All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 437,288 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.
MANDATORY skill that activates whenever the OpenSpec apply phase begins. Triggers: /opsx-apply runs, the openspec-apply-change vanilla skill is referenced or active, openspec instructions apply is invoked, or the user asks to implement, apply, execute, or build out an OpenSpec change ('implement the change', 'apply…
Model Context Protocol server for the fmpsdk Financial Modeling Prep library. Runs locally from the fmpsdk-mcp Python package. Needs 1 environment variable to run.
★not rated 215 2mo agoA
tokens not measured
originalBSD-3-Clause
A video-downloading skill built around yt-dlp, a command-line tool that retrieves media from websites. It supports sites including YouTube, Bilibili, and Twitter, among many others.
A product-requirements document writer that turns a brief or unclear idea for an app, website, or tool into a detailed plan. It writes the plan in Chinese by default and structures it for people and AI coding assistants to implement.
Create, refine, or replace Canvasight graphs through writecanvasightgraph; combine professional content Skills with Canvasight's validated horizontal graph structure; and assign explicit or clearly matched Skills to individual Task Nodes. Use when the user asks Codex to generate or update Canvasight nodes, Asset…
MCP server "task-orchestrator" as configured in jpicklyk/task-orchestrator. Runs in Docker (ghcr.io/jpicklyk/task-orchestrator:latest). Needs 6 environment variables to run.
★not rated 214▲
+1 todayA
tokens not measured
originalMIT
Opinionated engineering agent team with progressive-disclosure specs for Python / TypeScript / Go monorepos. Ships PA / SWE / Tester / PR Reviewer / On-Call sub-agents, /squid-plan / /squid-implement-task / /squid-implement-night pipelines, and a library of language/framework/infra specs that agents load on-demand.
Battle-tested configuration system for Claude Code agents: safety hooks, composable skills, review agents, workflows, and an index of the working rules injected at session start. The plugin version comes from the marketplace entry that lists it.
★not rated 214
changed 14d agoA
tokens not measured
originalMIT
A plugin collection for TavernWeave, a system for guided brainstorming, project blueprints, reusable libraries, and evidence-based review in rolecard and vibe-coding projects.
★not rated 214▲
+8
changed 8d agoA
tokens not measured
Write captions, on-screen text, hashtags, and CTAs for short-form video that earn saves and sends without tripping engagement-bait penalties. Use when someone asks for a viral caption, an instagram caption or tiktok caption or video caption, wants to fix a weak cta or call to action, asks about hashtag strategy and…
A workflow for solving mathematical modelling competition problems and delivering the work as a LaTeX paper. It organises the problem statement, modelling notes, code, results, references, and final PDF.
A personalised chat tool that uses a user profile and vectorised notes, meaning notes indexed so related ideas can be found by meaning. It uses earlier thoughts and notes to shape replies.
Product Manager-led orchestration with optional thinking modes, MCP servers, and flexible input types (request/PRD/PRP).
★not rated 213 1y agoA26 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: