Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Personal X (Twitter) analytics — timeline engagement, mentions, follower tracking, read any tweet/thread, bookmarks, and combined briefings via X API v2. Cost-optimized with persistent local store and daily budget guards.
Write TypeScript code using the Thinkwell framework. Covers the @JSONSchema syntax, Plan fluent API, agent lifecycle, tools, skills, thought streams, and the thinkwell CLI.
Run a 6-8 minute conversational interview that gives a UK user transparency on their finances, surfaces their savings "leak" (the gap between what they could save and what they actually save), and projects their FIRE readiness. Use this skill whenever the user asks for a financial check-up, mentions FIRE or "financial…
Rewrite any raw content into polished business prose through an editorial pipeline with optional voice matching. Use when the user asks to "rewrite," "polish," "clean up," "tighten," "make this sound better," "turn this into something readable," "edit this for me," "make this professional," "rewrite in my voice," or…
Query the St. Louis Fed (FRED) economic data API. Use this skill to search for economic data series, fetch observations (GDP, unemployment, inflation, etc.), or browse FRED's catalog of categories/releases/sources. Trigger when the user asks about economic data, Fed data, FRED series, or wants to fetch/chart economic…
A project-memory system called Vibe Memory, or VBM, for Codex and Claude Code. It initializes project guidance, stores controlled rules, enables global instructions, and reads or writes verified memories during development.
Interact with the VALR cryptocurrency exchange API. Handles authentication (HMAC-SHA512 signing), account balance queries, market data retrieval, spot order placement, perpetual futures trading, fee queries, VALR Pay (instant P2P payments), crypto deposits and withdrawals, and more. TRIGGER when: the user mentions…
A guide for turning a product idea, requirements document, Lark document, or competitor analysis into a short build-ready product brief. The brief is written for coding agents such as Claude Code or Codex.
A production-grade developer design-system skill for AI coding assistants. Use it to enforce strict layout constraints, typography locks, accessibility compliance, and anti-slop visual rules across generated frontends.
Capture the intent behind staged changes as a provenance doc in docs/intents/, extracted from the Claude Code and Cursor chats that produced the code. Use when the user asks to generate or preview an intent doc, capture commit intent, check why the pre-commit intent hook skipped or failed, or run its self-test.
A toolkit for working with Microsoft Word files such as DOCX, DOC, and RTF documents. It can convert, extract, replace, merge, split, format, and check document content.
Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides…
A tool for turning articles, scripts, screenshots, product notes, subtitles, or other source material into Chinese Xiaohongshu posts. Xiaohongshu, also called Rednote, is a social platform built around image-and-text posts.
Inject the experiment orchestrator role into the current session. Drives the full investigation pipeline: hypothesis refinement, environment exploration, experiment execution, transcript analysis, and reporting.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
Build or update UI screens, dashboards, forms, modals, and tables. Use when the subtask is primarily a frontend implementation — page layout, component composition, responsive design, interaction polish, or UI state wiring to existing APIs.
Hunt for bugs in distributed consensus protocol implementations using a 2-agent strategy+testgen pipeline. Use when targeting consensus protocols (Raft, PBFT, HotStuff, Tendermint, etc.) for automated vulnerability discovery.
★not rated 11 3mo agoA53 tokens
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: