SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

swarma
Framework for running high-velocity growth experiments with agent teams that generate hypotheses, run tests, observe signals, and build a validated playbook.

specialist-agent
Audit landing pages and user flows to find conversion friction and deliver prioritized, testable A/B recommendations.

ScienceClaw
Plan rigorous scientific studies: choose designs, calculate sample size/power, set up randomization and blinding, and produce a study protocol template.

agent-skills-hub
Design, launch, and optimize referral or affiliate programs — incentives, mechanics, measurement, and launch checklists for growth teams.