Skill of Skills
📄 skillActiveExperimentalhigh

ResearcherSkill

by krzysztofdudek

One file. Your AI coding agent becomes a scientist. 30+ experiments while you sleep.

Supported Platforms

🤖 Claude Code

Stars

236

Skill Type

📋 Runbooks

Quality Score

59/200

License

MIT

Forks

26

Last Updated

Jul 25, 2026

Discovered

May 11, 2026

Validation

Passed

github.com/krzysztofdudek/ResearcherSkill

Quality Breakdown

59/ 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

high

Broad system access required. Carefully review permissions before installing.

Active

Updated within the last 90 days. Actively maintained.

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

Risk Assessment

  • Repository contains CLAUDE.md configuration file that modifies Claude agent behavior persistently
  • Designed to enable autonomous multi-experiment execution ('30+ experiments overnight while you sleep') without explicit human approval gates for each experiment
  • Plugin architecture across multiple AI platforms (Claude Code, Copilot CLI, Cursor, Codeium) suggests capability to modify agent behavior across tools
  • Archive contains test automation scripts (run.sh, scorer.py, verify.py) indicating shell/execution capabilities
  • Marketplace registration mechanism allows distribution and installation into AI coding agents with minimal friction
  • SKILL.md file is designed to be injected into agent systems to alter their operational behavior

Related guides

Best skills & plugins for Claude Code