All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 438,345 of
them, each with its token cost per session, a security scan with the
line that triggered it, and whether it is the original or one of the
copies.
Creates, supersedes and validates decision records (ADRs) against the convention a collection already follows, instead of against a published spec it may never have adopted. Ships the decision-records skill: a propose-then-write flow that never rewrites an accepted record, and check-decisions.sh, a validator that…
★not rated 72
changed 2mo agoA
tokens not measured
originalMIT
Rules for communicating with humans as an AI agent. Read in full BEFORE composing any text another person will read: PR titles and descriptions, issues, code review replies, comments, discussion summaries, emails, chat and forum posts, commit messages, changelogs. Also before replying when someone responds to you, and…
Senior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.
Write, push, run, publish, and manage Kaggle Benchmark tasks using the kaggle CLI and the kaggle-benchmarks Python SDK. Use when the user wants to create or push a benchmark task (optionally with attached Kaggle datasets), run benchmarks against LLM models, check task/run status, stream or fetch execution logs…
Plan, generate, QA, and package continuous raster animation frame sets, GIF previews, and transparent spritesheet atlases. Use when the user asks for a GIF animation, animation frames, sprite rows, web/game animation assets, or reusable visual animation materials.
Use when Dan explicitly asks Claude, Codex, Copilot, Grok, Hermes, OpenCode, or OpenClaw to perform coding work. Route it through the shared AI Agent Board instead of launching the coding agent directly.
An academic-integrity self-review skill for checking research papers, revisions, and published-work concerns for possible data, image, statistical, or reporting problems.
A Chinese city travel service that can arrange DiDi rides, check trip details and prices, locate drivers, plan routes, search nearby places, and cancel orders. DiDi is a ride-hailing and local transport platform used in China.
Train, evaluate, and use Cherimoya sequence-to-function genomic models with the cherimoya command-line tools or Python API. Use when a user wants to run the end-to-end pipeline, use a trained model to do downstream tasks, or troubleshoot a run. Designed for users who may be new to Cherimoya or to sequence modeling…
Complete video ad creation toolkit — from creative brief to published ad. Includes hook formulas, script frameworks, multi-format strategy, A/B testing methodology, and batch workflow patterns. Integrates with Creatify API for automated URL-to-video, ad cloning, AI script generation, custom templates…
Generate or edit images with GPT Image through Codex/ChatGPT subscription authentication instead of OPENAIAPIKEY. Use for text-to-image, reference-image editing, or visual assets when the user wants local Codex auth, especially when no native image tool is available. Do not use for official OpenAI API-key billing or…
Route broad or end-to-end Minecraft Bedrock JSON UI work to the smallest applicable specialist skill. Use when a request crosses layout, data flow, forms, HUD, assets, pack integration, and validation, or when ownership is unclear.
Use when converting OHLCV alpha ideas into QuantSkills organization factor Skills, batch-generating non-duplicate framework-neutral quant factor Skill folders, validating them on cached real market data such as AkShare A-share and Yahoo US data, and writing factor evaluation reports.
The Heimdall skill for App Store Connect: what each asc- server covers, which one owns a task, and how to stay inside the credential boundary. Pair it with the asc- plug-ins for the areas you need.
★not rated 72▲
+15
changed yesterdayA
tokens not measured
originalMIT
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: