Loading...
Loading...
Found 1,690 Skills
Autonomous multi-page site builder using a baton-passing loop pattern. Each iteration reads a task from .design/next-prompt.md, generates a page with Claude's HTML/CSS/Tailwind, integrates it into the site, verifies visually via browser automation, then writes the next task to keep the loop going. Drives complete website builds from a single starting prompt. Triggers: 'design loop', 'build the site', 'build all pages', 'autonomous site build', 'baton loop', 'next page', 'keep building pages'.
Unity 6 core concepts and architecture guide. Use when working with GameObjects, Components, Transforms, Scenes, Prefabs, ScriptableObjects, or Unity project structure. Covers the entity-component architecture, object hierarchy, tags, layers, and project conventions. Based on Unity 6.3 LTS documentation.
Implement reviewer feedback on a Canva design. Reads all comment threads, synthesises what reviewers want, makes the clear-cut changes directly, and flags anything that needs a human decision. Use when the user asks to "implement feedback on my deck", "address comments on a design", "apply review feedback", "fix the comments on my presentation", or "implement the feedback".
Competitor comparison and alternative page creation for SEO and sales enablement. Covers 4 page formats (singular alternative, plural alternatives, vs pages, competitor vs competitor), content architecture, research methodology, and centralized competitor data management.
Targeted Chat Room: Recommend experts based on topics or accept user-specified experts to simulate multi-role conversations. Trigger methods: /定向聊天室, 「定向聊天室」
Reset Claude Code buddy/companion by changing the season seed (fk_) in cli.js and removing the companion field from ~/.claude.json, allowing re-hatching a new buddy. Triggers: buddy reset, reroll buddy, new buddy, change buddy, reset companion, reroll companion, buddy reroll
Configure security headers to defend against clickjacking, XSS, MIME confusion, and SSL stripping attacks. Use this skill when you need to set up Content-Security-Policy, X-Frame-Options, HSTS, configure middleware headers, or understand browser security features. Triggers include "security headers", "CSP", "content security policy", "X-Frame-Options", "HSTS", "clickjacking", "MIME confusion", "middleware headers".
Used when a feature has been implemented but lacks design documentation and implementation plans. Automatically generate documents conforming to /hi-brainstorm and /hi-ace formats based on existing code and git history.
Twig coding standards and conventions for Craft CMS 5 templates. Covers variable naming, null handling, whitespace control, include isolation, Craft Twig helpers ({% tag %}, tag(), attr(), |attr, svg()), and collect() usage. Triggers on: any Twig template creation or review, .twig files, {% include %}, {% extends %}, {% tag %}, collect(), props.get(), .implode(), attr(), |attr filter, svg(), ?? operator, whitespace control, template coding standards, Twig best practices, naming conventions for Twig, currentSite, siteUrl, craft.entries, .eagerly(), .collect. Not for Twig architecture patterns (use craft-site) or PHP code (use craft-php-guidelines). Always use when writing, editing, or reviewing any Craft CMS Twig template code.
Craft CMS 5 PHP coding standards and conventions. Triggers: writing PHP classes, PHPDoc blocks, @author, @since, @throws, section headers (=========), defineRules(), beforePrepare(), addSelect(), MemoizableArray, DateTimeHelper, Carbon, ECS check-cs, PHPStan, ddev craft make, Twig templates, form macros, translations Craft::t(), enum definitions, commit messages. Always load when writing, editing, or reviewing any PHP or Twig code in a Craft CMS plugin or module.
Validates and scores Claude Code skill packages for quality, completeness, and best practices compliance. Tests Python scripts, checks YAML frontmatter, and generates quality reports. Use when creating new skills, validating skill packages, or auditing skill quality.
2-layer parallel agent hierarchy. Layer 1 deploys 3-50+ agents, each with independent context. Layer 2 adds 2+ sub-agents per member. No upper limit on either layer.