Agents Best Practices
agents-best-practices
A provider-neutral skill for designing agent systems: loop architecture, tools, permissions, memory and observability
Skills
A skill gives an agent a ready-made ability: a tested prompt, a set of steps, sometimes files and scripts. This section collects skills for Claude Code, Cursor, Codex and other agents, each with an install command, a risk level and a plain description of who needs it and when.
Match with Foxx AI
Describe the task or paste package.json, and Foxx AI will pick matching skills, MCP servers and CLI tools.
Found: 46
A skill that gives image recognition to models without native vision: it sends the image to a vision model and returns a text description
A skill that helps an agent author other skills to the agentskills.io spec: structure, metadata, progressive disclosure and validation
pohuy
ПОХУЙ
An agent voice mode using idiomatic Russian profanity while keeping technical precision, 18+
A set of CLI tools and a skill that give a text-only agent sight: image analysis, long-screenshot OCR and UI restoration
Skills that search a large base of Japanese NLP resources: libraries, models, datasets and dictionaries
Autoresearch for skills
autoresearch
A skill that improves another skill: runs it on test inputs, scores outputs with binary checks and mutates the prompt
Self-learning
self-learning-skills
A meta-skill that saves a hard-won working procedure as a new skill or rule, so the next session starts already knowing it
A skill for creating skills that proves them by behavior: before-and-after runs, regression evals and ecosystem audit
A set of skills, slash commands and agents for Claude Code that helps you build your own skills, agents, hooks, slash commands and prompts
An execution-discipline skill for Claude: staged planning, delegation to agents, failable checks and a double-check before delivery
A skill with daily rankings of agent skills by installs, growth and mentions across several platforms at once
A Claude Code skill that runs multi-agent work by a naval metaphor: planning, parallel tasks with checkpoints, stand-down
A skill that designs, tests, evaluates and packages other agent skills, starting from architecture
LangSmith skills
LangSmith Skills
Official LangChain skills for LangSmith: query and export traces, build eval datasets and write custom evaluators from your agent
Official skills for the Venice.ai API: chat, images, video, speech, embeddings, billing and x402 payments
Prompt caching audit
LLM Cache Audit Skill
Skill for Codex and Claude Code that traces what breaks LLM prompt caching in code and config and proposes a verification step
Russian stack
A skill collection for the Russian stack: GigaChat, YandexGPT, Yandex 360, Yandex Cloud, Metrika and marketplace orders
A skill based on the Recursive Language Models paper: the agent splits repo-wide or multi-PDF tasks into batches for sub-agents
Russian stack
Eight skills for coding against the GigaChat API: choosing a layer, access setup, SDK, LangChain, gpt2giga and Deep Agents
OpenAI to GigaChat migration skill
migrate-to-gigachat-skill
A Cursor skill that migrates Python, JS or TS projects from OpenAI to GigaChat: detects the stack, picks an adapter, and verifies with tests it still starts
Custom skills bundle for Hermes Agent
hermes-custom-skills
A monorepo of five skills for Hermes Agent: agent security hardening, skill auto-updates, skill search, cross-border expansion and Tencent Yuanbao chat
Frequently asked questions
What is a skill for an AI agent?
A skill gives an agent a ready-made ability: a tested prompt, a set of steps, sometimes files and scripts. The agent picks it up and solves the task by the defined scenario.
How do I install a skill?
Each entry has an install command for a specific agent: Claude Code, Cursor, Codex and others. Usually you copy a folder into the skills directory or install it through a plugin manager.
How is a skill different from an MCP server?
A skill gives the agent knowledge and a sequence of actions, an MCP server gives access to external data and tools over a protocol. They are often used together.