build-with-dhiraj/ai-workflow-framework-portability-kit

Portable, self-contained snapshot of a complete Claude Code setup — 36 specialist agents, 162 skills, plugins, MCP servers & host tooling. Clone, claude login, run one script, restore the whole orchestration stack in ~20 min.

This repository also configures its own agents. See what ai-workflow-framework-portability-kit tells them →

5Stars on the repository
198Mods indexed here, across every type
21d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

a11y-audit

02

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Audit a UI or design against WCAG 2.2 AA/AAA and ARIA patterns, returning criterion-referenced findings with severity and specific fixes. Use when the user wants an accessibility check, contrast verification, keyboard/screen-reader review, or wants to confirm a component meets POUR.

not rated 5 21d ago A 64 tokens copy · 91% MIT

add-custom-mcp

03

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Discover the best community MCP server on GitHub/npm for any service, install it into Claude Code via the claude mcp CLI, wire authentication from existing local credentials, and verify tools work. Use when the user asks to add, install, connect, or activate a custom MCP server or connector for any tool (GitLab, Jira…

not rated 5 21d ago D 86 tokens original MIT

arize-experiment

05

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluate AI, experiment…

not rated 5 21d ago A 73 tokens copy · 86% MIT

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output…

not rated 5 21d ago A 81 tokens copy · 84% MIT

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

A downloader for YouTube subtitles, also called captions or transcripts, plus video chapter data, speaker labels, and cover images. YouTube is a video-hosting service, and transcripts are written versions of spoken content.

not rated 5 21d ago A 107 tokens copy · 100% MIT

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.

not rated 5 21d ago A 43 tokens copy · 100% MIT

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

How to write effective prompts for Claude Design (claude.ai/design), for both creating new designs and editing existing prototypes, decks, or pages. Use this skill whenever the user wants to prompt Claude Design, iterate on a Claude Design project, convert feedback or a spec into Claude Design instructions, or asks…

not rated 5 21d ago A 102 tokens original MIT

color-expert

12

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Use when working with color naming, color theory, color spaces, color definitions, or any task involving color knowledge - palettes, ramps, gradients, conversions, accessibility, perceptual matching, pigment mixing, print-vs-screen color, CSS color syntax, or historical color terminology. Use this skill whenever the…

not rated 5 21d ago B 92 tokens original MIT

defuddle

17

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already…

not rated 5 21d ago A 74 tokens copy · 100% MIT

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Anti-slop frontend skill for landing pages, portfolios, and redesigns. Reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check. Triggers on "make this look premium", "build a beautiful…

not rated 5 21d ago A 116 tokens copy · 98% MIT

design-tokens

19

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Generate, extend, or audit design tokens in DTCG format with the 3-tier architecture (primitive → semantic → component). Use when the user wants a color palette, type scale, spacing/shadow/radius/motion tokens, multi-brand theming, or wants to validate token files. Covers colors, typography, spacing, shadows, borders…

not rated 5 21d ago A 92 tokens copy · 89% MIT

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude Code

This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mentions "GEPA optimizer", "LLM reflection", "execution trajectories", "agentic systems optimization", or needs to optimize complex multi-step agents using…

not rated 5 21d ago A 80 tokens original MIT

emil-design-eng

23

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Emil Kowalski's philosophy on UI polish, motion design, micro-interactions, easing, transitions, and the invisible details that make software feel alive instead of static. Triggers on "animate this", "add motion", "easing curve", "transition", "hover state", "micro-interaction", "make it feel alive", "polish the…

not rated 5 21d ago A 97 tokens copy · 97% MIT

error-analysis

24

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Help the user systematically identify and categorize failure modes in an LLM pipeline by reading traces. Use when starting a new eval project, after significant pipeline changes (new features, model switches, prompt rewrites), when production metrics drop, or after incidents.

not rated 5 21d ago A 53 tokens copy · 100% MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: