🎯Skills26
Part of the Atomic agent framework, this skill explains code functionality in detail using DeepWiki to provide comprehensive code understanding and documentation.
Part of the Atomic agent framework, this skill enables deep codebase research by dispatching specialized sub-agents — a codebase-locator finds relevant files, a codebase-analyzer reads implementations, and an online-researcher queries external docs.
Part of the Atomic agent framework, this skill helps create, improve, and optimize prompts using best practices, within Atomic's multi-agent architecture that dispatches specialized sub-agents for focused task execution.
An Atomic SDK skill for optimizing LLM context usage through KV-cache optimization, observation masking, and context budgeting techniques.
A built-in Atomic skill that discovers and installs agent skills from the community. Part of the Atomic multi-agent harness that orchestrates Claude Code, OpenCode, and GitHub Copilot CLI.
A meta skill from the Atomic multi-agent harness that enables creating, modifying, evaluating, and benchmarking custom agent skills. Auto-invoked when building or iterating on SKILL.md files.
An Atomic SDK skill for offloading context to the filesystem and enabling file-based agent coordination to work within LLM context limits.
An Atomic SDK skill for designing clear tool contracts and reducing agent-tool friction in AI coding agent workflows.
An Atomic SDK skill for strengthening applications with error handling, internationalization (i18n), overflow protection, and edge-case resilience.
An Atomic SDK design skill that pushes UI designs to their creative limits, maximizing visual impact and boldness beyond conventional boundaries.
An Atomic SDK skill for validating task-model fit before building and estimating costs for AI agent development projects.
An Atomic SDK skill covering how LLM context windows work, including attention mechanics and progressive disclosure techniques for effective context management.
An Atomic SDK skill for adding motion, micro-interactions, and personality to UI designs, enhancing the user experience with delightful interface elements.
An Atomic SDK skill for advanced evaluation techniques including pairwise comparison, position-bias mitigation, and building evaluation pipelines.
An Atomic SDK skill for diagnosing context degradation issues such as lost-in-the-middle effects, context poisoning, and distraction failures in long-running agent sessions.
An Atomic SDK skill for summarizing transcripts at session boundaries while preserving actionable information to manage long-running agent sessions.
Part of the Atomic agent framework, this skill enforces test-driven development by writing tests first, and includes a testing anti-patterns guide to avoid common testing mistakes.
An Atomic SDK skill covering supervisor, swarm, and handoff patterns for building and orchestrating multi-agent systems.
An Atomic SDK skill for conducting UX evaluation with quantitative scoring and persona testing to assess design quality.
A design-focused skill from the Atomic multi-agent harness that simplifies and distills UI/UX designs. Part of a suite with quieter, bolder, and overdrive variants for toning down, amplifying, or pushing designs to their limit.
An Atomic SDK design skill that amplifies and intensifies UI designs, making visual elements stronger and more impactful.
An Atomic SDK skill providing expert guidance on TypeScript type-level programming, performance optimization, and version migrations.
An Atomic SDK design skill that tones down and simplifies UI designs, creating a calmer, more restrained visual presentation.
An Atomic SDK skill providing expert code review for TypeScript + React 19 applications, covering component patterns, hooks usage, and type safety.
Skill
Skill