Explorar skills

End-of-session housekeeping for git repositories. Use when the user asks to 'end of session', 'clean up session', 'session housekeeping', 'clean up branches', 'clean up worktrees', or 'clean up remote branches'.

Automatic project tracking, progress management, and background quality agents for Claude Code

商业非虚构叙事写作工具。以「沉浸式小说笔法 × 商业事件真实感」为核心风格： 场景镜头切换、情绪藏在细节里、对话全是双关、商业信息自然渗透、结局前回望所有暗示。 给我一个真实商业人物/事件主题，我输出同风格的叙事长文。 触发词：/biz-fiction、写商业故事、叙事风格、商业小说、写一篇关于XX的故事 Trigger: /biz-fiction, write business story, narrative fiction, character story

Scans all active GitHub repositories using a Personal Access Token (PAT) and produces a full inventory of every programming language and framework in use — with repo counts, byte-share percentages, and version info where available. Use this skill whenever the user wants to audit their GitHub tech stack, see what languages or frameworks they use across repos, understand technology spread across an

Skill Claude Code — méthodologie rigoureuse de recherche en droit français, conçue contre 14 modes d'erreur LLM.

End-to-end web app testing. Use when user says "test the app", "run e2e", "smoke test", "regression run", "check the login/onboarding/chat flow", "audit accessibility", "test responsive", or "find bugs in <url>" — even when Playwright is not named. Bootstraps Playwright + axe-core, runs LLM exploration on first run, deterministic replay afterward, emits markdown report + bugs.json + *.spec.ts file

Use when starting features, projects, or refactors with AI coding agents and requirements feel informal, incomplete, or drift-prone. Triggers: AI generates code that ignores constraints, same prompt produces different implementations across sessions, team lacks shared technical understanding, complex features need traceable design decisions, or vibe-coding produces unreliable output. Keywords: spe

Build, fix, optimize, and debug WordPress sites with the standard stack (Astra Free + Elementor Pro + ACF + msrbuilds/elementor-mcp). Activates when the user asks for WordPress, Elementor, page-builder, landing-page, CPT, custom-field, theme-settings, plugin-config, deploy, migrate, performance, security, or SEO work, or mentions any tool in the stack (Astra, Elementor, ACF, JetEngine, Rank Math,

GitHub repo 展示层管家 — 让 repo 在 GitHub 页面上"看起来像个能用的项目"。三件套：① README 重写（mirror 参考 repo 的结构 + 填充本 repo 内容，含 badges / 它是什么 / 为什么做它对比表 / 安装两法 / 用法 / 流程 / 文件结构 / 自定义 / 版本史 / 贡献 / 致谢 / License）② GitHub 描述润色（30-100 字一句话，卖点 + 输出 + 价值，替代「X Claude Code skill」式裸分类描述）③ Topic 标签加 10-15 个，按 6 类分（生态/受众/用途/数据源/技术/语言）。**附加两步**（用户要求时启用）：⓪ 建新 repo（git init + gh repo create + push，当目录还没 git 化或 GitHub 上还没 repo 时）④ 补 LICE

Generates a daily work report from your git commit history. Triggered by "/report" (interactive) or "/report --direkt" (zero-question, auto-saves to ~/Desktop/rapor.md). Supports Turkish (default, or "-tr") and English ("-en") output. Flags can be combined freely (e.g. "/report -en --direkt"). Also triggers on "rapor oluştur", "günlük rapor", "iş raporu", "daily report", "work report", "generate r

Humanize AI-generated text to avoid AI detection. Use when the user wants to make ChatGPT, Claude, Gemini, or other AI text sound human and pass GPTZero, Turnitin, ZeroGPT, and other AI detectors.

Правила производственного цикла разработки кода для всех проектов Jared. Тирует задачу (XS / M / L), требует RFC перед кодом для M/L, обязательный smoke-тест даже на XS, мульти-агентное ревью для M/L, `/security-review` для L и любых фич с auth/данными, инцидент-лог в blameless-режиме, DOD-чеклист перед отчётом. Уровни безопасности S1→S3 подключаются инкрементально. Дополнительно: groom-режим (`/d