Barebrowse
Gives agents a real browser. URL in, pruned snapshot out. Replaces Playwright, Selenium, Puppeteer. Zero deps, zero wasted tokens.
Trace Back
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Live Canvas
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.
Debug Method
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
Verify Done
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Liteagents
Comprehensive AI liteagents kit (subagents, skills/commands) for Claude Code, Opencode, Ampcode, and Droid
Beeperbox
Plug your AI agent into 50+ messengers (WhatsApp, iMessage, Signal, Telegram, Slack…) through one MCP endpoint. Two modes: a self-contained Docker container (headless Beeper bundled) or a lite npx MCP layer pointed at the Beeper you already run.
Test Traps
Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies
Docs Builder
Create or reorganize project documentation with structured /docs hierarchy
Tdd Flow
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
Test Skill
A Claude skill from hamr0/liteagents.
Brainstorming
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