Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,381 indexed, measured the same four ways as everything else here.
One shared, durable memory for your AI coding agents — local-first, zero-dependency. Decisions, lessons and status persist across sessions, tools and projects.
★not rated 21 26d agoA
tokens not measured
AGPL-3.0
Developer tooling setup and management (SOPS secrets encryption, Claude Code environment setup, multi-ecosystem quality stack for JVM/Node.js/Python, Taskfile task runner setup and audit, Tilt local Kubernetes development setup and audit, browser-companion live-preview server for agent↔browser workflows via the…
★not rated 21 1mo agoA
tokens not measured
originalMIT
Autonomous AI research harness for Claude Code. Plan -> Research -> Build -> Audit -> Run -> Assess -> Codify, with adversarial subagent review, a taste corpus, a [LEARN] memory system over SQLite/FTS5, and a spot-first GPU procurement router.
★not rated 21 13d agoA
tokens not measured
originalApache-2.0
MCP server that indexes a codebase's public API at startup and serves it via compact tool responses. Pluggable parsers for C#, Go, Java, TypeScript, Python, C++, and more. Runs locally from the codesurface Python package.
★not rated 21 2mo agoA
tokens not measured
originalMIT
Use when the user wants to find NEW external skills for a project, build a skill stack from external registries, or compare external options against project needs. Do not use for questions about how to use already-installed/local skills.
Iterative OpenAPI improvement subagent. Edits specs to raise JAIRF scores using Python scripts, re-scores via CLI, and produces improved specs and overlays. Spawned by the jentic-api-improve skill — do not invoke directly.
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress or "compress memory…
Use this skill whenever the user mentions a "brief" (e.g. "turn brief mpogywhs-ft15hr into a ticket", "process my inbox: briefs X, Y, Z"). Briefs are captured with the Brief Chrome extension and stored locally on disk. A brief may contain a screen+voice recording, an annotated screenshot, a text description, or any…
MCP server for PixelPanda — AI image processing tools for Claude Desktop, Cursor, and other MCP clients. Runs locally from the pixelpanda-mcp Python package. Needs 1 environment variable to run.
Ultimate MCP server for Civitai — search models, browse top images with prompts, download LoRAs/Checkpoints, analyze trends. Use when user asks about AI models, LoRAs, checkpoints, Stable Diffusion, Flux, image generation prompts, or Civitai.
Drive a real Chromium browser through the tidesurf CLI or MCP tools. Use when a task needs live web browsing: reading pages as compact, token-efficient text with action IDs; clicking, typing, selecting, and scrolling elements by ID; taking screenshots of the full page, viewport, or one element; managing tabs; handling…
Expert developer context for the PotBot v2 project — group trading vaults on Solana (Solana Frontier 2026). ALWAYS use when the user mentions potbot, pot vault, anchor program, devnet/mainnet deploy, the hackathon, strategy vaults, governance, leaderboard, AI agent, personal voters, MCP server, money tree /…
Runs SEO and AEO (Answer Engine Optimization) analysis on websites or specific pages. Use when the user mentions SEO, AEO, search rankings, search optimization, or wants to analyze how their pages perform in search engines and AI answers. Produces a data dashboard and action report with before/after recommendations.
Install or update the binlog-insights MCP server tool. Use when binlog-insights-mcp is not found, tool installation fails due to NuGet configuration, or the tool needs updating. Also triggers for dotnet tool install errors, NuGet source problems, and MCP server not starting.
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: