Find plugins

by Inbrace

Audit a Claude Code setup for a model transition — reads today's Anthropic docs, explores the project, checks the known traps (Opus 5 to 5.5, Sonnet 5 to 5.5): report, ask, then apply only what you approve.

by Jung Jiwon & Lee Jongkwan

The incident-response role on contract v3: 장애 후 무엇을 배웠고 재발을 무엇으로 막을 것인가. use_when: 장애 종결 직후. Hand-off: 용량 부족이 원인이면 → capacity-planning; 계측 부재가 원인이면 → observability.

by Lukas Kellerstein

Infrastructure plugin for Kubernetes, Istio, Helm, Terraform, Traefik, and auth workflows.

by Junjie Luo

In-lab human interaction with deployed prediction endpoints — the Claude Code chat is the UI. CONSOLE mode (default): patient-first on-demand inference — list patients, view the full chart, list available models (Endpoint_Set packages + live status), and run 'this model on this patient': the endpoint-predict MCP tool prepares the payload (required tables + trigger record), POSTs to the endpoint, and returns the score verbatim with a data-gaps report. STUDY mode: formal reader protocol (frozen review_bundle.json, blind→assisted session, decision-influence metrics vs gold). Endpoint-agnostic: local Flask, Databricks, SageMaker — same wire contract.

Non-loopback remote over plain HTTP.

by DH Shin (신동형)

신동형 인사이트 4종 문서 생성기 (Word KR+EN, PowerPoint KR+EN). v0.9.1 Unified Deep-Verify Edition: 동적 워크플로(ultracode) 하니스 내장, Deep Verification(Claims Ledger 기반 할루시네이션 차단), So-What 인사이트 프레임워크, 시각화 카탈로그, Word 챕터 자동 번호(H1C/H2C + HEADNUM 게이트), 4중 품질 게이트(toc/content/claims/judge).

by phazurlabs

Turn your AI agents and automations into installable plugins and packages — 12 skills, 10 commands across 3 phases (ASSESS → PACKAGE → SHIP). Covers every major framework (LangChain, CrewAI, AutoGen, Pydantic AI, LlamaIndex, n8n, Flowise, Dify, ComfyUI, browser agents) and every distribution target (MCP servers, Claude Code plugins, Custom GPTs, Docker, PyPI, npm, cloud deploy). Commands: /agent-guide, /agent-audit, /pick-target, /pick-framework, /gen-package, /gen-install, /pre-ship, /secure, /agent-roast, /glossary.

by David Kim

Read-only audit of the always-on instruction surface — host and container — for context waste, dead rules, cross-layer contradictions, and unclear authority.

by Simon Heimlicher

Create and audit instruction assets: skills, subagents, and agent prompt standards

by Simon Heimlicher

Create and audit instruction assets: skills, subagents, and agent prompt standards

by Simon Heimlicher

Create and audit instruction assets: skills, subagents, and agent prompt standards

by Ayan De

Researches a named company's interview process from public web sources and produces an evidence-graded interview-prep report — every predicted question labeled by how well-grounded it is, never a list of generic questions dressed up as company-specific ones.

by elisezhu123

Drive the iOS Simulator from Claude Code: live stream panel, taps and gestures, accessibility tree and OCR, apps, build & run. Ported from dsh-ios.

by Pierre-Yves Duquesnoy

20 skills that steer Claude when building IRIS For Health Interoperability productions — a task→component map, messages, BS/BP/BO, BPL, DTL transformations, HL7 v2 schemas, SOAP/REST, FHIR, DICOM, lookup tables, alerting, security, production lifecycle, message search/debug, a TDD-first workflow, and a post-build conformance review. Start at the iris-interop router. Assumes an IRIS MCP server (iris-agentic-dev or iris-interop-dev) is available. Ships 11 hooks (SessionStart conventions bootstrap + a UserPromptSubmit topic router that names the skills the turn actually needs + 2 PreToolUse gates that block non-conformant writes, illegal identifiers, class loads/compiles smuggled through iris_execute, and namespace-only classes missing from src/ + 6 PostToolUse guards, one of which warns when a put or a production edit leaves src/ stale + 1 blocking Stop gate that refuses to finish until the conformance pass has run) + 4 agents (interop-builder, deploy-smoke-test, introspect-dont-guess, conformance-reviewer).

by Thomas Tartrau

Set up an Ironflow project, write workflows and custom operations, test them end to end, and review handlers for replay and secret pitfalls

by iskron

NKS methodology skills — orient, write, design, and weave an NKS graph through the iskron_* MCP tools.

by Itixo

Itixo library for Codex users: custom-agent TOML templates, safe installer, prompts and rules. Includes Dirigent orchestration with shared itixo-* agent IDs. Recommended companions: the caveman marketplace (https://github.com/JuliusBrussee/caveman) and Mattpocock Skills (https://github.com/mattpocock/skills).

by Itixo

Itixo library for Claude users: agents, skills, rules and prompts shared across the company. Includes orchestration module (orchestrator on user-selected model delegates precise steps to cheaper-model subagents). Recommended companions: the caveman marketplace (https://github.com/JuliusBrussee/caveman) and Mattpocock Skills (https://github.com/mattpocock/skills).

by Itixo

Consumer guide for the @itixo/component-library design system: install, Tailwind v4 wiring, DashboardLayout, design tokens, and the component/prop reference.

by Itixo

Consumer guide for the @itixo/component-library design system: install, Tailwind v4 wiring, DashboardLayout, design tokens, and the component/prop reference.

Agent plugin for j2html-toolkit resources for Copilot customizations, covering Spring Boot integration, Bootstrap, HTMX, and template engine usage.

by janjaali

Reusable, agent-agnostic skills: general code and markdown conventions, Scala ADR compliance, and a spec-driven development workflow.

Agent plugin for browsing and linking to JavaDoc for any Maven Central artifact via javadocs.dev.

by Nathan Wong

System One sweeps over the jev-latest model: ground text against sources, pick browser elements, tag mail and rows.