Research & Data

Codex skill for HetrixTools API v3 uptime, heartbeat, cron, and backup monitoring

Self-improving measurement layer for Claude Code. Reads JSONL session data, computes effectiveness metrics, writes behavioral rules into CLAUDE.md. Companion to claude-daily-journal and claude-insights.

🪞 Systematic self-reflection for AI agents. GENERATE → CRITIQUE → REFINE → CHECK. Based on peer-reviewed research. Zero API cost. Works with Claude Code, Cursor, Copilot, Codex CLI, and 10+ more platforms.

Agent skills for setting up and operating Estuary data pipelines through your AI assistant.

An implementation of the paper: "Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces" with Swarms Primitives

Machine Learning Engineer (MLE): get your model trained with just a sentence.

Claude Code skill that derives infrastructure architectures from workload analysis using first-principles math (Little's Law, Erlang-C, USL, availability calculus). 7-dimension constraint framework with swappable cloud/regulatory catalog.

Access your human's personal context data (biometrics, sleep, activity, calendar, location) via the Fulcra.ai Life API and MCP server. Requires human's Fulcra.ai account + OAuth2 consent.

Naftiko capability specs across the APIs.io network — runnable as REST, MCP, and Agent Skills. https://capabilities.apis.io

Claude Code efficiency and hygiene toolkit — token spend analysis across the 5h / 7d / Sonnet-7d billing windows plus configuration overlap auditing. Ships as a Claude Code plugin with three skills (usage-analysis, usage-dashboard, claude-audit) backed by a Python CLI.

Multi-agent skill for Claude Code that delegates tasks to Google Antigravity CLI — web search, image gen, codebase analysis, 40+ science databases

Chainsaw - GraphRAG CLI & Daemon for local-first knowledge graph search

Homebrew taps for AI agent skills. Agent-agnostic. Install from any git host or npm registry, search across taps and searchable registries like skill.sh, find, static and semantic security scanning before anything touches disk.

Host-agnostic, industry-agnostic catalog of harnesses, knowledge objects, logic & rule packs, tools, pipelines, processors, personas, model adapters, rubrics, datasets, and benchmarks for AI-assisted systems. Emits to Croissant, MCP, Agent Skills, HF cards, CycloneDX-ML, OpenLineage, and more.

A Claude Code skill that produces presentations worth sending — research-first, narrative-driven 5-phase workflow inspired by Genspark AI Slides.

A universal senior data scientist skill for data mining, model building, validation, interpretation, responsible AI, and production-readiness across Python, R, SQL, Excel, notebooks, and agent workflows.

Research-grounded Agent Skills for coding agents: DX review, test strategy, and agent-readiness heuristics. Install via npx skills add Thulr/informed-skills.

Claude Code plugin: end-to-end used car buying — multi-site research, mass dealer outreach, OTD negotiation with 50-state fee data, CARFAX analysis, decision tracking

Manage and automate research tasks using a persistent LangGraph agent with PostgreSQL state and a Telegram interface for instant access.

Provide scripts to monitor and maintain OpenClaw services, ensuring stability through health checks, automatic restarts, and log cleanup.

Track Binance prices in real time with a fast Rust sniper and monitor for precise market alerts

From a sample document to a running Milvus / Zilliz Cloud search app in minutes — an AI-guided scaffold delivered as a Agent skill.

Analyze DeFi on-chain data with raw JSON-RPC calls for verifiable insights, contract discovery, and looped AI-driven analysis

Build AI trading agents for market research, strategy tests, and decision support with a clear multi-agent framework