LLM content governance and compliance standards. Use when llm governance guidance is required.

Comprehensive guide to LLM safety and guardrails implementation for AI systems.

Use when wanting to interact with any LLM - Explains available inference endpoints so the agent selects suitable models.

You are an expert in integrating Large Language Models with the emotive-mascot

Comprehensive guide to using LLMs as judges for automated evaluation including prompt patterns, calibration, bias reduction, and multi-judge ensembles

Comprehensive guide to securing LLM applications including prompt injection prevention, jailbreak detection, guardrails, and red teaming methodologies

LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies, and streaming response patterns. Use when designing LLM serving infrastructure, optimizing inference latency, or scaling LLM deployments.

LLMs, prompt engineering, RAG systems, LangChain, and AI application development

LMS-ESID core architecture including one-class-three-teachers system, course structure, grade levels, role permissions, and database schema. Use this skill when understanding teacher types (LT/IT/KCFS/HT), course relationships, class naming conventions, academic year data, or table relationships.

Research best practices via MCP Ref/Context7/WebSearch and create documentation (guide/manual/ADR/research). Single research, multiple output types.

Creates design_guidelines.md for frontend projects. L3 Worker invoked CONDITIONALLY when hasFrontend detected.

Traffic-First opportunity discovery. KILL funnel filters ideas by traffic channel, demand, competition, revenue, interest, MVP-ability. Outputs one idea + one channel recommendation.

LobeChat - Open-source AI agent workspace with multi-provider LLM support, plugin system, knowledge base RAG, 505+ agents, and self-hosting options via Docker/Vercel

LobeVidol - Virtual idol creation platform with MMD dance support, VRM character customization, multi-provider LLM integration, and interactive 3D conversations

Access LobeChat for AI chat, knowledge base queries, and multi-model routing.

Run local BLAST searches using BLAST+ command-line tools. Use when running fast unlimited searches, building custom databases, performing large-scale analysis, or when NCBI servers are slow or unavailable.

Enforces local-first architecture principles for Breath of Now. Use this skill when working with data, state management, or sync features. Ensures IndexedDB (Dexie.js) is always the source of truth.

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

Comprehensive guide for using Local Skills MCP - creating skills in the right locations, understanding skill directories, setup, and configuration. Use when creating new skills, deciding where to save skills, setting up the MCP server, or understanding how skill aggregation works.

Set up and manage local skills for automatic matching and invocation

LocalSend-based P2P transfer with MCP server design for NATS/Tailscale discovery and throughput tuning.

Reference for LocalStack AWS service availability by tier (Free/Base/Ultimate). Essential for KECS development to understand which AWS-compatible services can be used locally without cost.

Designs location-based augmented reality experiences with geospatial anchoring, GPS integration, and real-world interactive overlays.

Set up centralized logging with ELK, Loki, or Splunk for log management

log-product-standards-issues

Centralize logs with ELK/EFK and retention policies.

logging

logging-guide

| Atributo | Valor |

Master formal and informal logic - valid reasoning, fallacies, paradoxes. Use for: argument analysis, validity, soundness, logical form, fallacies, paradoxes. Triggers: 'valid', 'validity', 'fallacy', 'premise', 'conclusion', 'modus ponens', 'modus tollens', 'paradox', 'logical', 'syllogism', 'deduction', 'induction', 'inference', 'argument form', 'soundness', 'entailment', 'contradiction'.

Use when working with 74xx and CD4xxx series logic ICs - standard TTL/CMOS logic gates, flip-flops, counters, decoders, multiplexers. Includes technology families (LS, HC, HCT, AC, AHC) and LogicICHandler guidance.

Expert-level supply chain management, logistics optimization, warehouse systems, and fleet management

Create logo components with multiple variants (icon, wordmark, logo) and light/dark modes. Use when the user provides logo SVG files and wants to create a variant-based logo component following the Clerk pattern in the Elements project.

> **Version 2.35.0** | PRD to Production | Zero Human Intervention

Guide for implementing Grafana Loki - a horizontally scalable, highly available log aggregation system. Use when configuring Loki deployments, setting up storage backends (S3, Azure Blob, GCS), writing LogQL queries, configuring retention and compaction, deploying via Helm, integrating with OpenTelemetry, or troubleshooting Loki issues on Kubernetes.

---name: long-read-sequencing-agent

Maintains continuity across long-running tasks that span multiple agent sessions. Use when starting or resuming a complex project that spans multiple sessions, or for tasks with many discrete features requiring iterative development.

This skill enables targeted searches of longevity and aging research using the Semantic Scholar API. It provides a simple, focused interface for finding relevant academic papers and synthesizing resea

looker

Record and share video messages with Loom - create screen recordings, manage video library, and track viewer engagement

main concept behind cmta

Create a PRD through user interview, codebase exploration, and module design, then submit as a Linear issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.

Clarify ambiguities in plans with structured questions and auto-decide rules

Recover Neotoma SQLite Database

Verify NiFi custom UI tabs via Chrome and update doc/guides screenshots and guides

Notch overlay UI patterns — NSPanel setup, SwiftUI overlay views, screen-sharing hiding, and display adaptation

Create a error message copy with structured process, quality checks, and system integration

Create a offer letter real estate with structured process, quality checks, and system integration

This skill builds the project system and hardware definition workflow. Users create projects, define their board and components in a manifest, and see everything reflected in the parts panel. The mani

Configures the project management tool by guiding selection from supported options, applying the implementation guide, updating way-of-working adoption, and recording the decision via /pair-capability-record-decision. Idempotent — detects existing configuration.