Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.
Deploy validated metadata to a Production Salesforce org without re-running tests. TRIGGER when the user wants to deploy to production, says 'quick deploy', 'promote', 'ship to prod', or has just validated and wants to push the change live. REQUIRES a recent `sf project deploy validate` job ID (≤10 days old, ≤3 days for --use-most-recent). DO NOT TRIGGER for sandbox/scratch deploys (use platform-metadata-deploy) or unvalidated deploys (use platform-deploy-validate first).
DAVIS problem analysis including root cause identification, impact assessment, and correlation with other telemetry. Use when querying or investigating detected problems. Trigger: "active problems", "root cause analysis", "problem impact", "affected users", "list problems", "P-12345 details", "recurring problems", "problem history", "problem trending", "blast radius", "which entity caused the problem", "problems affecting Kubernetes", "problems by service". Do NOT use for explaining existing queries, product documentation questions, generic log searching, distributed tracing, or host-level resource monitoring
Log querying, filtering, pattern analysis, and error rate calculation. Use when searching application or infrastructure logs, analyzing error patterns, or correlating log data. Trigger: "show error logs", "search logs for keyword", "log error rate", "recent errors", "logs from last hour", "find log entries", "top error messages", "log patterns", "parse JSON logs", "logs by process group", "log trends over time", "log entry counts per minute". Do NOT use for explaining existing queries, product documentation questions, distributed tracing or span analysis (use dt-obs-tracing).
Formats and parses locale-aware numbers, decimals, currencies, percentages, dates, durations, measurements, names, lists, byte counts, and URLs with Foundation FormatStyle and ParseableFormatStyle. Use when replacing legacy Formatter subclasses, designing reusable format APIs, using SwiftUI Text(_:format:), correcting availability, or testing user-facing formatted output across locales.
[DEPRECATED — use deepline-gtm] Use this skill for GTM prospecting, enrichment, qualification, and outbound workflows, especially when users mention Deepline, CSV processing, lead/account/contact research, waterfall enrichment, email or LinkedIn lookup, personalization, scoring, or campaign activation. Route CSV-heavy and provider-driven requests through this skill, then rely on linked sub-docs and provider playbooks for execution details. Available providers: adyntel, ai_ark, apify, apollo, attio, bettercontact, bloomberry, builtwith, cloudflare, contactout, crustdata, crustdata-v2, customer_db, dataforseo, datagma, deepline_native, deeplineagent, discolike, dropleads, exa, findymail, firecrawl, forager, fullenrich, generic_http, heyreach, hubspot, hunter, icypeas, instantly, ipqs, leadmagic, lemlist, linkedin_ads_audiences, linkedin_scraper, lusha, openwebninja, parallel, peopledatalabs, predictleads, prospeo, rocketreach, salesforce, serper, slack, smartlead, snowflake, theirstack, trestle, wiza, zerobounce.
Export a promoted fine-tuned model in the right deployment format - merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes promotion, when choosing a quantization format for a target device, or when an exported model fails its smoke test.
Guide a user end to end through setting up Chrome Web Store API release automation in any repository. Use when asked to walk someone through OAuth/CWS credential setup, refresh token creation, local/CI secret setup, version-based publish automation, and submission status checks.
@copilotkit/react-core — mount the CopilotKit provider (from @copilotkit/react-core/v2) in a Next.js App Router / React Router v7 / TanStack Start / SPA app, drop in CopilotChat/CopilotPopup/CopilotSidebar (v2 chat components ship from react-core/v2 — NOT react-ui, which is CSS-only in v2), access and subscribe to agents with useAgent / useAgentContext / useCapabilities, switch between multiple agents, manage durable Intelligence threads with useThreads, register browser-side tools via useFrontendTool, render tool calls with useRenderTool / useComponent / useDefaultRenderTool, gate execution with useHumanInTheLoop, wire file attachments with useAttachments, configure suggestion pills, and register activity- and custom-message renderers. Load the reference under references/ that matches your task.
Use when working with color naming, color theory, color spaces, color definitions, or any task involving color knowledge - palettes, ramps, gradients, conversions, accessibility, perceptual matching, pigment mixing, print-vs-screen color, CSS color syntax, or historical color terminology. Use this skill whenever the user is choosing, comparing, generating, naming, converting, or explaining colors, even if they do not explicitly ask for "color theory".
Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.
Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks.
Execute the destructiveChanges.xml delete-and-deploy workflow against a Salesforce org. TRIGGER when the user asks to delete/remove a custom object, field, Apex class, flow, or any metadata component FROM an org, or to perform a 'destructive deploy' / removal as part of a release. Validates first and gates production with explicit confirmation. DO NOT TRIGGER for local file deletion (use Bash), or for net-new deploys (use platform-metadata-deploy).
Full Caido SDK integration for Claude Code. Search HTTP history with HTTPQL, test with curl proxied through Caido (caching auth in reusable static curl config files), add match & replace rules, and organize handoffs into named replay sessions and collections - all via the official @caido/sdk-client. PAT auth recommended.
Create polished, general-purpose Microsoft Word documents with clear structure, typed content blocks, and strong visual hierarchy for any brief. Use when the user asks for Microsoft Word, MS Word, a Word document, DOCX, .docx, a beautiful or professional Word doc, an editable Word handoff, or to beautify Word formatting. Create Microsoft Word documents with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
Search PubMed for scientific literature, including published clinical trials. Fetch abstracts and full text. Link published research to biological databases (gene, protein, nucleotide, PubChem) to discover associations between papers and specific compounds or genes. Verify medical spelling, match raw citations, and cache result sets for bulk processing. Interfaces NCBI E-utilities and PMC BioC APIs.
Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.
Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma. Handles plan resolution via whoami if needed. Usage — /figma-create-new-file [editorType] [fileName] (e.g. /figma-create-new-file figjam My Whiteboard)
Use Sentry MCP to discover, triage, and fix production issues with root-cause analysis. Use when asked to fix Sentry issues, triage production errors, investigate error spikes, or clean up Sentry noise. Requires Sentry MCP server. Triggers on “fix sentry”, “triage errors”, “production bugs”, “sentry issues”.
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
Manages existing Elastic Cloud Serverless projects: list, get, update, delete, reset credentials, resume, and load saved credentials. Connects to existing projects by resolving endpoints and acquiring scoped Elasticsearch API keys. Use for day-2 operations on serverless projects, connecting to an existing project, loading or resetting project credentials, or looking up project details.
Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backed reports to /tmp/{datetime}/. Every claim requires a GitHub permalink as proof. NEVER takes any action on GitHub - no comments, no merges, no closes, no labels. Reports only. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'
Build, review, or improve Core Data persistence in apps that have not adopted SwiftData. Use when working with NSManagedObject subclasses, NSFetchedResultsController for list-driven UI, NSBatchInsertRequest / NSBatchDeleteRequest / NSBatchUpdateRequest for bulk operations, NSPersistentHistoryChangeRequest for persistent history tracking and multi-target sync, NSStagedMigrationManager for staged schema migrations (iOS 17+), NSCompositeAttributeDescription for composite attributes (iOS 17+), or when integrating Core Data threading with Swift Concurrency. For Core Data + SwiftData coexistence or migration, see the swiftdata skill instead.
Nitro is the framework-agnostic server toolkit (powering Nuxt) for building and deploying web servers anywhere. Use when working with nitro.config, server routes/event handlers, route rules, caching, storage, tasks, websockets, or deploying to Node/Bun/Deno/Cloudflare/Vercel.
A skill that captures experience automatically and evolves safely. Triggers: (1) when a command or operation fails → record in ERRORS.md (2) when the user corrects you ('that's wrong'/'it should be') → record in LEARNINGS.md (3) when the user needs a capability that does not exist → record in FEATURE_REQUESTS.md (4) when an external API or tool errors → record in ERRORS.md (5) when you find your own knowledge is outdated or wrong → record in LEARNINGS.md (6) when you find a better approach → record in LEARNINGS.md (7) when each task completes → review the process and record any new experience in LEARNINGS.md. Deduplication rule: skip writing if there is no new experience or an existing entry already covers it. Every write also appends a JSONL log to .learnings/CHANGELOG.md. When an experience recurs 3 or more times, promote it to AGENTS.md/TOOLS.md/SOUL.md. See the body for details.
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.