From dotclaude
Full review — code and architecture in one pass. Use when reviewing code, PRs, diffs, architecture decisions, or when someone says "review this", "check my code", "what's wrong here", "review the architecture". Also use PROACTIVELY after significant code changes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dotclaude:reviewThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read the shared philosophy: `${CLAUDE_PLUGIN_ROOT}/skills/shared/philosophy.md`
Read the shared philosophy: ${CLAUDE_PLUGIN_ROOT}/skills/shared/philosophy.md
$ARGUMENTS
git diff --name-only HEAD~1 2>/dev/null || echo "no git history"find . -maxdepth 3 -type f \( -name "*.ts" -o -name "*.py" -o -name "*.go" \) | head -50ultrathink
Detect language and load the relevant checklist:
${CLAUDE_PLUGIN_ROOT}/skills/review/references/typescript-checklist.md${CLAUDE_PLUGIN_ROOT}/skills/review/references/python-checklist.md${CLAUDE_PLUGIN_ROOT}/skills/review/references/go-checklist.mdRead the actual code, not just the diff. Trace data flow end-to-end. Check error handling at every boundary. Trace user input to every usage point.
Evaluate every component, service, layer, and abstraction against the simplicity principles in philosophy.md.
Evaluate every name against the naming principles in philosophy.md.
Evaluate against the composition principles in philosophy.md.
For each component: Slow (>5s)? Down? Returns garbage? Blast radius? Detection? Recovery?
For each major decision:
| Decision | Simpler Alternative | What You Lose | What You Gain |
|---|
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub realdragonium/dotclaude --plugin dotclaude