Bundled design + quickstart skills, code-writing and code-review subagents, lint guard + end-of-turn verify hooks, runtime-error and OCC-insights monitors, and MCP server for live deployment introspection. The quickstart scaffolds a running app from one sentence and builds it live LOCALLY, narrated in chat; the convex.
Official Carbone skill — complete templating language reference covering tags, loops, conditions, formatters, aggregators, PDF form filling (AcroForm), format support and conversion, and all template formats (DOCX, XLSX, PPTX, ODT, HTML, Markdown, PDF, CSV, TXT, SVG, IDML).
★not rated 6 29d agoA
tokens not measured
originalApache-2.0
Official JFrog plugin. Connect Claude Code to JFrog to manage, secure, and govern your software supply chain. Give agents the context to build secure, compliant software.
★not rated 6
changed yesterdayA
tokens not measured
originalApache-2.0
Configurable Claude Code plugin for professional development workflows. Bundles skills, agents, hooks, and automation into a single installable plugin.
Persistent project knowledge base for Claude Code. Records current state, phased roadmap, decisions and their rejected alternatives, and failed approaches — so a new session resumes from what was recorded instead of re-reading the whole codebase.
★not rated 6 1mo agoA
tokens not measured
originalMIT
Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.
★not rated 6
changed todayA
tokens not measured
originalMIT
Persistent memory for AI assistants — runs locally on your machine. Remember every decision, debugging session, and architecture debate across sessions. One MCP server, zero cloud dependencies, works on a Raspberry Pi.
Chat with your affiliate-network data in Claude through a local MCP server. 80+ publisher and advertiser-side adapters across the US, EU, Nordics, APAC and LatAm, most experimental.
★not rated 6 1mo agoA
tokens not measured
originalMIT
Audit any website across SEO, answer-engine and generative-engine criteria, and generate llms.txt, llms-full.txt and facts.json so AI engines can ingest it as ground truth.
★not rated 6 18d agoA
tokens not measured
originalMIT
AI agent for full-cycle project management: document generation, monitoring, coordination, and scheduled reporting based on PMBoK 8 + Agile hybrid methodology. Covers all 32 PM tasks across 6 project phases — from initiation to closure.
★not rated 6 5mo agoA
tokens not measured
originalMIT
14 battle-tested Claude Code skills for planning, research, code review, UI/UX, databases, copywriting, design, video, and more — curated by the GoClaw / AgentBrain team.
★not rated 6 4mo agoA
tokens not measured
originalMIT
Compiler-exact code search for .NET, for Claude Code and Codex - find references, callers and change impact across C#, VB, Razor Pages, MVC views and Blazor components. Built on Roslyn, so answers come from the compiler rather than pattern matching, and Razor and Blazor are indexed rather than skipped. Deterministic…
★not rated 6 todayA
tokens not measured
originalMIT