Research

A wave-based research framework that stops you from drawing conclusions after three Google searches. It pushes agents out in parallel sweeps, accumulates findings across multiple sources, then synthesizes only when coverage is actually sufficient. The skill maps breadth-first versus depth-first patterns and includes calibration tables for quick scans versus deep dives. Most useful when evaluating technologies, doing competitive analysis, or any investigation where the fourth source regularly contradicts the first three. The gap analysis phase between waves is the real value here, it forces you to check for contradictions and coverage holes before committing to a direction.

skills.sh installs: 645
GitHub stars: 36
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add hyperb1iss/hyperskills --skill research --agent claude-code

Installs into .claude/skills of the current project.

Files

Evidence-Driven Research

The user's instructions take precedence over this skill; carry existing authorization forward and do not add approval gates. Research does not authorize implementation or external mutations.

Frame the Decision

Name the question, target system, time or version, and consequence of being wrong. Confirm the named artifact exists. Memory is a lead, not proof. For an existing system, run an internal investigation alongside external research, since an installed version or deployment constraint can rule out an attractive option.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly