Skill of Skills
📄 skillStaleExperimentallow

research-companion

by andrehuang

Strategic research thinking agents for Claude Code — idea evaluation, project triage, and structured brainstorming. Helps you decide which papers to write, not just how to write them.

Supported Platforms

🤖 Claude Code

Stars

683

Skill Type

🔄 Business Process & Team Automation

Quality Score

70/200

License

MIT

Forks

56

Last Updated

Jul 24, 2026

Discovered

Apr 23, 2026

Validation

Passed

github.com/andrehuang/research-companion

Quality Breakdown

70/ 200

Content Signals

○Gotchas/Edge Cases+40
○Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

○Recent Activity+15
○Scripts/Automation+10
○Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

low

Standard permissions only. Safe for general use.

Stale

No commits in 90-365 days and no tagged releases.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Repository contains AI agent/plugin configuration files and markdown documentation only
  • No executable scripts, bash/shell commands, or system capability requests
  • No installation automation, bootstrap scripts, or persistent config modifications to system paths
  • No multi-agent spawning or autonomous operation without human approval
  • No external code execution or remote command execution capabilities
  • No offensive security, pentesting, or exploit-related content

Related guides

Best skills & plugins for Claude Code