공개 Claude Code 마켓플레이스의 플러그인 19개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
필터와 일치하는 19개의 플러그인을 표시합니다.
lawve-ailawve-ai/awesome-legal-skills2
agents-incagents-inc/skills2
claude-code-skillsalirezarezvani/claude-skills1
pm-claude-skillsmohitagw15856/pm-claude-skills1.claude-plugin/marketplace.json이 포함된 repo를 제출하면 모든 plugin을 목록에 추가합니다.
marketplace 제출Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified or unwaived. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon (Anthropic long-running harnesses, verifier's law, SWE-agent, Ralph loop, Cognition), harness-runner agent + /cs-harness command. Use when an agent or subagent should pick up a goal, define its tasks, complete and verify them, and close the loop.
Event planning: run of show, budgets, venue contracts, supplier briefs, safety plans and post-event debriefs.
Test process and strategy: risk-based testing, test strategies, Definition of Done, smoke gates, test pyramid balance, effort estimates and post-mortems. Also covers E2E suite budgets, test ideas from stories and live features, framework choice, and attack-surface checklists. Agents (release-readiness-checker, quality-coach, release-engineer) run multi-gate go / no-go checks, audit work against the Definition of Done, and walk a release runbook with human gates.
foundations
Validate application against performance budgets
Build, monitor, and adjust fee budgets across the full matter lifecycle. At matter setup: translate scope into a phase-based fee estimate with contingency and AFA structure. In flight: run WIP reviews that explain variance, not just report it. When scope changes are confirmed: model the financial impact.
Reviews outside counsel invoices and related billing data for an in-house legal department, including LEDES or e-billing exports, OCGs, approved rates, discounts, budgets, AFAs, and staffing rules. Starts with internal comparisons before bringing in external data. Produces invoice review findings, MBR/QBR scorecards, dispute logs, and management reports. For demonstration purposes only and not professional advice.
Load and performance testing with k6 and JMeter, Lighthouse CI for Web Vitals, SLO-driven load plans, and performance budget gates. Covers tool choice and load profiles (with Gatling and Locust references), per-interaction INP budgets, flame-graph analysis, and database query-plan analysis.
operations-resilienceEngineering constraints for emerging-market products: network resilience, payload budgets, low-end device performance, integration cost modeling, and localization for varying literacy.
Serverless testing for AWS Lambda, Azure Functions and Cloudflare Workers: local emulators, cold-start and timeout budgets, and integration test suites. Builds integration tests from SAM, Serverless Framework, Wrangler, Vercel or Netlify definitions and covers .NET Lambda test tools. A critic agent (serverless-cold-start-critic) flags cold-start anti-patterns.
backend-distributedSpecification frameworks for features that call a model — approach tier, model pinning, output contracts, budgets, failure modes and eval design. Load when a spec touches model calls, prompts, retrieval, tool calling, agent loops or evals.
AI integration review patterns. Use when reviewing model API calls, prompt construction, LLM output handling, RAG pipelines, and tool-calling code. Covers prompt-injection call-chain tracing, output validation, stop reasons, token budgets, retry and timeout handling, streaming, and key/PII exposure.
Operate an evaluated agent with tools and authority in production through a runtime control plane covering versioning, staged rollout, fallback, cost and latency budgets, tool health, human escalation, disablement, and trace-to-eval feedback. Do not use for building agents, designing evals, or general release, SRE, security, or platform engineering — those methods stay with their specialist skills.
Review a code change for correctness, security, maintainability, and test adequacy, and reach a defensible verdict. Use when reviewing a pull request, diff, patch, or AI-generated change; when scoping an oversized review into reviewable units; when writing or triaging review comments; when assigning reviewers or setting review policy; or when investigating why a defect escaped review. Covers change sizing and attention budgets, risk-tiered checklists, severity-labeled comments, verdict and residual-risk records, review metrics that resist gaming, and the measured limits of checklists and AI reviewers. Do not use for implementing the requested change, root-cause debugging of a failing test or incident (use systematic-debugging), security assessment of a whole system (use security-audit-methodology), designing new code securely (use secure-software-engineering), architecture review across systems (use software-architecture), or reverse-engineering an unfamiliar codebase (use software-arc
Operate, configure, secure, and troubleshoot the LiteLLM AI gateway (proxy) and Python SDK: run the proxy (litellm --config), route to 100+ providers through one OpenAI-compatible API, configure model lists and routing/reliability, virtual keys, teams, budgets, rate limits, caching, guardrails, observability, and spend, and diagnose request failures. Use when deploying or running a LiteLLM proxy or gateway (config.yaml, ghcr.io/berriai/litellm), wiring the Python SDK or OpenAI SDK through it, or hardening a public-facing deployment. Do not use for operating a single inference engine (vllm, llama-cpp), for engine-selection methodology (ml-engineering), or for building applications on top of an LLM API (backend/frontend engineering).
Use this skill to shape product or engineering work before committing time to it: set appetites instead of estimates, narrow raw ideas into bounded problems, sketch solutions at the right level of abstraction, de-risk rabbit holes, write pitches, bet with capped downside (circuit breaker), and govern builds with discovered scopes and scope hammering. Adapted from Basecamp's Shape Up and extended for human+AI-agent teams. Use when a raw idea, feature request, or "redesign X" grab-bag needs to become a bounded project before anyone builds; when planning how much work an idea is worth; or when delegated agent builds need budgets, kill criteria, and non-convergence rules. Do not use for discovering whether a problem is real (use product-discovery), for portfolio-level sequencing across quarters (product-roadmapping-and-portfolio), for formal specification after the bet is placed (spec-driven-development), or for task-level prioritization frameworks like RICE (product-methodology).
Design, operate, and improve reliable production systems with SLOs, incident command, observability, error budgets, and operational practices. Do not use this skill for unrelated requests; route to the nearest named specialist.
12 Google Ads management skills: audits, keywords, ad copy, bidding, PMax, Shopping, audiences, conversions, budgets, Quality Score, remarketing, competitor analysis
Performance engineering: frontend performance budgets and Core Web Vitals, backend latency, memory and resource profiling, caching, and Python performance.
Design a Toast-1 harness for your backend or framework: exploration, evidence handling, context budgets, and evaluation, with optional runnable examples.
