Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,173 indexed, measured the same four ways as everything else here.
Generate publication-quality DESIGN.md v2 files from any website URL. Analyzes CSS, typography, colors, components, layout, content, accessibility, state patterns, and iconography to produce a 17-section design system reference that AI agents can use to reproduce the website's visual style. Use when the user wants to…
A command for reviewing the current state of a SpecPilot requirement, where SpecPilot tracks feature requests through planning and implementation stages. It checks the request against its stage and reports what is complete or still missing.
MCP server "fxflow" as configured in bmarshall511/forexflow. Launched with pnpm --filter @fxflow/mcp-server exec tsx src/index.ts. Needs 2 environment variables to run.
★not rated 14▲
+1 4mo agoA
tokens not measured
AGPL-3.0
Set up a web-based Claude Code conversation history viewer with FastAPI backend. This skill should be used when the user wants to view, search, or manage their Claude Code conversation history through a web interface, or when they ask about setting up a history viewer, conversation browser, or session manager for…
Spawn one or more OpenAI Codex CLI subagents from bash to offload context-heavy work from the parent Claude. Use when the user says "use codex", "build with codex", "ask codex", "get a codex second opinion", "compare codex vs claude", "have two agents try it", or otherwise asks to delegate or parallelize work to…
Write or edit OpenSCAD (.scad) files using the BOSL2 library. Use whenever the user is designing a 3D-printable part — jigs, holders, brackets, enclosures, fixtures, household items — and the file is OpenSCAD. Covers the user's house style (BOSL2 idioms, anchors, epsilon/layerheight baselines, Customizer parameters)…
Cross-source analysis for detecting patterns across data sources. Includes intention-reality gap detection, commitment accountability tracking, and serendipity/convergence analysis. Reads vault.toml and queries normalized SQLite databases (see SCHEMAS.md).
Scores candidates against an ICP rubric with evidence-based evaluation. Handles single profiles and batch screening with ranked comparison tables. Use when the user pastes a candidate profile (LinkedIn text, resume, GitHub), multiple profiles, or asks to evaluate/compare/rank candidates.
A toolkit for taking software apart to inspect how it works, across formats such as Android packages, Windows programs, Linux binaries, JavaScript, and firmware.
A browser-based operations assistant for Xiaohongshu, a Chinese social-media and shopping platform. It uses a logged-in Chrome browser to analyse accounts and content and manage publishing workflows.
MCP server for Microsoft To Do via Microsoft Graph. MSAL device code flow, no client secret needed. Runs locally from the @mag-cie/mcp-microsoft-todo npm package. Needs 2 environment variables to run.
★not rated 14▲
+2 4mo agoA
tokens not measured
originalMIT
Prevents overengineering when designing, implementing, refactoring, or reviewing software. Use when the user asks to implement a feature, add an abstraction, refactor code, review a design, simplify existing code, or make an architectural decision. Also triggers when the user asks if code is too complex, whether to…
Telegram channel analytics and scheduled publishing, through the slop-writer MCP server's tools. Covers posts, comments, engagement over time and forwarder networks; subscriber growth and churn by source; who subscribed lately and which of them are bots; views by hour of day; a discussion group's threads and…
A portable GTD trusted system for Claude Code — capture, clarify, update, organize, engage, and review commitments in plain Markdown lists under memory/gtd/. Calendar writes fail closed; engage and review stay human-led.
★not rated 14 3mo agoA
tokens not measured
originalMIT
Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4)…
Install and verify Shellby MCP on a Mac using terminal access only. Use when a user asks an agent to install, set up, configure, or finish a new Shellby MCP installation from this repository.
Dispatch a research or build task into a live tmux session running another LLM CLI (Codex/GPT, GLM/Z.AI, Claude, etc.), then collect the result via a file-based output contract and an event-driven handback ping. Use when the user wants to hand work to another model running in a tmux window, fan a long-running task out…
Use this skill when the user wants to integrate Mayar payments or billing into an application—hosted, embedded, or native checkout, payment links, invoices, memberships, subscriptions, credit wallets, licenses, QRIS, or webhooks—or operate their Mayar account from the terminal, including balance, products, customers…
Self-improving robotics expertise for AI agents: skills for architecting, integrating, simulating, visualizing, testing, and training physical-AI applications (ROS 2, Nav2, Gazebo, LeRobot, Isaac, HuggingFace) — captured from real builds, mined from the ecosystem, evidence-verified.
★not rated 14
changed 14d agoA
tokens not measured
originalMIT
Eliminates generic AI-generated design from any front-end you build or review, web or mobile. 20 reference modules: the slop taxonomy, personality axes and product registers, mobile and app-screen patterns, trust signals, data visualisation, a craft list, a pre-emit checklist and a worked example.
★not rated 14 2d agoA
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: