Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 389,383 indexed, measured the same four ways as everything else here.
Evidence-first development — surround the implementation with an executable spec and a gauntlet of constraints (tests, types, coverage, mutation) so line-by-line review becomes optional. Use when the user explicitly asks for high-assurance or evidence-first work ("reliable", "TDD", "prove it works", "I won't read the…
★not rated 757▲
+4 3d agoASkillSpector: pass116 tokens
originalMIT
Use when checking skills for security or quality issues, reviewing audit results from skills.sh or Tessl, or remediating findings across published skills.
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?".
Use when a change is non-trivial by DSH standards (behavior, architecture, cross-file contracts, process/tooling, testing strategy, or on-disk/wire/config formats), when choosing between technical alternatives, superseding a decision, or writing a postmortem. Records the why and rejected options in .agents/notes/ with…
Browse websites, read web pages, interact with web apps, call website APIs, and automate web tasks. Use Neo when: user asks to check a website, read a web page, post on social media (Twitter/X), interact with any web app, look up information on a specific site, scrape data from websites, automate browser tasks, or…
Sync local files with a Kanwas workspace using the kanwas CLI. Use when the user wants to pull workspace content into the repo, push local edits back, or bulk-import markdown files from disk. Workspaces are trees of markdown notes organized into canvases (directories).
A project knowledge base for JiwuChat, a cross-platform chat application built with Tauri 2.9 or later and Nuxt.js 4.0. Tauri lets web technologies run as desktop applications.
Skeptical second-opinion reviewer. Reads the diff and the builder's evidence, then returns PASS or NEEDSWORK with specific findings. Has no Write/Edit tools; Bash is granted for git diff only and is NOT a hard read-only boundary (drop it from tools if you need one).
A Chinese-language skill for writing prompts, scripts, and shot lists for AI-generated short videos, including stories, product videos, advertisements, travel scenes, and interface demonstrations.
Search the documents in the company folders connected to this plugin (SFTP, FTPS, FTP, WebDAV, Nextcloud, ownCloud, S3, Synology, QNAP, FRITZ!Box, Hetzner Storage Box). Use when the user asks about the content of their files, price lists, contracts, manuals, emails or spreadsheets, or which folders are connected.
Use when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
A writing guide for applications to China’s National Natural Science Foundation, a major public research-funding body. It covers sections such as the abstract, background, research plan, originality, and feasibility.
Complete documentation knowledge base for ofa.js framework. Use when users ask about ofa.js usage, component development, page modules, routing configuration, state management, or want to build Web applications without Node.js/Webpack.
Genjutsu - the art of illusion for Claude Code and claude.ai. Cast motion and paint visual signatures into Web, Android (Compose), and Apple (SwiftUI) interfaces. Anti-AI-slop creative coding.
★not rated 754▲
+33
changed 6d agoA
tokens not measured
original
Taste Skill, subtitled "the anti-slop frontend framework for AI agents," adjusts layout, typography, motion, and spacing in AI-generated interfaces. The skills cover different registers, including a minimalist editorial style and an industrial brutalist style, and several generate reference images before any code is…
Use when editing VibeResume templates, turning resume facts and a target role into a one-page or two-page HTML resume, and validating the generated PDF.
/skysynth: coding agents build a system specialized for your workload, checked by tests or machine-checked proofs. Includes the /skysynth skill, the agent roles (Spec Builder, Planner, Coding Agent, Evaluator, Critic, Auditor), and the hook that runs the tests before anything is delivered. Also install the skydiscover.
★not rated 752▲
+20 1mo agoA
tokens not measured
originalApache-2.0
Daily cross-platform rankings of AI agent skills (skills.sh, ClawHub, Tencent SkillHub, GitHub, X/HN/Bluesky). Use when the user asks which agent skill to install, what is trending, whether a skill is popular or trusted, or wants to compare skills. Read-only public CSV data; it recommends and links, it does not…
Implicit feedback scoring, confidence decay, and anti-pattern detection. Use when understanding how the swarm plugin learns from outcomes, implementing learning loops, or debugging why patterns are being promoted or deprecated. Unique to opencode-swarm-plugin.
★not rated 749▲
+1 3mo agoA49 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: