tailwindcss agents

CaliCastle/cali.so

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

CaliCastle/cali.so

Agent

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

CaliCastle/cali.so

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

PostHog/posthog.com

Agent

Reference this guide when creating pages or working with app templates.

PostHog/posthog.com

Agent

Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite, apply Simplified…

PostHog/posthog.com

Agent

Every visual change needs before/after screenshots in four states: light and dark, narrow window and wide window. Anything that moves needs a before/after GIF as well. This guide explains how to capture them, and how to put them in the PR.

boussadjra/vuestrata

Agent

Analyze an existing codebase area and produce .specify/specs//research.md or an inline research summary.

boussadjra/vuestrata

Agent

Generate a checklist for validating a feature spec before implementation begins.

boussadjra/vuestrata

Agent

Review or amend the project constitution. Displays current principles and optionally proposes amendments through the governance process.

incubrain/foundry

Agent Claude Code

UI/UX visual bug detection using the agent-browser skill. Read-heavy — only modifies files when explicitly asked.

incubrain/foundry

Agent Claude Code

Deep codebase research and exploration. Read-only — does not modify files.

incubrain/foundry

Agent Claude Code

Nuxt 4 layer development specialist for the IncuBrain Foundry project.

tutur3u/platform

Agent Claude Code

Use this agent when the user requests code refactoring, code improvement, code cleanup, or optimization of existing code. This includes requests to make code more maintainable, reduce duplication, improve performance, enhance readability, or align with best practices. The agent should be invoked proactively after the…

tutur3u/platform

Agent Claude Code

Use this agent when the user needs to create, update, or improve automated tests for their codebase. This includes writing unit tests, integration tests, component tests, or test utilities. The agent should be used proactively after new features are implemented or when existing code lacks test…

Dwsy/agent

Agent

An update summary for a Pi Agent system, describing changes inspired by Claude Code version 2.1.19.

Dwsy/agent

Agent

A quick reference for the Pi Agent system, including its agent modes and read-only, planning, and standard ways of working.

Dwsy/agent

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

aitorllj93/babilim-info

Agent

You are an expert in comparative mythology and you are helping me to build an online library of mythology. I will pass you a “Culture” and I want you to write an article about it based on this template. If you make reference to any specific deity or character, use [[Wikilinks]]. Make the article feel narrative for…

aitorllj93/babilim-info

Agent

Agent "motifs-generator" from aitorllj93/babilim-info, covering introduction: the motif at a glance, comparative analysis, structural function in narratives, archetypal and psychological readings and variants and submotifs.

aitorllj93/babilim-info

Agent

You are an expert in comparative mythology and you are helping me to build an online library of mythology. I will pass you a “Motif / Mytheme / Mythologeme” and I want you to write an article about it based on this template. If you make reference to any specific deity or character, use [[Wikilinks]]. Make the article…

voidmatcha/ui-clone-skills

Agent Claude Code

Parse downloaded JavaScript bundles for animation-library construction sites and concrete parameters. Invoked at Phase 5d when bundle-map.json detects Lenis, GSAP, Framer, Anime, Webflow IX2, Lottie, or related motion libraries but transition-spec.json is empty or under-populated. Writes bundle-extraction.json for…

voidmatcha/ui-clone-skills

Agent Claude Code

Iterate Phase 7 visual-fix cycles in a separate context with vision-free hard rule (no PNG/JPG/WebP reads). Invoked after section-compare.sh or tree-diff.sh reports FAIL. Reads gate text outputs (auto-diagnose, tree-diff-status, computed-diff), applies ONE scoped fix per iteration, re-runs gate, max 5 iterations.…

voidmatcha/ui-clone-skills

Agent Claude Code

Phase E LLM visual review for visual-debug — read ref/impl PNG pairs at every scroll position, judge PASS / PARTIAL / FAIL semantically, return a verdict table. Used after AE + SSIM + auto-diagnose agree. Vision-using (the inverse of visual-debug-iterator) — the 44K vision tokens stay in the subagent context, only the…

luminary19/atelier

Agent

Atelier suite build engineer (Opus). Owns the IMPLEMENTATION half of the image-first pipeline: takes atelier-design-lead's spec packet (comps + role-named tokens + per-section analysis) and writes the bespoke, token-driven frontend that FAITHFULLY matches the comps — components (atelier-components), motion…