メニュー
Review code for bugs, security vulnerabilities, performance issues, and maintainability. Trigger with "review this code", "check this PR", "look at this diff", "is this code safe?", or when the user shares code and asks for feedback.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | code-review |
| description | Review code for bugs, security vulnerabilities, performance issues, and maintainability. Trigger with "review this code", "check this PR", "look at this diff", "is this code safe?", or when the user shares code and asks for feedback. |
Structured code review covering security, performance, correctness, and maintainability. Works on diffs, PRs, files, or pasted code snippets.
Rate each dimension and provide specific, actionable findings with file and line references. Prioritize critical issues first. Always include positive observations alongside issues.
Atlas architect: boot the workspace. Verify claude-mem and context-mode, scan the project, recommend tooling (confirm first), wire hooks, seed the docs/ SSOT.
Measure atlas's own run health, audit context/asset waste, and mine session transcripts. Three lenses: RUN HEALTH reads the observability DB for metrics (wall-clock, dispatches, verifier coverage) and baseline->target goals; ASSET AUDIT scores each context-loaded skill/agent/plugin by token cost and relevance to flag disable/relocate; SESSION FORENSICS mines transcripts for unused tools and unverified claims into rules. No args reports trends.
Use to map a codebase into feature-grouped flowcharts, find architectural duplication across features, and propose the simplest unified architecture - discovery-first and zero-arg. Runs as a Workflow that fans out one explorer per feature, hunts duplication, and synthesizes a unification proposal with file:line evidence. Use before a refactor, to "find the ideal path," or to unify duplicated systems.
Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" -> Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" -> Loads existing skill, asks targeted questions, appends/updates reference files Use when data analysts want Claude to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns.
QA an analysis before sharing with stakeholders - methodology checks, accuracy verification, and bias detection. Use when reviewing an analysis for errors, checking for survivorship bias, validating aggregation logic, or preparing documentation for reproducibility.
Build self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling. Use when creating dashboards, building interactive reports, or generating shareable HTML files with charts and filters that work without a server.
