t4sh

@t4sh source repo

13 skills
0 followers
14 hours ago last updated

▌
Paseo Loop · t4sh bundle
Run an agent loop until an exit condition is met. Use when the user says "loop", "babysit", "keep trying until", "check every X", "watch", or wants iterative autonomous execution.

0
installs
▌
Paseo Plugin · t4sh bundle
Build and manage trusted local Paseo plugins. Use when the user asks to create, edit, install, reload, enable, disable, remove, or troubleshoot a Paseo plugin; add a native surface or sidebar item; use Paseo from plugin code; add plugin RPCs; or contribute composer attachments.

0
installs
▌
Init Rulebook · t4sh
Load and rehydrate the user-level agent rulebook by reading `~/.agents/AGENTS.md` plus every top-level `~/.agents/rules/*.md` file. Use when handling explicit requests such as init rulebook, reload rulebook, or load user-level agent rules, or when rehydrating after context compaction.

0
installs
▌
Transitions Dev · t4sh bundle
Production-ready CSS transition recipes and motion tokens for web apps. Use when implementing dropdowns, modals, panels, page transitions, cards, text or icon swaps, accordions, toasts, tooltips, form feedback, loading states, toggles, or streaming AI interfaces; or when asked to replace ad-hoc transitions with reusable motion tokens. Supports transitions reveal, review, apply, and refine. See the quick reference for all 32 recipes.

0
installs
▌
Skill Development · t4sh bundle
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

0
installs
▌
Code Review Nextjs · t4sh
This skill should be used when the user asks to "review Next.js code", "review this Next.js pull request", "check my App Router changes", "audit a Next.js component", or evaluate Next.js code quality, accessibility, security, performance, routing, caching, or framework conventions.

0
installs
▌
Agent Memory · t4sh bundle
Cross-interface persistent memory for project context, decisions, conventions, and session handoffs. Use when the user asks to "manage project memory", "initialize .agent-memory", "migrate memory", "build memory from docs", "save session learnings", "sync memory", "run memory maintenance", "check memory status", or mentions persistent memory across Codex, Claude Code, Cursor, VS Code, Craft Agent, or other file-reading agents.

0
installs
▌
Code To Figma · t4sh bundle
CI-anchored code-to-Figma token export pipeline for keeping Figma aligned with the codebase. Use when the user asks to "sync code to Figma", "export design tokens to Figma", "set up a Figma sync pipeline", "wire up the tokens-sync-to-figma plugin", "generate a figma-export.json", "create a page walker", or "keep Figma up to date with the codebase".

0
installs
▌
Figma To Code · t4sh bundle
Repo-first Figma-to-code workflow for implementation, design tokens, design-system rules, and Code Connect. Use when the user asks to "implement this Figma design", "turn this Figma into code", "build from a Figma link", "match this Figma mockup", "extract Figma design tokens", "create Figma design system rules", "set up Figma guidelines", "code connect this component", or "map this Figma component to code"; or when a Figma URL/selection must become repository code, code tokens, agent rules, or Code Connect mappings.

0
installs
▌
Discord Harvest · t4sh bundle
Discord content extraction and archival workflow for images, attachments, links, and conversation files. Use when the user asks to "extract Discord images", "download Discord attachments", "harvest a Discord channel", "archive a DM", or mentions scraping or preserving content from a Discord conversation.

0
installs
▌
Skill Architect · t4sh bundle
Architect and audit portable agent skills for retrieval, predictability, progressive disclosure, evals, and repository gates. Use when the user asks to "create a skill", "author a skill", "improve a skill", "review a skill", "refactor a skill", "compare skill rubrics", "distill a skill from sessions", "reconcile skill plans", or "teach skill authoring"; when paths include `skills/<name>/SKILL.md`, `references/*.md`, helper scripts, evals, lockfiles, security manifests, or vendor adapters; or when mentions include skill-creator, Skill Development, skills.sh, trigger descriptions, completion criteria, leading words, or model/user invocation.

0
installs
▌
Eleventy Nunjucks · t4sh bundle
Eleventy v3, Build Awesome v4 prerelease, and Nunjucks operating guide for static-site authoring, templates, build pipelines, migrations, and security review. Use when the user asks to "create an 11ty page", "add a Nunjucks filter", "fix my layout chain", "review my .njk template", "set up Eleventy", "migrate to Build Awesome", or "audit my static site"; when `package.json` includes `@11ty/eleventy` or `@awesome.me/buildawesome`; when paths include `.eleventy.js`, `eleventy.config.js`, `.njk`, `.11tydata.js`, `.data.js`, `.11ty.js`, or `.server.js`; or when debugging data cascades, filters, shortcodes, async Nunjucks, autoescape, or static-site security.

0
installs
▌
Localhost Screenshots · t4sh bundle
Localhost screenshot capture and visual-regression workflow for responsive pages and local dev servers. Use when the user asks to "screenshot my site", "capture pages", "visual diff", "compare screenshots", "responsive screenshots", "check breakpoints", "visual regression", or any request involving programmatic screenshots of a local dev server or localhost site across viewport breakpoints.

0
installs

13 published skills