$ loading_
Review code changes across perspectives and produce structured findings.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "code-review" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/hve-core/main/.github/skills/coding-standards/code-review/SKILL.md 2. Save it as ~/.claude/skills/code-review/SKILL.md 3. Reload skills and tell me it's ready
Please review the following code diff and context for correctness, maintainability, and security. Output structured findings with severity, evidence, and suggested fixes.
A severity-ranked list of issues with evidence and fix suggestions.
This is a high-risk code change. First bootstrap the context, then review it with stricter depth for security, release readiness, and regressions, and finally provide a conclusion and key findings.
A deeper risk analysis and a merge-readiness verdict.
Please review this change set from functional, standards, accessibility, and PR-quality perspectives, then merge the results into one unified report.
Findings from each perspective, merged into one report.
Developers can use it before or after opening a PR to check whether changes are correct, consistent, and safe. It turns review results into structured findings for discussion and fixes.
When changes affect security, release readiness, or regressions, use a deeper review mode. It emphasizes reading the full diff first and grounding conclusions in evidence.
For orchestrated reviews with multiple subagents, this skill provides a shared context bootstrap, severity normalization, and a consistent output contract so perspectives stay aligned.
This document is the entrypoint for the Code Review skill. It explains a reusable workflow for reviewing code changes from functional, standards, accessibility, security, readiness, and other perspectives, while keeping results consistent through context bootstrap, depth tiers, severity normalization, and a structured output contract. It also points to reference docs for report formats, checklists, dispatch flow, and cross-skill routing.
This SKILL.md is the entrypoint for the Code Review skill.
The skill provides a reusable review workflow for orchestrators and perspective subagents that evaluate code changes across functional, standards, accessibility, PR, security, readiness, and full review perspectives. It centralizes change-brief preparation, review depth selection, severity normalization, and output contract details so that review agents stay thin and consistent.
Review work should stay anchored in evidence and should avoid premature conclusions. Keep the review grounded in file and line evidence, use proportional depth based on risk, read the full diff range before narrowing, and keep factual orientation separate from structured findings.
SKILL.md — this file (skill entrypoint).references/ — durable review knowledge documents.
output-formats.md — output schema, report skeleton, and persistence behavior.severity-taxonomy.md — severity and verdict normalization model.lens-checklists.md — per-perspective review checklists.context-bootstrap.md — Tier 0 context bootstrap and human-scoping workflow.depth-tiers.md — Tier 1/2/3 verification-depth guidance.walkthrough-protocol.md — orientation-first walkthrough contract and Register 1 narrative expectations.dispatch-loop.md — dispatch board, manifest schema, and walk-back loop.emission-modes.md — native and canonical emission strategies.cross-skill-forks.md — specialist review registry and gating rules.It is a reusable code review workflow that evaluates changes from functional, standards, accessibility, security, and readiness perspectives. It also includes context bootstrap, depth tiers, severity normalization, and a structured output contract.
The docs stress evidence-based review: read the full diff range first, then narrow to hotspots. So at minimum, you need the code changes and relevant context. For finer format details and contracts, see the referenced docs.
It is not a single-dimension check; it supports multi-perspective review, depth tiers, and normalized severity output. That makes it better suited for PR reviews and structured analysis of risky changes.
Helps you write cleaner, safer, more maintainable Python code.
Turns Design Thinking outputs into RPI-ready handoff context.
Compress replies to terse, accurate output with selectable intensity levels.
Use a Python CLI to automate reading and writing Mural content.
Generate, update, and manage PowerPoint decks with YAML-driven Python scripts.
Provides the foundational rules and workflow for Design Thinking coaching.
Review code or branches for correctness, compatibility, architecture, tests, performance, and security.
Run a structured code review before commit or release on local or PR branches.
Review code deeply across correctness, tests, security, performance, and product quality.
Run live code reviews on PRs or MRs from their URLs.
Run multi-model reviews for code changes, PRs, and risky edits.
Trigger a code review against plans or requirements before moving forward.