Find plugins

by Ilan Bar Magen

Make your agents' reasoning explicit, persistent, and deterministically checkable. Connect decisions to evidence and assumptions, and see what needs another look when a recorded premise changes.

by Jordan Martinetti

Terse responses that stay readable. Cuts claim count, not grammar: no preamble, no unrequested options, no recaps — with complete sentences at every level.

by Cordova Strategy

Linear issue-comment and issue-link formatting conventions for tracker writes. Not the Linear MCP server registration — see linear@claude-plugins-official for that. This plugin carries only the linear-formatting skill. Install at project scope in any repo whose tracker MCP server is Linear.

by Patrice Huetz

Keep noisy command output (tests, builds, package managers, diffs, logs) out of the context window. Ships the lm-resizer skill and the lm-resizer MCP server (compress, tool_output, retrieve, stats). Requires the lm-resizer binary on PATH.

by Labyrinth Analytics Consulting

Searchable, organized, version-tracked knowledge base for your AI projects. Store documents, tag them, search across them, and inject context into any Claude conversation.

by Cordova Strategy

Skills and hooks for Lovable Cloud projects — Project/Workspace Knowledge fields, edge-function auth model, migration-sync workflow, and UTC-enforced migration filename generation.

by Lusha

Find and enrich B2B contacts and companies with verified emails, direct dials, mobile numbers, and real-time buying signals from Lusha.

by Matt Pocock

Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.

by baleen37

Unified development workflow - design, planning, TDD, debugging, git protection, verification, review, and shipping

by AIGC Skills Community

MiniMax AIGC skills — text, image, video, speech, music generation

by Emanuele Minotto

Use whenever the user asks about QA, testing strategy, CI/CD health, team processes, developer experience, code review practices, test coverage, flaky tests, monitoring, or any audit of an engineering team's quality practices.

by Felipe Sauer

Puts the project's committed mnema record into the session's opening context without the agent asking, with the latest notes recorded for it on this machine beside it, and connects the mnema MCP server so it can record its own work.

by CANNBot

NPU 模型推理端到端优化 Team。涵盖从零适配到 baseline 的固定阶段优化（并行、KVCache/FA、融合算子、量化、图模式），以及 baseline 之上 profiling 驱动的探索式优化（多方向发现候选、Plan/round 自循环，按需调用多流、预取、SuperKernel 等单点优化）。含两条 workflow 与 9 个 Subagent。

by BTCH Uro AI Lab

Medical research methodology framework — 20 skills with selective constraints covering the full research pipeline. Supports clinical, basic science, AI/ML, qualitative, and survey research design. 240 journal templates, 47 reporting standards (CONSORT 2025, STROBE, PRISMA, TRIPOD+AI, DECIDE-AI, IDEAL), 7 commands, PubMed MCP integration, one-click .docx export.

by lazygophers

Claude Code Hooks 通知插件 - 通过系统通知和 TTS 语音实时提示会话状态变更、权限请求等重要事件

by lazygophers

小说写作全流程插件 - 从爆款题材选择/世界观/人物/大纲设定到章节编写、一致性检查、校对、去AIGC、重写的端到端工作流。中文目录结构(人物/世界观/章节/大纲/情节/设定)细粒度拆分, 编写前四要素确认, 生成后收尾链(检查→校对→去AIGC→定稿), 支持从指定章节起重写与连续多章重写; craft 三流派叙事镜片 + trending 选题方法论 + humanize 去AI味。

by Cordova Strategy

Semver and version-field discipline for published npm packages. Install at project scope in any repo that publishes an npm package.

by Seraphim0916

One routing table, every harness: classify subtasks into lanes and delegate through compatible caller-owned native agents or vendor CLIs with exact-AA downward policy and supervised jobs.

by OmniNode

Unified ONEX architecture plugin with intelligent agent routing, manifest injection, quality enforcement, 53 polymorphic YAML agents, and 100+ reusable skills (invoked as /onex:<skill-name>) for comprehensive workflow automation and observability

by OmniNode

ONEX customer delegation: ships exactly one local delegation skill, delegate — no hooks, no agents.

by CANNBot

Ascend C 算子代码审查 Team。含独立审查 Agent，支持 PR diff 审查和代码质量评估。

by CANNBot

skill 驱动的多角色直调算子开发工作流 Team。PM 调度 architect / developer(-code/-test/-doc) / qa 六角色，8 阶段 7 CP 全流程（需求→设计→开发→验收→上库），支持静默模式、可插拔流程插件与算子仓继承定制。

by CANNBot

当需要从 CPU 函数、数学公式、代码片段或文本描述出发构建全新的 Ascend C 或 Ascend950 Reg API 核函数时使用。覆盖从规格定义到验证通过的 NPU 核函数的完整路径。

by CANNBot

Ascend C 算子性能进化优化 Agent Team。对已有 AscendC 内核或 ops 仓库算子进行多轮并行进化优化，包含 1 个 Orchestrator Agent 和 4 个路径专用 Subagent。