Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Read-only evo run reporting. Use when the user invokes /evo:report, asks what happened overnight, asks what improved recently, asks for the best/frontier candidates, asks for a quick score chart without opening the dashboard, or wants the scatter plot in chat output. Never run benchmarks, gates, Slurm commands, evo run, or ad-hoc verification scripts for report requests.
Use when options, a recommendation, or an already-chosen approach are on the table and the reasoning under them has not been independently checked — especially when the case rests on cited documentation, remembered behavior, or premises nobody verified. Not for generating alternatives, and not for critiquing a spec, which is /pushback.
Review code changes and identify high-confidence, actionable bugs. Use when the user wants to: - Review a pull request or branch diff - Find bugs, security issues, or correctness problems in code changes - Get a structured summary of review findings
Called by review-pr after its reviewer fleet and judgment pass return: consolidates their findings against the PR's history into the set of comments worth posting — pruning what the PR already covers, merging duplicates, subordinating defects under premise questions, bounding to the reviewed range, and rewriting every body in the caller's voice. Not for direct use
Called by review-pr in both modes: independently judges whether landing the whole change serves the project after its material consequences are considered. Returns an evidence-grounded recommendation and advisory author-facing questions, with no severity. Not for direct use.
Called by review-pr for each review thread it authored that is unresolved or that someone else resolved: judges from the thread, the author''s replies, and the current code whether the original concern is addressed, stale, or still standing, and returns exactly one disposition with a drafted reply where one is needed. Not for direct use.
Test Riverpod providers and widgets; ProviderContainer.test, unit tests, widget tests with ProviderScope, tester.container(), mocking with overrides, container.listen for auto-dispose, awaiting .future. Use when writing unit or widget tests for Riverpod code, mocking providers, or testing with overrides. Use this skill when the user asks about testing Riverpod, mocking providers, or ProviderContainer in tests.
Use when building, animating, or debugging Roblox GUI elements including HUDs, menus, world-space UI, and player labels. Triggers on: ScreenGui setup, SurfaceGui or BillboardGui placement, UDim2 sizing questions, TweenService UI animations, responsive scaling, LocalScript GUI logic, ResetOnSpawn issues, or any Frame/TextLabel/ImageButton layout work.
RouterOS firewall filter, NAT, mangle, and address-list configuration. Use when: writing firewall rules in RouterOS, configuring NAT, setting up address-lists or interface-lists, writing idempotent firewall scripts, configuring DNS redirect or port forwarding, or when the user mentions /ip/firewall, chain=forward, chain=input, connection-state, address-list, interface-list, or layer7-protocol on MikroTik.
Enriches contacts and companies with verified emails, phones, and firmographic data — single-record, batch, and waterfall enrichment with credit optimization. Use when contact data is missing emails or phones, lead records are incomplete or outdated, enrichment credits are burning too fast, you need to enrich a batch of leads before a campaign, or a single enrichment provider isn't catching enough data. Do NOT use for building new prospect lists from scratch (use /sales-prospect-list), interpreting buying signals (use /sales-intent), CRM data hygiene and deduplication (use /sales-data-hygiene), ZoomInfo-specific enrichment config (use /sales-zoominfo), Clearbit/Breeze Intelligence platform help (use /sales-clearbit), RB2B platform help (use /sales-rb2b), 6sense platform help (use /sales-6sense), general Apollo platform help (use /sales-apollo), Clay platform help (use /sales-clay), or LeadMagic platform help (use /sales-leadmagic).
Set up and run Airtable-based sales operations and CRM workflows — pipeline management, account and renewal management, deal desk, RFP / tender pipelines, partner CRMs, sales forecasting, vertical CRMs (real estate, mortgage, brokerage, capital markets, public works, nonprofit), and AI-native lean stacks (Clay-equivalent enrichment, AI-assisted outbound, conversation-intel ingestion). Use when the user wants to track deals, manage accounts, build a pipeline, run a deal desk, coordinate partners, manage RFPs, or build an AI-forward GTM stack. Defaults to augmenting existing CRMs (Salesforce / HubSpot); also supports Airtable-as-CRM and AI-native stacks. Asks scope first. Commercial workflows only; post-sale support belongs to a future customer-success skill.
Generates annotated screenshot documentation for web apps and websites — local dev servers or live sites. Use when asked to "screenshot the app", "document the app", "visual docs", "screenshot documentation", "show me the app", "screenshot <url>", or "document this website".
Sentry-specific security review based on real vulnerability history. Use when reviewing Sentry endpoints, serializers, or views for security issues. Trigger keywords: "sentry security review", "check for IDOR", "access control review", "org scoping", "cross-org", "security audit endpoint".
Use to deploy an Omni PresenceUserConfig (presence configuration) as one whole-record Metadata write with the decline/ACW fields set consistently: Auto-Accept off, Decline on, Decline Reason on (with a PresenceDeclineReason deployed in the same package), and an After-Conversation-Work wrap-up timer. Agents are assigned by username. Idempotent via the Metadata API files[].state signal. Triggers: create presence configuration, enable decline + decline reason + ACW wrap-up timer for agents, assign presence config to users. Do not use for ServicePresenceStatus (separate skill), for permission-set access to statuses, or to set the channel-level ACW timer on a ServiceChannel.
Use to assign the Salesforce-shipped standard ContactCenterSupervisor PermissionSet (default) to N existing supervisor users via PermissionSetAssignment DML. Idempotent — SOQL detects existing (user, perm-set) pairs before POST, and DUPLICATE_VALUE is treated as reused. The standard set carries its own permission-set license and assigns cleanly on Service-Cloud-enabled orgs; a user whose license lacks the entitlement surfaces FIELD_INTEGRITY_EXCEPTION so the operator can fix the profile/license. Triggers: assign the supervisor permset, grant supervisor perms, complete supervisor provisioning. Do not use on production orgs or to assign agent permsets.
Use to populate the Omni-Channel Supervisor action + tab surface on an existing OmniSupervisorConfig by inserting the standard OmniSupervisorConfigAction and OmniSupervisorConfigTab companion rows via the Data API, idempotent (inserts only the missing types). Requires an OmniSupervisorConfig from service-omni-supervisor-config-deploy. Triggers: give the supervisor the standard action buttons and tabs, add Wallboard/Agents/Queues tabs to Omni Supervisor, configure supervisor actions like Change Queues/Skills. Do not use to create the supervisor configuration itself, create supervisor users, assign the supervisor permission set, or add custom-action / FlexiPage / AWS-dashboard / AI-agent surfaces (those need an external reference and must be set up in Setup).
Use to create N Omni-Channel supervisor users on a Salesforce org via Anonymous Apex, using the supervisor{i}.<suffix>@example.com pattern with SOQL-based idempotency (re-runs skip existing usernames). Passwords are set via System.setPassword and handled fail-closed: the wrapper proves no active debug TraceFlag before setting a password, and otherwise leaves the user ACTIVE and reset_required. Triggers: create supervisor users, provision supervisor accounts, scaffold supervisor personas. Do not use on production customer orgs (blocked by the safe_to_write guard), to bind supervisors to OmniSupervisorConfig (service-omni-supervisor-config-deploy), or to assign the ContactCenterSupervisor permission set (service-omni-supervisor-permset-assign).
Debug and troubleshoot Salesforce applications using debug logs, governor limit monitoring, error diagnosis, and performance profiling. Use when analyzing debug logs, diagnosing governor limit violations, interpreting stack traces, resolving common Salesforce errors, or profiling Apex performance. Activate on .log files, mentions of "debug", "governor limit", "error", "exception", "troubleshoot", "stack trace", or "performance issue".
Use at a checkpoint after real friction — a task where something was repeatedly confusing, a skill misfired or failed to fire, or a workaround was invented that should not have been needed. Concerns turning friction into a change to the skills themselves, and knowing when the right change is to cut rather than add. Trigger at session end after substantial work, or when the same problem has now happened more than once. Do NOT use reflexively after routine tasks, or mid-task.
