AGENT SKILL

open-research

Conduct autonomous multi-source academic, technical, and open-web research using ArXiv, Wikipedia, and web endpoints. Use for architecture investigations, algorithm discovery, literature review, and synthesizing citations into structured research dossiers.

License 许可
MIT
最近更新
2026-10-16
Stars
★ 2
Forks
0

01 前言 Front Matter

name
open-research
description
Conduct autonomous multi-source academic, technical, and open-web research using ArXiv, Wikipedia, and web endpoints. Use for architecture investigations, algorithm discovery, literature review, and synthesizing citations into structured research dossiers.
argument-hint
What topic, paper, library, or algorithm do you want to research?
user-invocable
true
disable-model-invocation
false

03 SKILL.md 正文

Open Research

Purpose

Autonomous multi-source research workflow that discovers academic papers, technical documentation, and encyclopedic references, extracting primary citations and synthesizing actionable research dossiers.

Use this skill when:

  • Investigating algorithms, academic papers, or protocol specifications
  • Evaluating competing technical libraries, architectural patterns, or frameworks
  • Researching API specs, RFCs, or formal models
  • Compiling structured technical dossiers with validated primary sources

Research Tool Integration

When conducting open research, call the available research tools:

  1. vscode_open_research: Executes a federated multi-source search query across ArXiv, Wikipedia, and open web endpoints with automatic deduplication, scoring, and synthesized key findings.
    • query: Focused keywords (e.g., "MCTS tree search context pruning", "raft consensus invariants").
    • sources: Optional subset ["arxiv", "wikipedia", "web"].
    • maxResults: Total entries per source (1 to 10).
  2. Direct URL and web inspection tools (read_url_content, search_web, fetch): Retrieve complete whitepapers, documentation pages, and GitHub markdown specifications.

Autonomous Research Procedure

Follow this 4-stage loop:

Stage 1: Problem Decomposition & Query Generation

  1. Extract core technical concepts from the user's objective.
  2. Formulate 2 to 4 orthogonal queries:
    • Theoretical / Academic: "formal specification <concept> arxiv"
    • Implementation / Technical: "<technology> architecture benchmark github"
    • Contextual / Encyclopedic: "<term> overview wikipedia"

Stage 2: Federated Information Gathering

  1. Invoke vscode_open_research with the decomposed queries.
  2. Collect the resulting sources, URLs, and snippets.
  3. If specific papers or documentation pages contain high-signal content, inspect the target URLs directly to extract exact formulas, benchmark figures, or architecture patterns.

Stage 3: Synthesis & Verification

  1. Cross-reference claims across multiple independent sources.
  2. Filter out promotional claims; focus on verified constraints, benchmark numbers, complexity bounds, and interface definitions.
  3. Identify actionable implementation decisions directly applicable to the codebase.

Stage 4: Dossier Compilation

Format the final findings as a structured research dossier:

# Research Dossier: <Topic>

## Executive Summary
Concise synthesis of the state-of-the-art and direct relevance to the project.

## Key Technical Findings
- Finding 1 with verified rationale
- Finding 2 with concrete operational trade-offs

## Primary Sources & Citations
- [<Paper/Spec Title>](<URL>) - Key contribution and relevant section.

## Architecture & Implementation Recommendations
Actionable steps to apply in the codebase.

Token Optimization Rules

  • Do not dump entire fetched HTML pages into context.
  • Extract only pertinent sections, function signatures, or mathematical formulas.
  • Compact intermediate findings before generating final code or PRs.

04 同仓库更多 Skills

sridhar-mani
sridhar-mani/npc-code

troubleshoot

Investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files. Use when users ask why something happened, why a request was slow, why tools or subagents were used or skipped, or why instructions/skills/agents did not load.

★ 2
sridhar-mani
sridhar-mani/npc-code

project-setup-info-local

Comprehensive setup steps to help the user create complete project structures in a VS Code workspace; this tool is designed for full project initialization and scaffolding, not for creating individual files. When to use this tool: user wants to create a new complete project from scratch; setting up entire project frameworks (TypeScript projects, React apps, Node.js servers, etc.); initializing Model Context Protocol (MCP) servers with full structure; creating VS Code extensions with proper scaffolding; setting up Next.js, Vite, or other framework-based projects; user asks for "new project", "create a workspace", "set up a [framework] project"; need to establish a complete development environment with dependencies, config files, and folder structure. When NOT to use this tool: creating single files or small code snippets; adding individual files to existing projects; making modifications to existing codebases; user asks to "create a file" or "add a component"; simple code examples or demonstrations; debugging or fixing existing code. This tool provides complete project setup including: folder structure creation; package.json and dependency management; configuration files (tsconfig, eslint, etc.); initial boilerplate code; development environment setup; build and run instructions. Use other file creation tools for individual files within existing projects.

★ 2
sridhar-mani
sridhar-mani/npc-code

project-setup-info-context7

Comprehensive setup steps to help the user create complete project structures in a VS Code workspace. This tool is designed for full project initialization and scaffolding, not for creating individual files. When to use this tool: when the user wants to create a new complete project from scratch; when setting up entire project frameworks (TypeScript projects, React apps, Node.js servers, etc.); when initializing Model Context Protocol (MCP) servers with full structure; when creating VS Code extensions with proper scaffolding; when setting up Next.js, Vite, or other framework-based projects; when the user asks for "new project", "create a workspace", or "set up a [framework] project"; when you need to establish a complete development environment with dependencies, config files, and folder structure. When NOT to use this tool: when creating single files or small code snippets; when adding individual files to existing projects; when making modifications to existing codebases; when the user asks to "create a file" or "add a component"; for simple code examples or demonstrations; for debugging or fixing existing code. This tool provides complete project setup including folder structure creation, package.json and dependency management, configuration files (tsconfig, eslint, etc.), initial boilerplate code, development environment setup, and build and run instructions. Use other file creation tools for individual files within existing projects.

★ 2
sridhar-mani
sridhar-mani/npc-code

pdf

Read, extract text, extract tables, and summarize PDF documents. Use for examining specifications, reports, papers, and user manuals.

★ 2
sridhar-mani
sridhar-mani/npc-code

open-research

Conduct autonomous multi-source academic, technical, and open-web research using ArXiv, Wikipedia, and web endpoints. Use for architecture investigations, algorithm discovery, literature review, and synthesizing citations into structured research dossiers.

★ 2
sridhar-mani
sridhar-mani/npc-code

install-vscode-extension

How to install a VS Code extension from an extension ID. Useful when the user wants to add new capabilities to their VS Code environment by installing extensions.

★ 2