agent-evals-and-observability
Design, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when defining agent evals, datasets, graders,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
Agents & models
24,527 results
multi-perspective-analysis
Adopt multiple expert personas sequentially for complex problem analysis from diverse perspectives. Single-agent only — do NOT spawn sub-agents.
reasoning-controls
Use when adjusting reasoning depth, budgets, or metrics visibility - provides guidance for selecting and applying reasoning controls safely.
stable-diffusion
Provides comprehensive guidance for Stable Diffusion AI image generation including model usage, prompt engineering, parameters, and image generation. Use when…
pollo-ai-video-generator
Generate AI videos using the Pollo AI API. Supports 13 leading models (Kling, Sora, Runway, Veo, Pixverse, Hailuo, Vidu, Luma, Pika, Wan, Seedance, Hunyuan,…
principle-guard-the-context-window
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not…
qe-skill-builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build…
redfox-skill-generator
One-click generation of high-quality Redfox Skill exclusive skill file packages (SKILL.md + supporting resources). Just describe the functional requirements, provide the API address and API documentation, and it will automatically generate professional skill files that comply with Redfox specifications, ready to use out of the box. Supports on-demand customization and iterative optimization. Trigger words: when the user mentions 'create Redfox skill', 'generate Redfox skill', 'create a new Redfox skill', 'write a Redfox skill', 'make a Redfox ski…
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and…
blockfill-agent-execution
AI agent execution skill for crypto order execution — TWAP, maker execution, transaction cost analysis and slippage reduction. Supports 11 CEX and DEX venues…
openai-playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging)…
dotnet-agent-gotchas
Generating or modifying .NET code. Common agent mistakes: async, NuGet, deprecated APIs, DI.
autoresearch
Use for measured, iterative optimization; skip one-shot edits and review-only tasks. Routes to agi-mode Hillclimb for experiments on code, skills, prompts or…
sol-luna-setup
Implement the "high-intelligence lead + cheap execution" layered sub-agents on a new machine or new project: Codex Sol as lead + Luna as workers, optionally Claude Code project-level agents and Pi/pi-flow cross-tool orchestration. Used for: (1) Installing and configuring Codex / Claude Code / Pi from scratch (2) Writing project-level...
1inch-mcp-server
Connect to the 1inch MCP server for documentation search, SDK examples, token swaps, limit orders, authenticated product API access, WalletConnect, Aqua…
ask-question
Use the IDE AskQuestion tool when the agent needs user input. Use when asking the user to choose between options, confirm a decision, or pick from discovered…
alibabacloud-lindorm-agent-skill
Use this Skill for Alibaba Cloud Lindorm work: instance lifecycle and configuration, networking and access control, monitoring, performance, storage,…
mllm-eval
Use when designing or auditing how an LLM or multimodal LLM is evaluated on a clinical task (report generation, VQA, text extraction). Covers reference…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
bdpan-storage
Baidu Netdisk file management. Supports upload, download, transfer, share, search, move, copy, rename, and create folder. Triggered when the user mentions "Baidu Netdisk", "bdpan", or "Netdisk" and is involved in file operations.
model-architecture-diagram
Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook model families. Use when the user…
hackathon-judge-simulator
Simulate a panel of hackathon judges to generate adversarial questions, objections, and predicted scores for pitch hardening.
agents-progressive-disclosure
Refactor bloated AGENTS.md/CLAUDE.md-style instruction files into a compact router plus focused on-demand docs. Use when users ask to apply progressive…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and…