analyze
Deep analysis workflow for codebases, architectures, systems, products, markets, or research topics. Use when the user asks to analyze, investigate, assess, evaluate, compare, or research something in a structured way.
npx skills add majiayu000/claude-skill-registry --skill analyze-avav25-ai-assets-2 --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.
# Analyze Perform structured analysis with explicit scope, evidence, and conclusions. ## 1. Classify the Request Identify: - Subject - Core question - Scope - Desired depth - Audience - Decision the analysis should inform ## 2. Choose a Framework Pick one to three frameworks from `analytical-frameworks.md` based on the question type. Typical pairings: - Current-state assessment -> gap analysis, architecture assessment - Root cause -> 5 Whys, fishbone, causal analysis - Comparison -> weighted scoring, MCDA - Strategy -> SWOT, Porter's Five Forces, JTBD - Technical assessment -> architecture review, technical debt assessment ## 3. Plan the Investigation Break the work into MECE dimensions. For each dimension, define: - What evidence is needed - Where it will come from - What would confirm or contradict the current hypothesis ## 4. Collect Evidence Use the minimum set of relevant sources: - Repository files and docs - Structured data or metrics - Targeted commands - Web research when current external information is required Track evidence quality and note assumptions. ## 5. Analyze Rules: - Lead with evidence, not opinion - Consider at least one alternative explanation - State confide
- 1. Classify the Request
- 2. Choose a Framework
- 3. Plan the Investigation
- 4. Collect Evidence
- 5. Analyze
- 6. Present the Result
- Companion Resources
What does the analyze skill do?
Deep analysis workflow for codebases, architectures, systems, products, markets, or research topics. Use when the user asks to analyze, investigate, assess, evaluate, compare, or research something in a structured way.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill analyze-avav25-ai-assets-2 --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.