Skills for Microsoft Agent 365 — transform agents into AI Teammates, register blueprints, add WorkIQ MCP servers, instrument observability, integrate Purview DLP, and test locally. Supports .NET (AgentFramework, Semantic Kernel) and Node.js (LangChain, OpenAI Agents SDK, Claude SDK, Semantic Kernel, Google ADK) and…
Open-source MCP server: 500+ tools AI agents call and pay for per request, in USDC over x402 or MPP, by card, or free via proof-of-work for pure-compute tools. Web search and rendering, PDFs, OCR, SEC filings, market and crypto data, and utilities. Most tools are deterministic code; model-backed tools are marked as…
★not rated 51▲
+2
changed yesterdayA
tokens not measured
AGPL-3.0
Publish websites, apps, and files to live URLs at {slug}.here.now or custom domains. Publish HTML apps, documents, images, PDFs, videos, and static files, with access control, custom domains, analytics, and private Drive storage for agent files.
A Cowork plugin for saving distilled skills to Claude.ai and helping them persist across cloud-container sessions. A cloud container is a temporary remote environment, so the plugin also guides synchronization when a new session starts.
★not rated 51 1mo agoA
tokens not measured
originalMIT
Two skills that eliminate the two biggest sources of token waste: think-twice (pick the cheaper approach before starting) and surgical (build only what was asked, nothing more). The best tokens are the ones you didn't spend.
★not rated 50
changed 1mo agoA
tokens not measured
originalMIT
A project-analysis tool that reads a codebase and creates a CLAUDE.md file with project rules. It also supports monorepos, which are repositories containing multiple related projects.
★not rated 50 11mo agoA
tokens not measured
originalMIT
LLM-powered personal wiki — autonomous knowledge base with research-on-miss, ingestion, search, a browsable web UI, and universal data gravity. Saves and retrieves knowledge automatically whenever relevant.
★not rated 50 6mo agoA
tokens not measured
originalMIT
A plugin for coordinating several Codex agents on one complex task, including parallel work and review of the results. An agent is a separate AI worker given a specific part of a task.
★not rated 50 1y agoA
tokens not measured
originalMIT
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.
A guardrail that flags code foreign to a repo's own patterns — learned from git history. Bundles the argot-setup, argot-refresh, argot-check, argot-review-pr, argot-setup-ci, argot-write-rule, and argot-suggest-rules skills, the argot MCP server, and an opt-in, non-blocking pre-write guardrail hook.
98% fewer context tokens for your coding agent to find code — a queryable, PageRank-ranked ts-morph import/symbol map for TS/JS repos. Bundles the PreToolUse grep nudge, the navigation skill, and a stdio MCP server exposing 11 query tools including a compiler-accurate call graph, BM25 lexical search, plus CLI-only Mer.
★not rated 50 22d agoA
tokens not measured
originalMIT
Convert any HTML/CSS/JavaScript project into a production-ready WordPress Block Theme (Full Site Editing): theme.json v3, block patterns, FSE templates, the Interactivity API, and optional WooCommerce support. Bundles 11 slash commands, a quality-review agent, deterministic validation scripts, and a full reference…