A hypothesis-driven structured diagnosis and solving skill — using measurable criteria, information gain/cost ranking, and three-role orchestration to tackle stuck, ambiguous, multi-possibility problems.
This skill provides a structured, hypothesis-driven approach to problem diagnosis and resolution, ideal for complex, ambiguous issues with multiple potential causes. It leverages three key principles: measurable criteria to validate or invalidate hypotheses, an information gain per cost ranking to prioritize the most efficient diagnostic steps, and a three-role orchestration framework (e.g., analyst, critic, driver) to systematically converge on the root cause and solution. Designed for use with AI agent platforms like Claude Code and Cursor, the skill guides the agent through a step-by-step process of generating hypotheses, designing tests, and executing actions, ensuring both rigor and efficiency. By focusing on cost-effective information gathering, it minimizes wasted effort and accelerates problem-solving in software engineering, DevOps, and technical support scenarios.
npx skills add yekeyekegh/hypo-driven-psInstalled? Explore more Coding & Development skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Hypothesis-driven structured diagnosis and solving skill — leveraging "measurable criteria + information gain per cost ranking + three-role orchestration" to overcome stuck, ambiguous, multi-possibility problems. Hypothesis-driven structured problem solving.
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.