Browse Skills

Legibility Check runs deterministic checks on maintainer docs to catch stale standards metadata, broken architecture manifest paths, and plan state drift before CI does. Use it after modifying files under .agents/docs/standards/, .agents/docs/plans/, .agents/docs/architecture/, or AGENTS.md.

Playwright Screen Recording captures headless browser test sessions as .webm video files for PR review, bug fix verification, and regression evidence. Use it when you need visual proof of UI behavior changes alongside terminal logs.

PR Preflight runs a full merge-readiness check before opening or merging a pull request, validating local gates (lint, format, tests), CI status, screenshot evidence, and PR metadata in one pass.

Push Release pushes code to GitHub and bumps the version when pending commits include feature changes so CI auto-publishes to PyPI. Use it to deploy Python packages and confirm release status.

Real E2E Test runs real end-to-end tests that start claude-tap from local source, connect to the real Claude CLI, and verify trace output. Use it to validate pytest and tmux interactions, tool use, HTML viewer generation, and API key redaction.

Screenshot Validation checks evidence images and viewer HTML files for quality standards before committing, catching issues like small or blank screenshots and viewer rendering errors. Use it after generating PR evidence or new trace viewer HTML.

Translate i18n fills missing i18n translations in the viewer source JSON, using English and Chinese as source languages to auto-translate to Japanese, Korean, French, Arabic, German, and Russian via OpenRouter. Use it after adding or modifying UI strings in claude_tap/viewer_i18n.json.

Reversi Master provides a strategic framework for choosing moves in Reversi/Othello, prioritizing corners, avoiding dangerous squares, and maximizing mobility. Use it when you need an AI agent to play Reversi at a strong level.

Trash Talk makes an AI aggressive and entertaining during Reversi matches by mocking opponents, bragging about moves, and taunting in-game. Use it when you want playful trash-talking commentary instead of dry move explanations.

Avoid AI Writing audits and rewrites content to remove AI writing patterns (AI-isms). Use it when asked to remove AI-isms, clean up AI writing, audit writing for AI tells, or make text sound less like AI.

Playwright Browser Automation writes and executes Playwright scripts to test websites, automate browser interactions, validate UI flows, capture screenshots, and check responsive layouts. Use it for end-to-end testing, login validation, link checking, and other browser automation tasks.

Loop Library is a compatibility alias for Loopy that discovers, audits, repairs, crafts, runs, debriefs, saves, and prepares bounded feedback loops for engineering work. Use it when older instructions invoke loop-library or when analyzing codebases for repeated work.