Comprehensive AI liteagents kit (subagents, skills/commands) for Claude Code, Opencode, Ampcode, and Droid
This repository also configures its own agents. See what liteagents tells them →
Skill Claude Code
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes.
Skill Claude Code needs its repo
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.
Skill Claude Code
Review a branch before merge.
Skill Claude Code
Reorg a docs corpus, split an oversized doc, search it, keep pages current, index them.
Skill Claude Code
Refactor and optimize [code].
Skill Claude Code
Verify, write the CHANGELOG, cut a version — then hand the release sequence back.
Skill Claude CodeCodex
Consolidate stashes + friction into project memory.
Skill Claude Code
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
Skill Claude Code
Security audit — recurring six, injection, auth, trust boundaries.
Skill Claude Code
Stash session context [name].
Skill Claude Code
Generate and run tests [file].
Skill Claude Code
Verify what you delivered since the last self-review with real runs, and review its structure.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: