Loading...
Loading...
Found 1,274 Skills
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
Ready-to-use prompt templates for specialized agents. Use when building n8n workflows, AI integrations, or sales materials. Contains structured prompts for automation-architect, llm-engineer, and sales-automator agents.
Implements and debugs browser Proofreader API integrations in JavaScript or TypeScript web apps. Use when adding Proofreader availability checks, monitored model downloads, proofread flows, correction metadata handling, or permissions-policy checks for built-in proofreading. Don't use for generic prompt engineering, server-side LLM SDKs, or cloud AI services.
Firecrawl produces cleaner markdown than WebFetch, handles JavaScript-heavy pages, and avoids content truncation. This skill should be used when fetching URLs, scraping web pages, converting URLs to markdown, extracting web content, searching the web, crawling sites, mapping URLs, LLM-powered extraction, autonomous data gathering with the Agent API, or fetching AI-generated documentation for GitHub repos via DeepWiki. Provides complete coverage of Firecrawl v2.8.0 API endpoints including parallel agents, spark-1-fast model, and sitemap-only crawling.
Analyzes images using a vision-capable LLM (Optic). Can read workspace images, URLs, base64 data, or previously generated images by ID.
Async media + document derivations via `platform.media.transforms` and the declarative `transforms` block in `maravilla.config.ts`. Media: transcode video, thumbnail extraction, image resize/variants, OCR. Documents (.docx/.odt/.pptx/.xlsx/...): convert to PDF, render page thumbnails, generic format conversion, Markdown extraction (RAG-ready), single-file HTML with inlined images, image-replacement templating ({{TAG}} swap + named-object swap), QR-code injection. Use when ingesting user uploads that need normalised renditions, generating contracts/invoices from templates, or extracting structured content for LLMs. Critical: derived keys are content-addressed — `keyFor(srcKey, spec)` is known up front, before the worker starts, so clients can render placeholder UI without round-trips. Declarative config is the default; imperative `transforms.*` calls are for one-offs.
Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow HTTP/database spans, error spans, trace IDs, or span attributes — not LLM analytics traces or product logs. Uses posthog:query-apm-spans, posthog:apm-trace-get, posthog:apm-services-list, posthog:apm-attributes-list, and posthog:apm-attribute-values-list.
Guides product infrastructure security—securing the runtime, data plane, and control plane that ships with the product: multi-tenant isolation, service-to-service auth, customer data boundaries, secure defaults in APIs and workers, abuse-resistant rate limits, product-scoped secrets and encryption, and security design reviews for product infra changes. Use when threat-modeling product features, designing tenant isolation, hardening service mesh or internal APIs, reviewing product IaC/modules for data leaks, defining secure baselines for microservices the product team owns, or partnering on incidents affecting customer workloads—not for corporate IdP/SIEM (information-security-engineer), CI pipeline gates only (devsecops), SOC operations (defensive-security-analyst), authorized pentest execution (offensive-security-analyst), general IDP golden paths (platform-engineer), company-wide GRC (cybersecurity), or applied AI solution architecture for LLM features (applied-ai-architect-commercial-enterprise).
Guides digital forensics for security incidents—evidence acquisition and chain of custody, disk/memory/mobile/cloud artifact analysis, log and network forensics, timeline correlation, malware artifact triage, and investigation reports for legal/IR and expert-witness preparation outlines (not legal advice). Use when preserving and analyzing forensic artifacts, building super-timelines, documenting acquisition worksheets, triaging malware samples, or preparing forensic findings for counsel—not live incident command (incident-responder), SOC alert queue triage (soc-analyst), authorized penetration testing (penetration-tester), deep binary RE (reverse-engineer), LLM red team (ai-redteam), enterprise ISMS programs (information-security-engineer), audit control mapping (compliance-engineer), or cloud guardrail implementation (cloud-security-engineer).
Deploy Nemotron Voice Agent on Workstation (x86), Jetson Thor, or Cloud NIMs. Real-time speech-to-speech using NVIDIA ASR, TTS, LLM with WebRTC/WebSocket transport.
Three-layer PII anonymization for session transcripts (therapy, coaching, consulting, mentoring). Runs Natasha (Russian NER), OpenAI Privacy Filter, and local LLM (Ollama) in sequence for maximum coverage. Fully local by default. This skill should be used when anonymizing session transcripts, notes, or any text containing client PII before AI analysis. Triggers on "anonymize", "redact PII", "anonymize session", "protect client data", "strip personal data", "anonymize transcript".
4-stage funnel that screens all 500+ Hyperliquid perps down to the top trading opportunities. Scores setups 0-400 across smart money, market structure, technicals, and funding. BTC macro filter, hourly trend gate (counter-trend = hard skip), cross-scan momentum tracking. Near-zero LLM tokens — all computation in Python. Use when scanning for new trading opportunities on Hyperliquid, evaluating setups, or checking market conditions.