QuickClaw-Skills/skill-ci
Reusable CI workflow for QuickClaw-Skills org — validates SKILL.md, skill.json, forbidden files, secrets, paths, syntax, release sync 3-way.
Reusable CI workflow for QuickClaw-Skills org — validates SKILL.md, skill.json, forbidden files, secrets, paths, syntax, release sync 3-way.
npx add-skill QuickClaw-Skills/skill-ciReusable CI workflow for QuickClaw-Skills org — validates SKILL.md, skill.json, forbidden files, secrets, paths, syntax, release sync 3-way.
Visual-first UI/UX collaboration for AI agents — browser automation, screenshot comparison, wireframes, design tokens, and the 8-step design loop.
Disciplined method for investigating a specific bug, regression, or anomalous behavior. Use when the user reports a concrete symptom ("X is broken", "this worked last week", "Y returns the wrong value", "intermittent failure in Z") and wants the root cause found — not a quick patch. Enforces reproduce-first, read-only diagnosis, differential disconfirmation, and git forensics. Do NOT use for open-ended "find any bugs" sweeps, code review, or feature work.
A modular, extensible AI agent built on top of adk-rust and the teloxide framework.
🎨 Format Markdown to styled HTML for WeChat articles, with automatic image uploads and custom CSS for optimal readability.
MCP server that lets Claude Code and other AI agents read large PDFs without hitting context limits. Chunked reading, hybrid search, OCR, table and image extraction, SQLite cache.
Claude Code skill that diagnoses scroll and animation jank in SwiftUI apps using Instruments .trace exports to DuckDB