14 plugins de marketplaces públicos de Claude Code. Cada uno agrupa skills, comandos de barra, agentes, hooks o MCP servers que se instalan juntos.
Mostrando 14 plugins que coinciden con estos filtros.
pmstackRyanAlberts/pmstack1
magnus-agent-skillsmagnus919/agent-skills1Envía el repo con .claude-plugin/marketplace.json y listaremos cada plugin.
Enviar marketplaceTwelve NSDI-specific skills covering the spring/fall submission calendar, track choice, evaluation design with real traces and testbeds, one-shot revise-and-resubmit, artifact badges, and camera-ready duties, grounded in the NSDI '27 and NSDI '26 official pages checked on 2026-07-08.
academicOffline security scanner for AI-agent repos, skills, plugins, and MCP servers. 29 scanners detect prompt injection, MCP tool poisoning, credential exposure, malicious lifecycle hooks, package IOCs, CVEs, CISA KEV exposure, and post-incident traces. Zero dependencies. Zero telemetry.
Error discovery for AI products: read real traces, name failure modes and success modes by stage, and turn the ones that matter into code checks and AI judges you can trust. Includes Eval Studio and a zero-dependency command-line tool.
Bug reproduction and triage: well-formed bug reports, minimal failing tests built from issue reports, and CI failure classification before a fix starts. Also classifies production escapes by root gap. Agents (bug-report-from-recording, bug-repro-builder, defect-pipeline-runner) turn Playwright traces and HAR files into bug reports, build the repro test, and run the weekly defect review that clusters the backlog and narrates trends.
operations-resilienceDesign, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when defining agent evals, datasets, graders, trajectory review, monitor independence, oversight quality, regression analysis, release gates, production traces, or privacy-aware telemetry. Covers task and trajectory contracts, statistical comparisons, and incident-to-case learning; route framework implementation to pydanticai or langgraph when needed. Do not use this skill for unrelated requests; route to the nearest named specialist.
Tenant isolation testing for B2B SaaS: cross-tenant leak tests with a CI gate, row-level security, and tenant onboarding and offboarding tests. Includes silo / pool / bridge isolation models and a Postgres-first RLS reference. A review agent (tenant-leak-critic) traces tenant-id propagation through a diff to find leak risks.
security-complianceCreate a 3D spinning coin from any logo image. Removes white, black or any flat-colour background, traces the exact outline for a chrome rim, adds environment reflections. Works with any PNG/JPG logo.
designFor Grafana Cloud: a hosted MCP server with OAuth sign-in for dashboards, metrics, logs, traces, alerts, and incidents. Nothing to install.
backendRecords which repository and branch each coding-agent session worked in, and teaches the agent to read its own traces back from LangWatch.
backendWork with your OneUptime project from your coding agent: investigate and respond to incidents and alerts, check monitors and status pages, and query logs, metrics and traces.
backendRespan for ChatGPT and Codex: inspect LLM logs and traces, and manage prompts, datasets, evaluators, experiments and monitors in your Respan workspace.
backendServe vLLM presets on demand - locally, Kubernetes (KServe), Azure (Container Apps), AWS (ECS) or GCP (Cloud Run) - with their traces over OTLP, and tear them down again.
instrumentationConstruct telemetrygen commands for generating synthetic OpenTelemetry traces, metrics, and logs via OTLP; load-test collectors and validate pipelines.
Concurrency, retries and crashes can break invariants that ordinary tests miss. Check small finite-state models, retain counterexamples and bounds, and connect useful traces to implementation tests without claiming a whole-program proof.
