Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
FigGenie-Skill · 无痛画顶会风格论文图 — Painless top-venue-style paper figures: describe your system or method, get a camera-ready architecture, mechanism or Figure 1 / overview diagram (SVG · PDF · editable PPTX). Learned from OSDI/NSDI/SOSP/ASPLOS and ICLR/ICML/NeurIPS/CVPR/ACL/AAAI figures.
Railway agent skills and hosted MCP server for deploying, configuring, monitoring, and troubleshooting apps and infrastructure on Railway from Claude Code. Manage services, environments, deployments, databases, object storage, networking, and observability.
Go-to-market Agent Skills for developer tools and AI products, the GTM co-founder you don't have. For founders, early GTM hires, and founding AEs. Market research, positioning, ICP, homepage, launch, pricing, distribution. Grounded in Adam Frankl and Jakub Czakon.
Teaches coding agents to drive the swift-section CLI: Swift and Objective-C declarations, memory layout and ABI diffs recovered from a Mach-O binary or a dyld shared cache.
Skills for working with local Beancount ledgers through a coding agent: init, add, trade, property, import, importer-author, reconcile, migrate, ask, roll-forward, accruals, invoices, report-pack, business-metrics, close, options. Needs `bea` 0.3.1 or later for checks, queries, and writes.
Agent Skills for automating, inspecting, and testing Tauri v2 applications directly from the terminal. Includes skills for driver-session management, webview inspection, and UI interactions.
Ask a running Spring Boot or Quarkus application about itself: architecture, Spring, Hibernate, memory, security, pentest, GraalVM and CRaC advisors plus live runtime diagnostics, over BootUI's local MCP server.
Two-loop skill pipeline for Claude Code. Inner loop (plan-interview, intent-framed-agent, session-context, context-surfing, verify-gate, self-healing, simplify-and-harden) catches failures in-session — including active runtime recovery via self-healing when a command, test, build, helper, env, or external service fails mid-task. Outer loop (learning-aggregator, self-improvement, eval-creator, pre-flight-check) captures recurring patterns, promotes them to CLAUDE.md as permanent rules with human approval, and turns failures into regression tests. The harness gets stronger with every cycle.