Spring WebFlux for reactive programming in Spring Boot 3.x. Covers Mono/Flux, reactive operators, WebClient, functional endpoints, R2DBC integration, reactive error handling, and testing. Use for non-blocking high-concurrency apps. USE WHEN: user mentions "spring webflux", "reactive Spring", "Mono", "Flux", "WebClient reactive", "functional endpoints", "R2DBC", "non-blocking", "StepVerifier", "reactive streams" DO NOT USE FOR: traditional blocking MVC - use `spring-web` skill, simple REST APIs - use `spring-rest` skill, batch processing - use `spring-batch` skill
Microsoft SQL Server specific features. Covers data types, indexes, partitioning, and SQL Server-specific syntax. Use for SQL Server database work. USE WHEN: user mentions "sql server", "mssql", "IDENTITY", "GETDATE()", "temporal tables", "columnstore", "SQL Server specifics", "Azure SQL" DO NOT USE FOR: T-SQL programming - use `tsql` instead, PostgreSQL - use `postgresql` instead, Oracle - use `oracle` instead
Use when the user says 'find old content', 'what is stale', 'what needs refreshing', or 'what should i archive'. Categorizes pages and posts as fresh, aging, stale, or archive-candidate by age, traffic signal, and internal link count, with a refresh, redirect, or archive call per item.
Configuration and login management for the SwanLab experiment tracking platform. Trigger scenarios: (1) configure SwanLab login credentials (2) install/log in to SwanLab inside a container (3) configure SwanLab for a specified container (4) check SwanLab connection status. Supports multiple configuration sources: environment variables, config files, interactive input. Can be called by other skills via source scripts/functions.sh.
Implement Syncfusion ASP.NET Core Barcode components including BarcodeGenerator (1D codes like Code39, Code128, Codabar), QR Code Generator, and DataMatrix Generator. Use this when rendering barcodes, implementing QR codes with logo embedding, or generating DataMatrix codes. This skill covers barcode type selection, color and dimension customization, display text configuration, and export functionality (JPG, PNG, Base64).
Display temporal sequences with Syncfusion Timeline component. Supports vertical/horizontal orientations, flexible item alignment (Before/After/Alternate), rich templating for content and dots, content positioning strategies, and comprehensive event handling for item rendering lifecycle. Essential for chronological visualization in ASP.NET Core applications.
Extract tables, form fields, barcodes, and document layout from PDFs or images (scanned PDFs, PNG/JPG) using Syncfusion Smart Data Extractor. Trigger when users ask to parse/extract/convert document data (invoices, receipts, KYC/forms) into structured output and want C#/.NET integration code using the extractor.
Implements Syncfusion WinForms SfDataGrid component for displaying and managing tabular data in Windows Forms applications. Use this when working with data grids, column management (auto-generation, stacked headers), data operations (filtering, sorting, grouping), or grid editing with validation. The skill covers data summaries, selection modes, export capabilities (Excel/PDF), conditional styling, master-detail views, and drag-and-drop functionality.
Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.
Turns a support agent's ticket-resolution recording (e.g. a screen-share where they walked a customer through fixing an issue) into a clean, reusable how-to video that any future customer with the same issue can watch. Strips customer names, account-specific screen data, ticket numbers, and small talk, then reframes the narration around the general problem and solution rather than one customer's specific case. Use when the user says "turn this ticket resolution into a how-to video", "make this support recording reusable for other customers", "generalize this screen-share into a customer-facing clip", or "turn this ticket recording into a help video".
Produces a batch of short, deflection-style how-to videos from a list of top recurring support ticket topics: one focused video per topic, each built from whatever source material actually exists for that topic (a real resolution recording, a written description, or steps supplied on request). Aimed at cutting repeat ticket volume by giving customers a self-serve fix before they file again. Use when the user says "make how-to videos for our top 10 recurring tickets", "batch-produce deflection videos from this list of common issues", "turn these frequent support topics into videos", or hands over a list of recurring ticket topics and asks for videos against each.
