deep-research

Research-driven course generator for Claude Code. Reads real articles. Writes real courses.

Persistent project-scoped knowledge base for Claude Code and Codex: quick and deep research depths, contrarian pass, source-independence rules measured on DeepResearch Bench II. Tested end to end on Haiku agents and a local 35B under noob-cli. Installs via npx skills add, /plugin install, codex marketplace, or git clone.

Turn research questions into reports with source links and open questions: Research for Codex and Claude Code, plus multi-model dispatch tooling for Claude Code.

The ultimate MiniMax 2.7 Highspeed Claude Code harness - 100 TPS, 204K context, GStack skills, 5-tier memory, 10x productivity.

使用 Claude Code / Codex 操作 ChatGPT 的 Skill｜Skill for controlling ChatGPT with Claude Code / Codex

The Synapti Marketplace is a curated collection of Claude Code plugins designed for AI-augmented development + advanced analytical and research tasks. Each plugin provides specialized agents, skills, and commands that extend Claude Code's capabilities in specific domains.

Autonomous multi-session research agent for Claude Code. Decomposes research into 100+ tasks, spawns subagents, verifies every output, and self-improves over time. Run overnight, come back to structured findings.

Claude Code research ladder: 6 composable skills (L0→L5) from 10s fact-check to 1h knowledge vault, plus /osint-research for entity recon. Stack: Firecrawl (search+scrape+summary) + Tavily (search + research with structured schema verdicts) + Exa (neural) + optional Codex CLI cross-model. MIT.

Self-hosted deep research engine for Claude Code. Open a GitHub Issue → cited research published to your Jekyll site via GitHub Pages.

🧠 AI Thinking Coach for Claude Code — Stop letting AI think for you. Research from X/Perplexity/RSS, Socratic guided thinking, belief tracking.

OpenClaw deep research workflow with prompt optimization, RAGFlow/MinerU, scientific visuals, progress reporting, and release gates.

Local, private, uncensored AI research workstation for Linux: a self-hosted LLM with an autonomous deep-research agent, anonymous web search, encrypted DNS, and Tor egress - fully ephemeral, no telemetry, no cloud.

Consult the frontier models you pay for, no API keys. Agent skill: compose once, paste around, collect, verify, synthesize.

DeepSeek Harness agent in a locked-down Apple container: default-deny egress via pf, self-hosted web research, loop guard

Claude Code plugins for deep GTM research, competitive analysis, and more — by Raine Soriano

Safety and deep-research enhancements for Hermes Agent — human approval gates, evidence-aware /deep workflows, and controlled subagent delegation.

Autonomous multi-step deep research engine plugin for Google Antigravity (AGY). Recursive query decomposition, iterative web search, cross-source fact verification, and publication-grade report synthesis.

Codex and Claude skill for Stanford STORM deep research and cited report generation

Portable Claude × NotebookLM deep-research skill · 4-stage workflow + anti-hallucination guardrails · installs to Claude Code, Codex CLI, Anthropic Agents SDK, Hermes

Multi-cycle deep research using a locally-hosted Local Deep Research (LDR) service for OpenClaw / ClawHub