Find plugins

by Eugene Novikov

DotRush C# LSP for Claude Code with live LSP injection, semantic rename, solution diagnostics and .NET CPU/managed-memory profiling skills. Auto-installs required tools on first use.

Context-continuity workflow for multi-session agentic coding: research, plans and handoffs kept in the target repository.

by HKTITAN

The Duolingo playbook as agent skills — retention, streaks, gamification, learning science, curriculum, efficacy, product metrics, experimentation, growth, brand, voice, culture, engineering, observability, and LLM feature design. Distilled from 750 posts on blog.duolingo.com plus the Handbook and Design System. Start at the /duolingo router; UI craft routes out to design-engineering.

by John Kozaris

ESP32 firmware review for all variants, FreeRTOS, ESP-IDF/PlatformIO, peripherals, and memory

by chock-core

Flag when code puts an AI system into an EU AI Act Annex III high-risk domain — biometrics, critical infrastructure, education, employment, essential services and credit, law enforcement, migration, justice and elections — and require the Article 9-15 obligations be owned before the capability ships. Use when adding scoring, ranking, eligibility, or screening over people. Do NOT use for banned practices (see eu-ai-act-prohibited-practices) or for systems with no natural-person impact.

by chock-core

Refuse to implement AI practices banned outright by EU AI Act Article 5: social scoring, untargeted facial-image scraping, emotion inference at work or school, biometric categorisation by sensitive traits, profiling-only predictive policing, subliminal or vulnerability-based manipulation, real-time remote biometric ID in public spaces, and NCII/CSAM generators. Use when a feature request names any of these. Do NOT use for lawful biometric verification, fraud detection, or safety/medical emotion detection.

by chock-core

Keep EU AI Act Article 50 duties in the code: disclose to a person that they are interacting with an AI system, mark generated audio, image, video, and text in a machine-readable format, and label deepfakes. Use when adding a chatbot or assistant surface, a generation endpoint, or an export path for model output. Do NOT use for assistive editing that does not substantially alter the input, or for internal batch jobs with no human recipient.

eval is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.

by Nate Swenson

Grades a real run of a skill against the contract that skill committed to, keeps only the findings it can cite, and turns the ones that will recur into permanent eval cases.

by voitta-ai

Keep a high-velocity development loop alive when the repository you integrate into gains a merge gate you cannot satisfy and forking is disabled: an experimental upstream repo, one reviewed fork-sync PR into the integration repo, a pre-push guard, and change-management issue framing.

by Francesco Sorrentino

Keeps Claude Code from spending your quota on work the top model didn't need to do: declared pre-budgets with deterministic 2x/3x enforcement, cheap-executor routing, objective token telemetry. Small one-offs pay a 5-20% premium (measured) - built for sessions that delegate. New in 1.42: reads video and audio for you at zero Claude tokens - a whole clip in one contact-sheet image, transcription on your CPU, voice-over timing checked before the studio; long footage on free-tier Gemini.

by chock-core

trigger: web research where a direct fetch fails, is blocked, or needs JS rendering. avoid: reaching for the Firecrawl connector as the default fetch path.

by chock-core

trigger: web research where a direct fetch fails, is blocked, or needs JS rendering. avoid: reaching for the Firecrawl connector as the default fetch path.

by Anilcan Cakir

FlutterSDK AI skills, commands, and MCP for Flutter: Wind UI, Magic Framework, Dusk, Telescope, Artisan

by SidCorp-co

Declared-edge layer for code: cm: annotations carrying the couplings LSP cannot derive (cross-language and cross-process contracts, parallel rules, flows, guards), verified in CI and auto-injected into the agent's context before it edits the file they are on.

by John Chilton

Corpus-grounded, schema-validated skills for constructing Galaxy workflows.

by akenoowww

Task-specific frontend workflows with typed product structure, capability-first implementation plans, and SHA-bound design/runtime evidence.

by ncaq

F# code intelligence for Claude Code via fsautocomplete LSP.

by Harry Yep

Multi-model orchestration: tier agents, routing rules, blind panel, ultra fleet, model config, and drift doctor.

by jaguilar87

GAIA — Generative AI Interface for Agents. Security-first multi-agent orchestration for Claude Code. Risk-classified commands: reads run free, state changes need approval, irreversible ops blocked.

by Open Agent Tools

Dev workflow and AI agent development skills for Claude Code

by Jarad Johnson

A generic bank of reusable AI skills for thinking, planning, visual direction, research, meetings, and agent tooling

by voitta-ai

Deleting the branch on gh pr merge can auto-close a dependent PR stacked on it.

ghfactory is an open-source Claude Code plugin indexed from GitHub. Review its manifest and source before installing.