Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 379,881 indexed, measured the same four ways as everything else here.
Milestone-triggered, in-session work diary for Claude Code. The model records meaningful milestones to plain-markdown log + status files as it works, across all projects. No database.
★not rated 6 3mo agoA
tokens not measured
originalMIT
Persistent memory for AI agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Hybrid search (BM25 + vector + graph) recalls what matters when you need it.
Use all the skills you've installed — not just the ones you remember. Each turn it surfaces the installed skills most relevant to your task, so a fitting one is in front of you instead of forgotten. Also offers high-leverage commands when they fit; handles the basics silently. Open source, zero telemetry, local-first.
★not rated 6 3mo agoA
tokens not measured
originalMIT
Create project.md (PRD), brand.md (brand guidelines), and CLAUDE.md (technical config) for any project. Interactive workflow with audit, archetype-based branding, and stack-specific optimization. Supports Laravel, Flutter, Vue2/3, Nuxt2/3, TailwindCSS, Alpine.js, and more.
★not rated 6 8mo agoA
tokens not measured
originalMIT
A learning add-on that turns AI-made code changes into guided, explainable understanding. It uses a question-and-answer process so developers can restate the reasoning and apply it elsewhere.
★not rated 6
changed 1mo agoA
tokens not measured
originalMIT
Autonomous dev agent — works through your task list while you sleep. Zero config after install. Builds, reviews, deploys, and verifies each task end-to-end.
★not rated 6 4mo agoA
tokens not measured
originalMIT
Two slash-command skills that diagnose and clean up your machine (macOS and Windows) and your Claude Code working directory. Reversible, permission-gated, no telemetry.
★not rated 6 4mo agoA
tokens not measured
originalMIT
Pattern taxonomy, agent role combinations, model routing, unit-of-work sizing, review-findings settling, and resilience discipline for Claude Code dynamic workflows. ALWAYS load this skill before authoring or running any Workflow tool script, and ALWAYS load it when the user mentions "workflow" or "ultracode" in any…
Use when answering Taiwan Legislative Yuan data requests with the ly CLI, including bills, laws, meetings, votes, legislators, committees, gazettes, interpellations, IVOD recordings, amendment history, proposal records, and meeting agendas. Trigger when a user asks for Legislative Yuan information that maps to ly…
Send email, look up public IP information, and convert files to Markdown through SendSoon. Runs locally from the @sendsoon/mcp npm package. Needs 1 environment variable to run.
★not rated 6 2d agoA
tokens not measured
originalMIT
Research any venture capital firm and produce a concise fundraising-focused briefing. Use when the user asks to look up, research, analyze, or get information about a VC firm, venture fund, or investor. Triggers on "tell me about {VC}", "research {fund}", "vc info {name}", "who is {VC}", "analyze {investor}", "{VC}…
Privacy-first unofficial Polar AccessLink v4 MCP server for AI health, sleep and training agents. Runs locally from the polar-mcp-unofficial npm package. Needs 8 environment variables to run.
★not rated 6 5d agoA
tokens not measured
originalMIT
MCP server for querying Codecov coverage data with configurable URL support. Runs locally from the mcp-server-codecov npm package. Needs 2 environment variables to run.
★not rated 6 7mo agoA
tokens not measured
originalMIT
Selenium Tools for MCP. Runs locally from the selenium-webdriver-mcp npm package. Needs 1 environment variable to run.
★not rated 6 1y 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: