Build agent skills that demonstrably change behaviour: a linter that rejects skills that cannot work, a scaffold that passes it, and an eval...
#claude-code
3234 posts
한국어 텍스트에서 AI 생성 글의 티를 제거하는 Claude Code 에이전트 스킬. ChatGPT 문체, 이중 피동, 번역투, 문체 혼용 등 33개 패턴 탐지. Korean...
Turn "does this AI feature work?" into a scorecard someone can argue with. Rubrics, failure taxonomies, gates and confidence intervals — ren...
🍎 Apple HIG & Apple Design System skill for all AI coding agents (Claude Code, Cursor, Copilot, Antigravity, Windsurf)
Claude skill for spec-driven development: interviews you one question at a time until your unknowns run out, then harvests and verifies real...
Open Agent Skill for evidence-grounded paper analysis with isolated subagents, adaptive notes, Markdown output, and optional Notion publishi...
Screenshot Time Machine is like a Wayback Machine for your own website, a visual archive of every page over time. One command screenshots ev...
Zero-dependency agent skills for Claude Code, Codex, Gemini CLI and any SKILL.md-compatible agent. First skill: site-risk-check.
Define project foundations before implementation with a reusable Agent Skill for Codex, Claude Code, and AI coding agents.
Claude Code skill: polished 60fps ScreenStudio-style demo videos of any web app via Playwright + Pillow + ffmpeg (no screen recorder)
Preserves a long-lived repository's engineering context — an architecture index, an impact map, session records, and the decisions behind th...
Structured dissent skills for product practitioners preparing for consequential decisions and executive rooms.