Principles for Japanese-language text communication with the user, meant to be consulted at the very start of any communication before writing prose. Covers term introduction, translation and Japanese phrasing, anti-compression, reference and quantity disambiguation, logic and document structure, evidence and…
★not rated 183▲
+8 4d agoA
tokens not measured
originalMIT
Rove activity hooks + agent skill for Claude Code: every session reports normalized activity events to the Rove daemon, and the bundled skill teaches the agent to drive rove api.
★not rated 183▲
+2 yesterdayA
tokens not measured
originalMIT
45 UX and design-system skills for AI agents: brand foundation, design tokens, layout, components, UX polish and an accessibility gate, plus live token extraction from any site through dembrandt.
Convene parallel role-specialized peer agents (dynamic roster, plan card first) to debate a cross-domain decision or audit a codebase in real time. Invoking Claude acts as CEO: convenes, routes peer-DMs, arbitrates deadlocks, writes a one-page decision log.
★not rated 182▲
+1 5mo agoA
tokens not measured
originalMIT
Give agents durable, scoped, explainable memory across sessions and repos via the Engraphis MCP tools. Use when you learn something worth keeping, need prior context before acting, or ask why/how a fact changed. Covers remember/recall, why/timeline, forget/pin/correct, sessions, and code search.
★not rated 182▲
+1
changed 3d agoA
tokens not measured
originalApache-2.0
A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed AI Agent Skills. Includes npu-smi device management, HCCL performance testing, and ATC model conversion.
Default diagrams for design docs, walkthroughs, and requirements (flowchart, sequence, class, ER, state, C4). GitHub wiki renders the fence. Confluence needs PNG or SVG as well.
Browser-native X workflows via x-use MCP: research, inbox reads, reviewed outreach, campaigns, posts, and threads. Requires x-use-mcp (pip install x-use-mcp) and an authorized X account.
Use when you want a delegated second opinion or implementation from GPT (Codex), Gemini, Grok (xAI), or OpenRouter (config-driven, 400+ models) - eight expert subagents (Architect, Plan Reviewer, Scope Analyst, Code Reviewer, Security Analyst, Researcher, Debugger, Writing Editor) and bundled…
Enhances Claude Code from producing raw code into delivering production-ready systems. 14 specialized agents handle architecture, tested code, security audit, CI/CD, and documentation. Use for building apps/websites/services, adding features, hardening, deployment, testing, review, or architecture design.
A Claude Code statusline that shows reasoning effort (⚡) and thinking (💡). 5 presets (xsmall-xlarge), Catppuccin theme, no Node/Nerd Font, native PowerShell on Windows.
Drop-in agentic loop skills — autoresearch, literature & scientific writing, data analysis, code/SQL/prompt optimization, red-teaming, and power analysis. Each loop binds to your own task at invocation time.
★not rated 180▲
+2 4mo agoA
tokens not measured
originalMIT
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use.
PRD lifecycle methodology engine: scaffolds PRD/SoT/EPICs to template, drives them to completion with stage skills, governs with hooks + deterministic readiness scoring.
★not rated 179▲
+2 2mo agoA
tokens not measured
originalMIT
Read and write Notion with a token: search pages, query databases with typed filters, read and write pages as markdown, and batch edits. Runs the open-source notion-mcp-server locally; not made by Notion.
★not rated 179
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: