query patterns. Includes scoring criteria (8+ points = good candidate) and pattern recognition for IoT, events, transactions, and sequential data.
Query Apple Health SQLite database for vitals, activity, sleep, and workouts. Supports Markdown, JSON, and FHIR R4 output formats. This skill should be used when analyzing health metrics, generating health reports, answering questions about fitness or sleep patterns, or exporting health data in standard formats.
Retrieve and download Amazon seller store reports. Supports requesting, polling status, downloading, and extracting more than 95 report types, including inventory, orders, sales and traffic, FBA, financial settlements, returns, and Brand Analytics, and generates a downloadable URL for the extracted files. Trigger this skill when the user mentions pulling or downloading Amazon reports, inventory reports, order reports, sales and traffic reports, Business Report, FBA reports, settlement reports, returns reports, Brand Analytics, ABA search terms, Amazon store reports, or pulling or downloading Amazon reports. Also trigger it when the user wants to bulk export structured business data for a time period from Amazon Seller Central, even if they do not explicitly say “report.” For a small number of real-time orders, products, or prices, prefer the corresponding dedicated skill. This skill depends on linkfox-amazon-store-auth.
Look up patent bibliographic data in the PatSnap database by patent ID or publication number. Trigger this skill when the user mentions patent bibliographic data, patent metadata, applicant or inventor lookup, patent classification, abstract retrieval, citation analysis, priority claims, citations in patent applications, patent examiner information, PatSnap, or patent citations. Also trigger it when the user needs detailed metadata for a specific patent by patent ID or publication number, even if they do not explicitly mention bibliographic data.
Minimal Chrome DevTools Protocol tools for browser automation and scraping. Use when you need to start Chrome, navigate pages, execute JavaScript, take screenshots, or interactively pick DOM elements. Triggers include "browse website", "scrape page", "take screenshot", "automate browser", "extract DOM", "web scraping".
Configures the rollout shape of a PostHog experiment — the variant split (50/50, 80/20, A/B/C ratios), the overall rollout percentage that gates how many users enter the experiment, and the disambiguation when a percentage like "roll out to 25%" could mean either. Use when the user mentions a rollout percentage, variant split, or traffic distribution; gives a ratio like 60/40, 70/30, or 80/20; asks "who sees the test variant?"; wants to increase, decrease, or change the rollout or split on a draft or running experiment; weighs equal vs uneven splits; or proposes a mid-experiment split change (often an anti-pattern that needs reset or end-and-restart).
Investigates a session recording by gathering metadata, person profile, same-session events, and linked error tracking issues in one pass. Use when a user provides a recording or session ID and wants to understand what happened — who the user was, what they did, what errors occurred, and whether there are related error tracking issues. Replaces the manual chain of session-recording-get, persons-retrieve, execute-sql, and query-error-tracking-issues-list.
SIF overview analysis of keyword competition in the Amazon marketplace. Trigger this skill when the user mentions keyword competition, supply-demand ratio, competitor count, keyword search volume estimates, market competitiveness assessment, keyword popularity rankings, ad competition analysis, the number of products under a keyword, keyword competition, supply-demand ratio, competitor count, search popularity, market competition analysis, SIF, or keyword overview. Trigger it even if the user does not explicitly say “SIF,” as long as their request involves assessing keyword-level competitive intensity, supply-demand balance, or the number of products in Amazon search results.
Create a new SigNoz dashboard from a natural-language intent: import a curated template (PostgreSQL, Redis, JVM, k8s, hostmetrics, APM, LLM, etc.) when one fits, or build a custom dashboard from scratch with metric / trace / log panels. Make sure to use this skill whenever the user says "create a dashboard for…", "set up monitoring for…", "build me a dashboard…", "I need observability for…", "import a dashboard template", or asks to track / visualize a service, database, cluster, or AI/LLM platform, even if they don't explicitly say "dashboard". Also use it when someone wants to "monitor", "watch", or "see metrics for" a technology and the natural answer is a dashboard.
Create and manipulate Excel XLSX files programmatically. Use when the user needs to generate spreadsheets, modify XLSX templates, extract spreadsheet content, or automate Excel workflows. Supports both template-based generation (for branding compliance) and from-scratch creation. Keywords: Excel, XLSX, spreadsheet, workbook, worksheet, data, report, template, financial, analysis.
Automate all Feishu (Lark) channels. Use the lark-mcp tool to work with Feishu Bitable, send messages, manage documents, create groups, automate workflows, and more. Use this skill when the user needs to operate the Feishu platform, sync data to Feishu tables, send Feishu notifications, manage Feishu documents, or automate Feishu business processes.
Use SIF data to reverse-search traffic keywords for any Amazon ASIN, including organic ranking, ad ranking, search volume, traffic share, organic/paid scores, ABA TOP3 click concentration, click-to-purchase conversion rate, year-over-year search volume changes, and weekly/monthly time windows. Trigger this skill when the user mentions ASIN keyword analysis, ASIN reverse lookup, traffic keyword research, organic ranking lookup, ad ranking lookup, keyword position tracking, SIF keyword data, competitor keyword research, identifying which keywords drive traffic to a product, analyzing keyword performance for a specific ASIN, weekly/monthly/recent N-day keyword time windows, ASIN reverse keyword lookup, traffic keywords, organic ranking, ad ranking, search volume, SIF keywords, competitor keyword reverse lookup, click concentration, click-to-purchase conversion, or week-over-week search volume. Even if the user does not explicitly mention "SIF," trigger this skill whenever their request involves finding keywords associated with a specific Amazon product (ASIN).
Diagnose and manage Alibaba Cloud databases through natural language. Use when users need to troubleshoot database performance issues (high CPU, slow queries, abnormal connections, lock waits), check instance status, analyze disk space, optimize SQL, run health inspections, or detect security baseline violations. Supports RDS (MySQL/PostgreSQL/SQL Server), PolarDB, MongoDB, Redis (Tair), and Lindorm. Trigger this skill even for casual descriptions like “my database is slow”, “can't connect to the database”, “help me check this SQL”, or “database disk is almost full”. Also suitable for consulting Alibaba Cloud-specific database features (e.g., PolarDB Serverless, DAS autonomy capabilities) and comparing product differences (RDS vs PolarDB). Do NOT use this skill for general SQL tutorials, non-Alibaba Cloud databases, or local database administration.
Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging diagnostics, and tier sizing. Supports Kafka, Atlas clusters, S3, HTTPS, and Lambda integrations for streaming data workloads and event processing. NOT for general MongoDB queries or Atlas cluster management. Requires MongoDB MCP Server with Atlas API credentials.
Automatically generate Excel reports from data sources including CSV, databases, or Python data structures. Supports data analysis reports, business reports, data export, and template-based report generation using pandas and openpyxl. Activate when users mention Excel, spreadsheet, report generation, data export, or business reporting.
Extract structured data from multiple web pages using Playwright with built-in ethical crawling practices including rate limiting, robots.txt compliance, and error monitoring. Use when asked to "scrape data from", "extract information from pages", "collect data from site", "crawl multiple pages", or when gathering structured data from websites. Supports pagination, multi-page extraction, data aggregation, and export to CSV/JSON/Markdown. Works with browser_navigate, browser_evaluate, browser_wait_for, and browser_snapshot tools.
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.
Generate, write, or run an ad hoc query against SigNoz observability data (metrics, logs, or traces) without wrapping it in a dashboard panel or alert. Use this skill whenever the user asks "show me error rates", "query logs for timeout errors", "what's the p99 latency for the cart service", "how many requests hit the payment endpoint", "find slow traces", "errors in the last hour", or another exploratory question requiring live observability data, even if they don't explicitly say "query" or "search"
Investigate LLM spend in PostHog: total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?", "why did cost spike?", wants to build a cost dashboard or alert, or pastes a trace URL and asks about its cost.
Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.
Jungle Scout product database with multi-criteria filtering for Amazon products by category, price, sales, revenue, reviews, rating, weight, BSR rank, LQS, seller type, and more, covering 10 marketplaces. Trigger this skill when users mention Amazon product research, product database filtering, BSR rank filtering, category-based product research, high-rated low-competition products, FBA product research, Amazon product search, product filtering, Amazon product database, product research, product filtering, BSR rank filter, category product search, niche product finder, FBA product search, Amazon product discovery, low competition products, or Jungle Scout product database. Trigger it even if the user does not explicitly mention “Jungle Scout” or “product database,” as long as their request involves filtering Amazon products by multiple criteria or discovering promising products.
Jungle Scout ASIN sales estimate lookup. Returns daily estimated sales and the latest known price for a specified ASIN over a period of time, covering 10 marketplaces including the US, UK, Germany, and Japan. Trigger this skill when users mention ASIN sales estimates, daily ASIN sales, sales estimates, competitor sales monitoring, average daily sales, sales trends, product sales tracking, Jungle Scout sales data, sales estimates, daily sales, estimated units sold, ASIN sales tracking, competitor sales monitoring, product sales trend, or daily unit sales. Even if the user does not explicitly mention “Jungle Scout”, trigger this skill whenever they need daily sales estimates for an Amazon ASIN over a period of time.
Analyze metabolomics data end-to-end — metabolite identification, quantification (TIC normalization, batch correction), differential analysis, and pathway interpretation. Use for processing mass-spec metabolomics output, normalization choice, untargeted metabolomics workflows, and integrating with other omics layers.
Databricks SQL (DBSQL) advanced features and SQL warehouse capabilities. This skill MUST be invoked when the user mentions: "DBSQL", "Databricks SQL", "SQL warehouse", "SQL scripting", "stored procedure", "CALL procedure", "materialized view", "CREATE MATERIALIZED VIEW", "pipe syntax", "|>", "geospatial", "H3", "ST_", "spatial SQL", "collation", "COLLATE", "ai_query", "ai_classify", "ai_extract", "ai_gen", "AI function", "http_request", "remote_query", "read_files", "Lakehouse Federation", "recursive CTE", "WITH RECURSIVE", "multi-statement transaction", "temp table", "temporary view", "pipe operator". SHOULD also invoke when the user asks about SQL best practices, data modeling patterns, or advanced SQL features on Databricks
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and experiment-craft (5-step diagnostic on failure). Use when the user has a planned experiment, needs to reproduce baselines, organize experiment workflow, or systematically validate a method. Do NOT use for debugging a specific experiment failure (use experiment-craft) or designing which experiments to run (use paper-planning).
Integrate Firecrawl `/scrape` into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.
Jungle Scout keyword expansion tool that expands seed keywords into lists of related keywords, with data such as search volume, trends, PPC bids, and ranking difficulty, across 10 Amazon marketplaces including the US, UK, Germany, and Japan. Trigger this skill when users mention keyword expansion, keyword mining, long-tail keyword mining, related keywords, keyword suggestions, keyword research, PPC bid research, keyword competition, keyword discovery, Jungle Scout keywords, keyword expansion, keyword discovery, keyword scout, related keywords, long-tail keywords, keyword suggestions, PPC bid research, keyword competition, seed keyword expansion, or keyword mining. Trigger it even if the user does not explicitly mention “Jungle Scout,” as long as their request involves finding related keywords from a seed keyword and metrics such as search volume and competition.
Analyze an ASIN's traffic sources and exposure distribution using SIF (Search Intelligence Framework) data, including comparisons across the current and previous periods and newly added and removed terms. Trigger this skill when the user mentions ASIN traffic sources, traffic structure analysis, organic versus paid traffic share, exposure score breakdown, period comparisons, new or removed traffic keywords, competitor traffic analysis, SP ad keyword counts, brand ad exposure, Amazon's Choice exposure, editorial recommendation exposure, Top Rated exposure, video ad exposure, organic search exposure share, PPC traffic sources, deal traffic sources, recommendation placement breakdown, ASIN traffic analysis, traffic sources, organic traffic share, ad traffic share, exposure analysis, traffic structure, period-over-period comparison, keyword churn, or SIF. Trigger it even if the user does not explicitly mention “SIF,” as long as they want to analyze ASIN traffic sources, exposure channel distribution, period comparisons, or competitor traffic structures.
Query basic patent bibliographic data from the PatSnap patent database. Trigger this skill when users mention patent bibliographic information, basic patent details, patent bibliography, patent publication details, looking up inventors by patent number, patent applicant information, patent abstracts, patent classification codes (IPC/CPC), patent citations, or any request to retrieve structured metadata using a patent ID or publication number, as well as patent brief bibliography, patent basic info, patent number lookup, patent abstract, PatSnap, or patent metadata. Trigger it even if the user does not explicitly mention “PatSnap” or “bibliographic information,” as long as their request involves querying key bibliographic fields for a specific patent.
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.