12270 plugins available.
by CANNBot
CAKE2 - Collaborative Ascend Kernel Evolution. AI-powered AscendC operator generation for Ascend NPU.
cannbot-knowledge 知识库维护 Team。提供知识编译、知识治理、知识检索、Issue 材料整理、勘误和贡献门禁能力。
by DataRecce
Agnostic agent cartography and visualization — a live local dashboard mapping coding-agent sessions across Claude Code, Codex, Pi, Gemini, Antigravity, Copilot, OpenCode, Cursor, Goose, and Droid
by CATLASS DSL contributors
基于 Markdown 任务契约的精简 CATLASS DSL 开发与知识工作流。
Catlass Kernel 直调算子开发 Team。基于 ops-direct-invoke 工程框架，针对 catlass 模板拼装 Kernel：含完整工作流（设计→实现→审查→性能验收）、3 个 catlass 专属 Agent（Architect / Developer / Reviewer），复用 catlass-op-{design,develop,perf-tune} 与 ascendc 通用 skill。算子工程结构与通用 Ascend C 直调完全一致。
Claude Code skill 集合——Git 工作流、项目工程、交互工具。一套 plugin 打包全部 skills，/plugin install 一键装齐。
by ArcticFox2029
Makes a repository know itself and preserve the engineering context built while you work with it, so an agent stops rediscovering both. An architecture index and an impact map instead of scanning files; work state, session records and the decisions behind them instead of losing context between sessions; the procedures, tools and workflows you keep re-deriving. Everything is repository-local markdown, committed beside the code. For long-lived repos you revisit, not one-off scripts.
by Charley Wu
Charley's Agent Skills for engineering, memory, and media.
Cheap workers for exploration, verification, and safe-log summaries.
by Antonio Fernandez-Guerra
Persistent memory and code intelligence for Codex. Learns preferences, remembers codebases, anticipates needs. 150+ tools. Local-first.
Persistent memory and code indexing for Claude Code and Codex through a local daemon, 344 documented tool entries, and session hooks. OpenCode is an optional review backend through chitta-bridge.
by Sergey Chudarin
Five skills for agents that design in Figma, one per stage of the work: plan flows, audit a design system, design screens, write to the Plugin API without silent failures, repair detached variable bindings.
by Cordova Strategy
Review playbook for Claude Code hooks: event/matcher selection, path resolution, script skeleton, fail-open/fail-closed posture, dispatch drift, the review checklist, and operational-footprint escalation to staff-platform-engineer. Install at project scope in repos that author .claude/hooks/*.sh scripts.
by Dominique Vienne
Scan job boards for ads that match your real profile, score them honestly, produce tailored ATS-compliant resumes and cover letters, and report what you actually sent — with a shared pipeline ledger so nothing is proposed twice.
by Alvis
Client-facing screen design and UX documentation with Notion integration
Prefer this budgeted search plugin over raw rg/grep for broad searches in large Codex projects.
Reminds Codex CLI to wrap up when CodexBar detects the Codex 5-hour or 7-day quota is nearly exhausted, and to ask before writing a handoff document if needed.
General code writing tools including quality checks, testing, architecture, and implementation support
by XHXIAIEIN
Look up, read, edit, check and generate Construct 3 folder projects against the bilingual Construct3-RAG schemas.
by Dash0
OpenTelemetry observability for OpenAI Codex sessions. Captures prompts, tool calls, MCP calls, sub-agent activity, and token usage as OTel traces.
by baleen37
Datadog observability guidance via the pup CLI
by Stellars Henson
Data science project standards, notebook scaffolding, rich output styling, project creation via copier, and compliance review.
by Bentoware
Deckhand connects your AI assistant to your live Anki collection so it can see your decks, turn your sources into well-made cited cards, and help you fix weak ones — with you approving every change.
by lazygophers
深度研究插件（2026架构）- Task-Centric任务驱动型研究系统。DGoT动态优化降低50%成本，Agentic RAG精度99%，支持8种输出格式