Implements work already planned—a plan.md from tlc-plan or a small ticket—by freezing it into checks with proofs, building, and proving every check with a script and an independent Verifier before declaring done. Use when the user says “implement this plan”, “build this ticket”, “implement this spec”, “write the checks”, “verify work”, or “tlc-implement”. Do NOT use when nobody has decided what to build, or to plan a feature that needs one (that is tlc-plan).
Use when upgrading TYPO3 extensions to newer LTS versions (v11->v12, v12->v13, v13->v14 - v14.3 LTS is the current target), running Extension Scanner, Rector, Fractor, PHPStan, fixing deprecated APIs, or resolving compatibility issues. Also triggers on: migration, version upgrade, deprecated API, dual-version compatibility, Fluid 5 strict VHs, HashService removal, ext_tables.php split.
Root-cause investigation protocol for live, complex or multi-layer technical problems. Use when a problem has resisted two or more fix attempts, the root cause is unknown or assumed, you are about to retry a variation of a failed fix, or the user says "ultrathink protocol", "think deeper", "figure out why", "stop guessing", "find the root cause", or "it's still broken after your fix". Also use proactively when about to write a fix before the cause is verified. Once the incident is resolved and a write-up is wanted, use rca-report instead.
Unity multiplayer networking with NGO, Mirror, Photon, and Fish-Net. PROACTIVELY activate for: (1) building Unity multiplayer games, (2) Netcode for GameObjects (NGO) setup and patterns, (3) Mirror networking, (4) Photon PUN and Photon Fusion, (5) Fish-Net networking, (6) RPCs (ClientRpc, ServerRpc), (7) NetworkVariable and network synchronization, (8) lobby and matchmaking systems, (9) dedicated server hosting and Relay, (10) server-authoritative architecture, (11) lag compensation and prediction. Provides: networking-stack comparison, NGO templates, RPC patterns, NetworkVariable usage, lobby/matchmaking setup, and authoritative-server design.
Unity performance optimization for slow games, stutters, and FPS drops. PROACTIVELY activate for: (1) game is slow, stuttering, or has FPS drops, (2) Unity Profiler analysis, (3) Frame Debugger and draw-call investigation, (4) batching (static, dynamic, GPU instancing, SRP Batcher), (5) object pooling to reduce GC pressure, (6) garbage collection spikes and allocation hot paths, (7) memory leaks and Memory Profiler usage, (8) LOD and occlusion culling, (9) texture compression and mipmap settings, (10) build size reduction. Provides: profiling workflow, batching patterns, object-pool implementations, GC reduction techniques, LOD/culling setup, and texture-compression matrix.
Use when the user asks to assess or carry out JavaScript/TypeScript project upgrades, modernization, technology migrations, template syncs, or project standardization. Covers Prettier/Oxfmt, ESLint/Oxlint, Jest/Vitest, CJS/ESM, pnpm latest, NestJS latest, SWC, Prisma Client, Docker builds, .gitignore, AGENTS.md/CLAUDE.md and more, with two modes: assessing project gaps only, and making actual changes.
Comprehensive US stock analysis including fundamental analysis (financial metrics, business quality, valuation), technical analysis (indicators, chart patterns, support/resistance), stock comparisons, and investment report generation. Use when user requests analysis of US stock tickers (e.g., "analyze AAPL", "compare TSLA vs NVDA", "give me a report on Microsoft"), evaluation of financial metrics, technical chart analysis, or investment recommendations for American stocks.
Deep understanding of TikTok, YouTube, Instagram, and Facebook algorithms for 2025-2026. PROACTIVELY activate for: (1) Algorithm optimization, (2) Platform-specific strategy, (3) Content distribution understanding, (4) Engagement signal optimization, (5) Cold start strategies, (6) Trending and discovery, (7) Hashtag and SEO strategy, (8) Posting time optimization, (9) Cross-platform differences. Provides: Algorithm signal breakdowns, platform comparisons, optimization strategies, posting schedules, hashtag strategies, and discovery mechanisms.
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.