plugins/code-review-report/skills/SKILL.md
Turn code changes into a single-file HTML code review report that pairs the diff with context a diff can't show — design decisions, rejected alternatives, tradeoffs, unfinished work — plus prioritized review points. Use when preparing for review after finishing a sizable change, refactor, or feature, or whenever the user asks for a review report, change report, or an HTML summary of their changes.
npx skillsauth add 2ykwang/agent-skills code-review-reportInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Build a single-file HTML report a reviewer reads before digging through the raw diff. A diff shows what changed; it doesn't show why, what was rejected, or what's still missing. Filling that gap with the context accumulated in this conversation is what separates this from a diff viewer.
Check the change with git status and git diff. Default scope: current branch vs the default branch, plus the uncommitted working tree.
git diff <base>...HEAD (committed), git diff HEAD (uncommitted)git status and read them directly.If the scope is mixed or contains unrelated changes, ask the user. Exclude unrelated changes or mark them separately.
Gather from this conversation the things a diff never records:
If the conversation lacks this (e.g., the skill was invoked fresh), reconstruct from git log, commit messages, PRs, and related docs. If still empty, ask the user.
Inject the changed code plus the working context into subagents and collect suspicious spots as P1–P3 findings. Read references/review-perspectives.md for the perspective list and the subagent prompt skeleton. The context injection is the point — without it you only get surface-level remarks, not findings like spec mismatches or contradictions between decisions. For large changes, run one subagent per perspective in parallel.
Start from assets/template.html. Follow references/report-structure.md for sections and references/style-guide.md for visual rules. Two things are non-negotiable:
language-* classes)Write the report in the language the user works in: translate the template's headings and set <html lang>. Keep code as-is. Before finalizing, run the self-check at the end of references/report-structure.md.
<task-slug>-review-report.html (kebab-case task name).python3 <skill-dir>/scripts/inline_hljs.py <report-path>open <report-path> (macOS), xdg-open (Linux), start (Windows).development
Turn code changes into a single-file HTML code review report that pairs the diff with context a diff can't show — design decisions, rejected alternatives, tradeoffs, unfinished work — plus prioritized review points. Use when preparing for review after finishing a sizable change, refactor, or feature, or whenever the user asks for a review report, change report, or an HTML summary of their changes.
development
Render an interactive HTML board for the user to pick among multiple comparable options side-by-side at once — engineering trade-offs, copy audits, action-item triage, architecture decisions, policy calls. Returns the picks (and optional hold/note flags) as a JSON file the agent can apply.
development
Render an interactive HTML board for the user to pick among multiple comparable options side-by-side at once — engineering trade-offs, copy audits, action-item triage, architecture decisions, policy calls. Returns the picks (and optional hold/note flags) as a JSON file the agent can apply.
data-ai
File a GitHub issue maintainers can actually act on — verified, not a duplicate, follows repo conventions (template/label/prefix), and previewed before publishing. Use when reporting a known problem.