Real-time guard on five Claude Code pre-execution hook events (tool calls, permission decisions, submitted and expanded prompts, and subagent creation) plus a response-end advisory that flags an action leaking a secret, installing a malicious package, or exfiltrating data, plus the skarn-audit skill (scan sessions and.
★not rated 34▲
+1
changed 3d agoA
tokens not measured
originalMIT
Open-source brand skills that turn an idea into a real brand — name, identity, voice & brand book — without leaving your AI agent. Works in Claude Code, Cursor & 70+ agents.
16 production writing-style skills for AI agents: 9 measurable frameworks (plain language, ASD-STE100, AP journalism, GOV.UK, Orwell's rules) and 7 character voices, as portable SKILL.md files.
Persistent memory for your agent as plain files in your folder: a hot cache injected every session and held under three size caps, per-session handoffs, and promotion into knowledge articles and rules only on your yes. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second…
★not rated 34
changed 10d agoA
tokens not measured
originalMIT
Claude Code skills for Unity MCP Server. Provides workflow-oriented guidance for C# editing, Scene/GameObject management, PlayMode testing, and Asset management using 108+ Unity automation tools.
★not rated 34 todayA
tokens not measured
originalMIT
Structured, artifact-driven development pipeline for Claude Code — plan, implement, review, and ship features with three ceremony tiers. Also includes arn-code-batch-cve-scan and arn-code-batch-cve-fix for CVE discovery, triage, and batch resolution. 37 pipeline skills, 18 specialist agents.
★not rated 33 1mo agoA
tokens not measured
originalMIT
Work WITH Storybook on React+Vite apps: audit a vibe-coded codebase for real-vs-slop components, capture flows/app-maps, write CSF3 stories, and ship — as focused skills, not one monolith.
★not rated 33 2mo agoA
tokens not measured
originalMIT
Risk-graded context engineering for AI-assisted software work — a catalog of agent skills, paste-ready command prompts, and change-record templates that keep agent work questioned, controlled, and reviewable.
★not rated 33 3d agoA
tokens not measured
originalMIT
Mountain route research for North American peaks: automated route beta reports with weather forecasts, avalanche conditions, daylight windows, and trip reports aggregated from 10+ sources including PeakBagger, SummitPost, WTA, and AllTrails.
★not rated 33 1mo agoA
tokens not measured
originalMIT
Skills that get AI assistants to stop agreeing with bad product ideas by default — pressure-test premises, separate hobbies from businesses, and refuse validation theater.
★not rated 33 1mo agoA
tokens not measured
originalMIT
Semantic search over the Garry's Mod Lua API wiki (gmodwiki.com). Adds the searchwiki and getpage MCP tools so assistants can look up GMod functions, hooks, classes, and examples.
★not rated 33 15d agoA
tokens not measured
GPL-3.0
Multi-platform content creation system for Chinese content - from research and image sourcing to writing, humanizing, and platform-specific formatting for Zhihu, Xiaohongshu, and WeChat.
★not rated 33 6mo agoA
tokens not measured
originalMIT
A cloud browser for automated web tasks, with one mode where an AI agent operates the browser and another where Playwright controls it directly. Playwright is a tool for writing browser automation scripts.
★not rated 33 3mo agoA
tokens not measured
originalMIT
ES: Vuelve a Claude en tu contra para criticar a fondo una idea, un plan o un proyecto entero — sin validar ni suavizar — por ocho ángulos, con investigación de fracasos reales y un veredicto priorizado de qué arreglar. EN: Turn Claude against you to harshly critique an idea, plan, or whole project across eight angles.
★not rated 33 3mo agoA
tokens not measured
originalMIT
Direct access to your browser's open tabs content via MCP.
★not rated 33 5d 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: