Claude Code plugins

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.

Generate NotebookLM artifacts (slides, audio, video, mind maps, quizzes, flashcards, infographics, reports, data tables) from your notebooks. Use when the user wants to create any NotebookLM Studio output from their uploaded sources.

1 skill

proyecto26/notebooklm-ai-plugin 66

10 composable reasoning moves: antithesize, excavate, dimensionalize, handlize, inductify, metaphorize, negspace, rhetoricize, rhyme, synthesize

1 skill

jordanrubin/FUTURE_TOKENS 66

opencad

claudecodex

Generate validated STEP and STL models from text.

1 skill

caid-technologies/OpenCAD 66

18 CIA/IC analytic techniques with OSINT evidence gathering, three-layer self-correction, and mandatory citation enforcement. Run /structured-analysis:analyze to start.

1 skill

Blevene/structured-analysis-skill 66

Search academic papers via OpenAlex — find papers by keyword, look up details by DOI, with pagination and sorting

1 skill

ykdojo/paper-search 66

Best practices for monitoring and controlling an Unraid server through the Unraid Management Agent's MCP tools, diagnostic prompts, and REST API

1 skill

ruaan-deysel/unraid-management-agent 66

opencad

claudecodex

Generate validated STEP and STL models from text.

1 skill

caid-technologies/Open-CAD 66

ohi

claudecodex

ohi + LinkML: ontology discovery, file acquisition, project selections and schema authoring.

NeverBlink-OSS/ohi 66

donewhen

claude

DoneWhen tracker helpers: /dw opens a menu to browse tickets and start work on one.

johnreginald/donewhen 66

kai

claude

A marketing team in Cowork or your terminal: 49 /kai skills, 3 marketing subagents, a full knowledge base, and quality gates that block slop before it ships. Type /kai:kai-start after install, or /kai:kai-goal to run an objective to completion.

63 skills · 3 agents

cgallic/kai-cmo-harness 65

kai-v2

claude

Kai for current frontier models: the same 49 skills stated as objectives, completion floors, and constraints instead of phase lists. Same knowledge base and gates as `kai`. Install this on Opus 5 / Sonnet 5 class models; install `kai` for smaller or older ones.

63 skills · 3 agents

cgallic/kai-cmo-harness 65

Connect Norman Finance to your AI for European bookkeeping, invoices and tax workflows. Polish tools include JDG KPiR, sp. z o.o. ledgers, JPK registers, estimates and existing filing status; they do not sign or submit Polish returns.

28 skills · 1 MCP server

norman-finance/norman-mcp-server 65

swcc

claude

Democratic centralism multi-agent orchestration for Claude Code. 10 agents, 7 skills for full-pipeline task-to-code delivery (民主集中制多智能体编排)

7 skills · 10 agents

ylxmf2005/swcc 65

11 skills covering J-Pop style composition, harmony, modulation, arrangement, mixing and jazz ad-lib

11 skills

jtydhr88/japanese-composition-skills 65

Ten installable research skills, each usable on its own.

10 skills

gxCaesar/open-research-skills 65

Build dlt pipelines for REST APIs: find a source, scaffold the pipeline, add endpoints and incremental loading, debug it, validate the data and view it in a report. Requires dlt[hub].

8 skills · 1 MCP server

dlt-hub/dlthub-ai-harness 65

Load tables from any SQLAlchemy-supported database into a destination with dlt, and tune performance with the available backends. Requires dlt[hub].

8 skills · 1 MCP server

dlt-hub/dlthub-ai-harness 65

threads-skills

claudecodex

Bundle of 8 Threads (Meta) marketing skills for Claude Code and Codex with Threads-native hook formulas, single-post and multi-post thread writing, a unified humanizer (rewrite plus `--mode audit` pre-publish check), viral hook extraction, reply and quote drafting, and a weekly content planner. Posts and threads ship via Publora, which auto-splits long content into a connected multi-post thread.

9 skills

sergebulaev/threads-skills 65

Turn raw dlt pipeline data into a Canonical Data Model: annotate sources, build an ontology, design a Kimball-style model and write @dlt.hub.transformation functions. Requires dlt[hub].

6 skills · 1 MCP server

dlt-hub/dlthub-ai-harness 65

Blender 3D automation via MCP

6 skills · hooks

sandraschi/blender-mcp 65

Convert Playwright traces into polished demo videos with TTS voiceover, subtitles, speed control — fluent pipeline API and CLI

3 skills · 1 MCP server · hooks

ThePatriczek/playwright-recast 65

zoteus

claude

Your Zotero library inside Claude: search by keyword or meaning, quote PDF passages with page numbers, format citations in any CSL style, add papers by DOI or arXiv id, and organize with reversible writes.

4 skills · 1 MCP server

oscardvs/zoteus 65

Simulate feedback from census-grounded virtual populations. Panel-score product/copy, predict votes with IPF post-stratification, or run what-if social-sandbox experiments. Ships with 4 skills (core + product-feedback / vote-predict / social-sandbox), a bias audit module, and 6 eval suites (GSS, BFI, test-retest, diversity, demo-correlation, bias-audit).

4 skills

Yrzhe/claude-skills 65

Agent Script workflows end to end: the ultracodex runner skill (execute multi-agent workflows on the OpenAI Codex CLI), the model-agnostic agent-script-authoring skill, and a seven-shape example gallery.

3 skills

YuanpingSong/ultracodex 65

Check how well your repo supports AI coding agents.

2 commands · hooks

0xmariowu/AgentLint 65

gala

claude

GALA code intelligence for Claude Code via `gala lsp`: diagnostics after every edit, hover types, go-to-definition and references. Requires the GALA CLI (`gala`) installed and on PATH; the plugin does not include it.

2 skills · LSP

martianoff/gala 65

jev-rules

claude

Jev picks which of your rules apply to each prompt, so Claude only sees the ones that matter.

1 command · hooks

EliaAlberti/jev-rules 65

claudemon

claude

Wild Pokemon appear while you work. Your prompts are steps through the grass.

1 command · hooks

zamarrowski/claudemon 65

Measures what share of your agent's loaded context is ever actually invoked - skills, MCP servers, subagents, hooks, always-loaded prose - using evidence from your own session transcripts. Then prunes the dead weight, reversibly.

2 skills

thousandflowers/skillreaper 65

Publishes Claude Code session context from a remote host to localvoxtral on your Mac over an SSH RemoteForward tunnel. Install this on the REMOTE host, not the Mac. Command hooks running a bundled POSIX-sh shim that POSTs via curl — no localvoxtral binary, needs only sh and curl. Fail-open: does nothing without a tunnel, a token, or curl.

1 skill · hooks

T0mSIlver/localvoxtral 65