SkillAgentSearch skills...

research-agent

Research agent for external documentation, best practices, and library APIs via MCP tools

Install / Use

npx skills add parcadei/Continuous-Claude-v3 --skill research-agent

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

83/100

Supported Platforms

Universal

Our assessment of research-agent

research-agent scores 83/100 on our quality scale, 907th of 1,153 Content & Media skills we index.

Its SKILL.md is 3.5 KB long, well organised into 23 sections with 6 code examples: a solid amount of guidance for an agent.

With 3,943 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
20/20
Description
12/15
Adoption
15/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 10 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-11-06 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 94/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

research-agent compared with similar skills

All 4 of these similar skills score higher than research-agent; compare them before choosing.

SkillScoreStarsUpdatedFormat
research-agent (this skill)by parcadei833.9k10mo agoSKILL.md
Agent-Reachby Panniantong100112.3k9d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md
CowAgentby zhayujie10048.0ktodayCLAUDE.md

Frequently asked questions

How do I install research-agent?
Run npx skills add parcadei/Continuous-Claude-v3 --skill research-agent. The install tabs above show the steps for each supported agent.
Which AI agents does research-agent work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is research-agent safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 94/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is research-agent still maintained?
The repository was last updated about 10 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

name: research-agent description: Research agent for external documentation, best practices, and library APIs via MCP tools user-invocable: false

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"

For best practices / general research (Perplexity):

uv run python -m runtime.harness scripts/mcp/perplexity_search.py \
    --query "best practices for implementing OAuth2 in Node.js 2024" \
    --mode "research"

For scraping specific documentation pages (Firecrawl):

uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
    --url "https://docs.example.com/api/authentication"

Step 3: Synthesize Findings

Combine results from multiple sources into coherent findings:

  • Key concepts and patterns
  • Code examples (if found)
  • Best practices and recommendations
  • Potential pitfalls to avoid

Step 4: Create Handoff

Write your findings to the handoff directory.

Handoff filename format: research-NN-<topic>.md

---
date: [ISO timestamp]
type: research
status: success
topic: [Research topic]
sources: [nia, perplexity, firecrawl]
---

# Research Handoff: [Topic]

## Research Question
[Original question/topic]

## Key Findings

### Library Documentation
[Findings from Nia - API references, usage patterns]

### Best Practices
[Findings from Perplexity - recommended approaches, patterns]

### Additional Sources
[Any scraped documentation]

## Code Examples
```[language]
// Relevant code examples found

Recommendations

  • [Recommendation 1]
  • [Recommendation 2]

Potential Pitfalls

  • [Thing to avoid 1]
  • [Thing to avoid 2]

Sources

  • [Source 1 with link]
  • [Source 2 with link]

For Next Agent

[Summary of what the plan-agent or implement-agent should know]


## Return to Caller

After creating your handoff, return:

Research Complete

Topic: [Topic] Handoff: [path to handoff file]

Key findings:

  • [Finding 1]
  • [Finding 2]
  • [Finding 3]

Ready for plan-agent to continue.


## Important Guidelines

### DO:
- Use multiple sources when beneficial
- Include specific code examples when found
- Note which sources provided which information
- Write handoff even if some sources fail

### DON'T:
- Skip the handoff document
- Make up information not found in sources
- Spend too long on failed API calls (note the failure, move on)

### Error Handling:
If an MCP tool fails (API key missing, rate limited, etc.):
1. Note the failure in your handoff
2. Continue with other sources
3. Set status to "partial" if some sources failed
4. Still return useful findings from working sources

Related Skills

View on GitHub
GitHub Stars3.9k
CategoryContent
Updated9mo ago
Forks303

Languages

Python

Trust signals

94/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 low