Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 377,196 indexed, measured the same four ways as everything else here.
Open-source local-first Chromium, Firefox, WebKit, Playwright, and Puppeteer automation for AI agents with semantic page snapshots, model-directed execution, MCP, SDKs, and verifiable evidence. Runs locally from the cockroach-browser npm package. Needs 2 environment variables to run.
★not rated 9▲
+1 10d agoA
tokens not measured
AGPL-3.0
Opinionated guide for building dApps on Arbitrum using Stylus (Rust) and/or Solidity. Covers local devnode setup, contract development, testing, deployment, and React frontend integration with viem. Use when starting a new Arbitrum project, writing Stylus or Solidity contracts, deploying to Arbitrum, or building a…
Build beautiful, self-contained HTML presentations (slide decks) with the bundled Presentation Forge engine: one HTML file per slide, bundled into a single portable index.html with presenter mode, progressive reveal, and swappable themes, plus built-in animations (five motion levels), charts, figures and icons. Use…
Audit how a brand appears in AI-powered search (ChatGPT, Perplexity, Claude, Gemini). Use when user mentions "AI search," "how do I show up in ChatGPT," "AI discoverability," "AEO," "LLM visibility," or wants to understand their brand's AI presence.
Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals…
Read-only session orientation. Full/quick views show Jira, PRs, beads and working-copy state; resume mode gives a compact local resume-or-next recommendation without loading a handoff or claiming work.
Adobe Express environment essentials, two-runtime architecture, project setup, and MCP server configuration. Use when starting add-on development, understanding iframe vs sandbox boundaries, configuring MCP servers, setting up local projects, or validating manifest configuration.
The backend habits an AI assistant misses on its own — API versioning, feature flags, circuit breakers, and four more. Measured across 13 baseline runs; everything the model already does reliably was cut.
★not rated 9 9d agoA
tokens not measured
originalMIT
Opinionated, batteries-included spec for adding an SEO-first, i18n-ready blog to a Next.js + Sanity site. Walks 40 intake questions, scans the project, drafts a one-page plan for approval, then implements against a 20-section technical spec with pass/fail checklist. Includes a working generator for AI hero images via…
★not rated 9 4mo agoA
tokens not measured
originalMIT
AI film production studio with pre-built scripts: analyze inspiration/reference videos (Gemini), write script + storyboard, generate stills (GPT Image 2.5 Sunburst by default; Flare for previs; GPT Image 2 / Seedream 5 / Nano Banana as fallbacks), video (Gemini Omni 1.1 Flash, FLUX 3 Video, Seedance 2.5/2.0, LTX…
Analysis skills for UN FAOSTAT food and agriculture data. Country profiles, commodity briefings, trade analysis, climate assessments, and data visualizations. Works with any AI assistant that supports the SKILL.md format.
★not rated 9 5mo agoA
tokens not measured
originalMIT
Critical thinking platform for decision analysis, proposal review, debate preparation, and due diligence. Three agents (advocate, adversary, judge) over a grounded argument graph, with a live transcript UI, appeal review, and 10 reasoning traditions.
Best practices for creating, editing, and manipulating Word documents (.docx files). Use when creating reports, memos, letters, templates, or any .docx output. Also use when reading, editing, or extracting content from existing Word documents.
Use when driving a uigraph workspace over MCP — building or auditing the UI transition graph, reconciling LLM proposals, or running Tier-3 runtime verification. Load before calling any uigraph tool.
MCP server "go-gerrit-mcp" as configured in GaijinEntertainment/go-gerrit-mcp. Runs in Docker (ghcr.io/gaijinentertainment/go-gerrit-mcp:1.1.3). Needs 11 environment variables to run.
★not rated 9 yesterdayA
tokens not measured
originalMIT
MCP server "rune" as configured in thecolourfoundation/rune. Launched with https://github.com/thecolourfoundation/rune/releases/download/v0.5.1/rune-mcp-li.
★not rated 9
changed 12d agoA
tokens not measured
originalMIT
WordPress MCP server + companion plugin giving AI native access to page builder content, not just the REST API. 248 tools, 352 with WooCommerce, 17 page builders and the Site Editor. Element-level edits, full page creation, HTML to builder conversion, sna. Runs locally from the @respira/wordpress-mcp-server npm…
★not rated 9
changed 7d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: