hoangsonww/AI-RAG-Assistant-Chatbot
Instructions file CodexOpenCode
Instructions for hoangsonww/AI-RAG-Assistant-Chatbot, covering lumina codex guide, repository overview, scope rules, working rules and validation commands.
hoangsonww/AI-RAG-Assistant-Chatbot
Instructions file
Instructions for hoangsonww/AI-RAG-Assistant-Chatbot, covering lumina repository guide, scope, working rules, validation defaults and use project extensions.
MCP server Claude CodeCodexCursor +2
MCP server "docuthinker-orchestrator" as configured in hoangsonww/DocuThinker-AI-App. Runs orchestrator/mcp/server.js with node. Needs 1 environment variable to run.
Instructions file CodexOpenCode
AGENTS.md instructions for hoangsonww/DocuThinker-AI-App, covering docuthinker — agent coordination protocol, project overview, file reservation system, conflict zones (single agent only) and safe parallel zones.
Instructions file
Claude Code instructions for hoangsonww/DocuThinker-AI-App, covering docuthinker — claude code configuration, architecture overview, code standards, testing and build & run.
Plugin Claude Code
Official plugin marketplace for comprehensive research, analytics, and intelligence tools.
Plugin Claude Code
Comprehensive AI news tracking, deep research agents, automated Notion/Teams/Slack publishing, and a 5-axis LLM-as-judge quality eval harness with offline dashboard.
MCP server Claude CodeCodexCursor +2
MCP server "notion" as configured in hoangsonww/AI-News-Briefing. Runs locally from the @modelcontextprotocol/server-notion npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Lets the agent fetch a URL and read its content as markdown. Runs locally from the mcp-server-fetch Python package.
Agent
A specialized agent for conducting exhaustive deep-dives on complex technical and industry topics.
Agent
A specialized agent for editing, fact-checking, and formatting AI news briefings with a critical journalistic eye.
Agent
Editorial reviewer agent that scores AI News Briefing cards on the 5-axis quality rubric (factuality, novelty, source diversity, signal density, coherence). Activate when the user wants a strict, structured assessment of a briefing's quality with concrete per-axis reasoning and actionable fixes.
Hook
Runs after a tool call finishes for mcp__notion__notion-create-pages, Write and Edit tool calls, executing runner.py with --date and --judge (2 commands). From hoangsonww/AI-News-Briefing.
Skill Claude CodeCodex
Deep-research a specific topic and produce a comprehensive news-focused briefing with optional Notion/Obsidian/Teams/Slack publishing.
Skill Claude CodeCodex
Search for today's latest AI news and create/update a comprehensive briefing in Notion, with optional Obsidian vault publishing for graph visualization.
Skill Claude CodeCodex
Run the eval harness against every card under example-cards/ in parallel and persist scores to eval/store.sqlite. Use when the user asks to "backfill", "score everything", or "score all cards" for quality eval.
Skill Claude CodeCodex
Build the interactive offline eval dashboard (eval/dashboard/index.html) — Chart.js trend, axis radar, composite histogram, per-card stacked bars, sortable card table. Use when the user wants to "see eval results", "open dashboard", "visualize quality", or "compare cards".
Skill Claude CodeCodex
Detect quality drift in published briefings by comparing the trailing-7d median composite score against the trailing-30d median (MAD-scaled). Use when the user asks to "check drift", "compare last week to baseline", or "is briefing quality slipping".
Skill Claude CodeCodex
Re-judge every pinned golden card in eval/golden/ and fail if any composite has dropped more than 0.5 points vs its baseline. Use when the user asks to "run regression", "check golden set", or wants CI-style quality gating after a prompt or judge change.
Skill Claude CodeCodex
Emit a Markdown weekly digest of briefing quality scores (coverage, composite stats, axis medians, per-day table). Use when the user asks for a "weekly report", "eval summary", or "quality digest" for a specific date range.
Skill Claude CodeCodex
Judge a single AI News Briefing card against the 5-axis quality rubric (factuality, novelty, source diversity, signal density, coherence) and persist the score. Use when the user asks to "score", "judge", "evaluate", or "rate" a briefing for a specific date.
Skill Claude CodeCodex
Run the system health check to verify the AI News Briefing setup and configuration.
Skill Claude CodeCodex
Fetch and summarize a specific URL for quick insights.
Skill Claude CodeCodex
Trigger the daily AI News Briefing manually.