Loading...
Loading...
Found 2,174 Skills
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
Complete reference for writing, running, and iterating on evals (automated conversation tests) for ADK agents. Covers eval file format, all assertion types, CLI usage, and per-primitive testing patterns.
Systematic debugging for ADK agents — trace reading, log analysis, common failure diagnosis, and the debug loop.
Multi-model agent orchestration using specialized agents for planning, coding, research, math/science, visual analysis, and adversarial review. Use when tasks are complex enough to benefit from different models' strengths, when you want adversarial review to catch blind spots, or when coordinating multi-step workflows across agent roles. Triggers on complex projects, multi-step tasks, architecture decisions, or when explicitly requested.
USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep research, news, images, videos, places, custom ranking
Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.
Enthu.AI platform help — contact center conversation intelligence with auto QA scorecards, agent coaching, compliance monitoring, and speech analytics. Use when setting up Enthu.AI QA scorecards for call center agents, calls not being scored or transcribed correctly, agents not seeing coaching insights from their calls, Enthu.AI integration with Aircall or RingCentral not syncing, comparing Enthu.AI vs Gong or CallMiner for contact center QA, or configuring sentiment analysis and keyword tracking. Do NOT use for building a general coaching program (use /sales-coaching) or reviewing a specific call transcript (use /sales-call-review).
Observe.AI platform help — enterprise contact center intelligence with Auto QA scoring on 100% of interactions, Agent Copilot real-time guidance, Coaching Copilot post-call performance management, VoiceAI and ChatAI virtual agents, screen recording, Insights Copilot. Use when setting up Observe.AI Auto QA scorecards for contact center agents, Agent Copilot not surfacing guidance during live calls, transcription accuracy issues or speaker attribution errors, comparing Observe.AI vs Balto or Cresta or CallMiner for contact center QA, integrating Observe.AI with Five9 or Amazon Connect or Talkdesk, or configuring compliance monitoring and regulatory audit trails. Do NOT use for building a general coaching program (use /sales-coaching) or reviewing a specific call transcript (use /sales-call-review).
Altern platform help — curated AI tools and agents directory (10,000+ tools, 100+ categories, ~5-28K monthly visits). Covers tool submissions (free + featured tiers: Gold/Silver/Bronze), listing optimization, category selection, newsletter inclusion (weekly AI tools + agents digest), alternatives pages, and dofollow backlinks. Use when your AI tool isn't listed on Altern, listing isn't getting visibility, not sure if a featured tier is worth it, or wondering how Altern compares to other AI directories. Do NOT use for multi-directory launch coordination (use /sales-launch-directory). Do NOT use for non-AI product directories (use the platform-specific skill).
Run cross-framework agent comparisons using evaluatorq from orqkit — compares any combination of agents (orq.ai, LangGraph, CrewAI, OpenAI Agents SDK, Vercel AI SDK) head-to-head on the same dataset with LLM-as-a-judge scoring. Use when comparing agents, benchmarking, or wanting side-by-side evaluation. Do NOT use when comparing only orq.ai configurations with no external agents (use run-experiment instead).
This skill helps agents use Figma's use_figma MCP tool in the FigJam context. Can be used alongside figma-use which has foundational context for using the use_figma tool.
Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.