This is a background agent that hits MCP tools (Nia for library docs, Perplexity for best practices, Firecrawl for web scraping) and writes up what it finds in a structured handoff markdown file. You spawn it when you need external documentation or current best practices before planning a feature. It's not user-invocable, so it runs as part of a larger agent workflow where one agent does research and hands off to a planning or implementation agent. The handoff format is well thought out with sections for findings, code examples, and pitfalls. Honest take: this is solid infrastructure for keeping AI context grounded in actual docs rather than hallucinated APIs, though you'll need those MCP connections configured.

skills.sh installs
530
GitHub stars
3.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill research-agent --agent claude-code

Installs into .claude/skills of the current project.

Files

Note: The current year is 2025. When researching best practices, use 2024-2025 as your reference timeframe.

Research Agent

You are a research agent spawned to gather external documentation, best practices, and library information. You use MCP tools (Nia, Perplexity, Firecrawl) and write a handoff with your findings.

What You Receive

When spawned, you will receive:

  1. Research question - What you need to find out
  2. Context - Why this research is needed (e.g., planning a feature)
  3. Handoff directory - Where to save your findings

Your Process

Step 1: Understand the Research Need

Identify what type of research is needed:

  • Library documentation → Use Nia
  • Best practices / how-to → Use Perplexity
  • Specific web page content → Use Firecrawl

Step 2: Execute Research

Use the MCP scripts via Bash:

For library documentation (Nia):

uv run python -m runtime.harness scripts/mcp/nia_docs.py \
    --query "how to use React hooks for state management" \
    --library "react"

Sponsors

Details

Repository
github.com/parcadei/continuous-claude-v3
Categories
Documentation, AI & Agent Building, Data Science & ML
First seen
Jun 3, 2026

More from parcadei/continuous-claude-v3

All 108
1parcadei avatarrepo-research-analystparcadei/continuous-claude-v3Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase522skills.sh installs
2robdefeo avataramazon-working-backwardsrobdefeo/agent-skillsGuide the Amazon Working Backwards process from the 5 Questions through to a full PR-FAQ document. Use when the user wants to (1) draft answers to the Amazon 5 520skills.sh installs
3libukai avatarvscode-httpyac-configlibukai/awesome-agent-skillsConfigure VSCode with httpYac for API testing and automation. This skill should be used specifically when converting API documentation to executable .http files513skills.sh installs
4manutej avatarvuejs-developmentmanutej/luxor-claude-marketplaceComprehensive Vue.js development skill covering Composition API, reactivity system, components, directives, and modern Vue 3 patterns based on official Vue.js d511skills.sh installs
5glittercowboy avatarcreate-agent-skillsglittercowboy/taches-cc-resourcesExpert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing507skills.sh installs
6manutej avatarhasura-graphql-enginemanutej/luxor-claude-marketplaceComplete guide for Hasura GraphQL Engine including instant GraphQL APIs, permissions, authentication, event triggers, actions, and production deployment506skills.sh installs