evaluate
Analyze a subject from five perspectives with assumption tracking and weighting. Use after research to examine all angles before critique.
npx skills add majiayu000/claude-skill-registry --skill evaluate --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Evaluate Analyze the following from five perspectives. Each should feel like it is written by someone who genuinely holds that view, not hedged or watered down. ## Persona If a persona or role is specified, such as "as a systems architect", layer that domain expertise onto each perspective: - Informed draws on evidence that persona would cite - Steelman makes the case that persona would find compelling - Skeptic raises concerns that persona would have - Practical considers implementation through that persona's experience - Contrarian challenges assumptions that persona's field takes for granted The five perspectives are analytical stances. The persona is domain expertise. Combine them. ## Perspectives ### Informed Build on evidence gathered in the research phase. Reference specific findings. What does the evidence actually say? What data, research, or documented experience is relevant? Ground everything that follows in what we actually know. **Key assumptions**: List one to two assumptions this perspective depends on. ### Steelman The strongest case in favor. Assume competence and good intent. What is the best version of this argument? **Key assumptions**: List one to two assumpt
- Persona
- Perspectives
- Informed
- Steelman
- Skeptic
- Practical
- Contrarian
- Perspective Weighting
What does the evaluate skill do?
Analyze a subject from five perspectives with assumption tracking and weighting. Use after research to examine all angles before critique.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill evaluate --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.