Mindket

AI skills and agents for developers

Prompts, coding agent briefs and kits for writing and reviewing code with fewer tokens.

Categories and filters
Filters
Clear filters

Listings

stuntd

pollix · Kit

A browser demo that answers questions two ways, with the base Laya model zero-shot and with a small head that stuntd trained for each decision, across support…

New

Sygma ASR Arabic

abedbanna · Kit

A test bench that records or takes Arabic speech and compares Sygma's decoding with the base model's greedy output, with word error rates. For speech researche…

New

DeepSite v2

ongudidan · Kit

A coding platform powered by DeepSeek AI that generates applications from your requests. For developers, data scientists and AI engineers who want generative A…

New

DeepSeek-V4.1-Flash-1017

deepseek-ai · Kit

An image and text model for reasoning, coding and agent tasks with a 1M-token context window, updated from DeepSeek-V4.1-Flash. Made for developers who build a…

New

Qwen3.8-27B

Qwen · Kit

Reads text, images and video and replies in text, with a 27B open model tuned for coding, research and multi-step agent work. Suits developers who run models t…

New

Ripple-65B Preview

ricursiveAI · Kit

Runs terminal coding agents on a 65B dense language model that reads up to 1,048,576 tokens of context. Made for developers and researchers who want open Apach…

New

deepseek-stack

aicodeking · Skill

Helps DeepSeek V4.1 Flash and V4 Pro plan, check their work and stop at a set point, so a cheaper model behaves more like a costly one. It suits developers usi…

New222

Microsoft Agent Skills

microsoft · Skill

Microsoft’s library of skills, agent personas and MCP setups for coding agents on Azure and Microsoft Foundry: one skill per SDK in five languages, plus deploy…

New3183

Cloudflare Skills

cloudflare · Skill

Cloudflare’s own 22 skills for coding agents that build on Cloudflare: Workers, Durable Objects, the Agents SDK, the cf and Wrangler tools, Turnstile and Cloud…

New3298

ehmo’s eight design skills for coding agents: iPhone, iPad, Mac, Apple Watch, Vision Pro, Apple TV, Android and the web. They hold rules from Apple’s HIG, Mate…

New638

ClickHouse Agent Skills

ClickHouse · Skill

ClickHouse’s official skills for coding agents. They review table designs and queries against written rules, advise on architecture, troubleshoot Node.js clien…

New563

AI Design Skills

elayadesign · Skill

Elaya’s two free design skills for AI coding tools. One builds a landing page from intake questions to conversion copy and a fixed visual system. The other des…

New14.7k

Emil Kowalski’s seventeen skills for coding agents that build interfaces. They build, review and audit animations, remove motion an app does not need, and cove…

New54.2k

SigmaStudioz Agent Skills

sigmastudioz · Skill

Lex from SigmaStudioz’s six skills for coding agents. Three shape engineering work: domain-driven changes, timeboxed spikes and outcome reviews. Three are visu…

New1

squirrelscan skills

squirrelscan · Skill

squirrelscan’s two skills for coding agents, MIT licensed. One teaches your agent to run the squirrel website audit program, and the other drives the loop of a…

New106

Cheap Agent

muaaz9329 · Kit

Moves routine coding in Claude Code or Codex to a low-cost model that must prove its work with a test, so your main model's usage lasts longer.

New310

Agentic Resource Registry

AgenticResourceRegistry · Kit

Keeps a team's coding agent skills, hooks, prompts and agent files in one self-hosted registry, with review of new entries and usage insight. Suits engineering…

New4320

Diffinery

codician-team · Kit

Hosts Git repositories, pull requests, code review and GitHub Actions workflows on your own Cloudflare account, with guarded accounts for AI coding agents.

New82

imbo

Bearisbug · Kit

Sends messages between coding agent sessions, so a question from one agent lands inside another's running session, on your computers or a teammate's. For devel…

New111

Harness Leaderboard

joelniklaus · Kit

Compares nine coding agents running the same open model, with three attempts per task, confidence intervals and public trajectories. For developers choosing wh…

New