Éco-conception de services numériques (RGESN 2024 / GR491 / Green Software Foundation) appliquée pendant que Claude Code écrit ou revoit du code, avec un audit déterministe et des pratiques d'usage sobre inspirées de Boris Cherny. Présentation : https://institut-du-numerique-responsable.github.io/green-claude/.
★not rated 45▲
+1 6d agoA
tokens not measured
originalMIT
Deep-dive spec interviewer that produces production-grade specs through rigorous 1-on-1 interviews, with --verify drift detection against the codebase.
★not rated 48▲
+2 1mo agoA
tokens not measured
originalMIT
Claude plugins for Abnormal Security - AI-powered email security, threat detection, abuse mailbox cases, message and header forensics, and per-message remediation for MSPs.
★not rated 44 yesterdayA
tokens not measured
originalApache-2.0
Cross-vendor IT asset lifecycle management — warranty tracking, end-of-life/end-of-support flagging, and hardware refresh-cycle planning across whatever RMM platforms and documentation tools you have connected.
★not rated 44 yesterdayA
tokens not measured
originalApache-2.0
MCP-backed workflow for building UI with @marmoui/ui. Bundles the marmo-ui skill, /marmo-ui: commands, and the Marmo MCP server so agents read real component props instead of guessing. Works free without a token; add your Pro token for on-brand generation.
★not rated 41▲
+5 1mo agoA
tokens not measured
originalMIT
LiveView introspection and accessibility testing skills for Phoenix. Use htmlsnapshot() to capture state at any point, axe-core for WCAG compliance, timeline analysis for debugging.
★not rated 42 yesterdayA
tokens not measured
originalMIT
Teach Claude to detect, wire, and troubleshoot FreeRide — a local OpenAI-compatible gateway routing across free-tier providers (OpenRouter, Groq, NVIDIA NIM, Cloudflare Workers AI, HuggingFace).
★not rated 42 yesterdayA
tokens not measured
originalMIT
Skills for analyzing GitHub pull requests and issues in depth. Fetches contribution data from GitHub and researches architectural context via chunkhound-integration. Standalone useful for code review, and designed to be consumable by Claude Agent SDK applications.
★not rated 43 todayA
tokens not measured
originalMIT
Three MCP servers for PHP and JavaScript operations plus an optional PHP language server. PHP (php-tooling): PHPStan, ECS, Rector, PHPUnit, PHPUnit coverage gap analysis, Symfony Console. Administration (js-admin-tooling): ESLint, Stylelint, Prettier, Jest, TypeScript, Vite builds. Storefront (js-storefront-tooling)…
★not rated 43 todayA
tokens not measured
originalMIT
Verification-gated workflow plugin for Claude Code tasks. Adds lightweight hooks for task classification, verification tracking, and stop-time completion review.
★not rated 41 1mo agoA
tokens not measured
originalMIT
Agent-native Stata bridge for Claude Code. Drive DiD/IV/RDD and publication-ready esttab tables in plain language, then cross-validate each estimate against StatsPAI. Bundles an MCP server (21 tools, 14 workflow prompts, token-economy result schema, typed errors, multi-session) and an agent skill with an on-demand…
★not rated 43 3d agoA
tokens not measured
originalMIT
Alem Tuzlak's personal Claude Code skills and plugins.
★not rated 39 4d agoA
tokens not measured
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: