incremental-review-router — Claude Code skill: install guide
incremental-review-router is a Claude Code skill that chooses review skills for the parts of a project affected by a change. It factors in relevant tasks, artifacts, and regression-related history.
MIT ★ 529 updated 2026-11-17
npx skills add ShuaiMXu/happyhands --skill incremental-review-router -a claude-codeWhat incremental-review-router does
The skill routes a project change to a focused set of reviews instead of repeating a full product audit after a limited change. Its inputs are an impact map, project history, available skills, and review evidence.
It matches reviews to affected tasks and artifacts, then brings in history that matters for regression checks. Each selected skill comes with a reason. The output contains structured evidence, findings, suggested updates, and limitations.
Routing quality relies on a dependable impact map. When required inputs or professional review are missing, the skill uses needs-evidence. It does not fabricate an Experience Score or turn a project-specific observation into a universal rule.
What it helps with
- route a project change to relevant reviews
- include regression-sensitive project history
- explain why each review skill was selected
- flag missing evidence or professional review
Example prompts for the agent
- Choose the reviews needed for this change and explain each selected skill.
- Map the affected tasks and artifacts, then account for regression-related project history.
- Return structured findings for this change and flag any missing evidence.
How to install incremental-review-router
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill incremental-review-router -a claude-code2Manually: put the files in place
~/.claude/skills/incremental-review-router/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/incremental-review-router/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill incremental-review-router -a codex2Manually: put the files in place
.agents/skills/incremental-review-router/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill incremental-review-router -a cursor2Manually: put the files in place
.cursor/skills/incremental-review-router/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ShuaiMXu/happyhands skills/product-design/incremental-review-router2Manually: put the files in place
.github/skills/incremental-review-router/SKILL.md1Skills CLI (Vercel)
npx skills add ShuaiMXu/happyhands --skill incremental-review-router -a gemini-cli2Platform CLI
gemini skills install https://github.com/ShuaiMXu/happyhands --path skills/product-design/incremental-review-routerManually: put the files in place
.devin/skills/incremental-review-router/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about incremental-review-router
How do I install incremental-review-router in Claude Code?
Run npx skills add ShuaiMXu/happyhands --skill incremental-review-router -a claude-code. The skill file is at ~/.claude/skills/incremental-review-router/SKILL.md.
What does incremental-review-router do?
It selects review skills based on the tasks and artifacts affected by a project change, while incorporating relevant regression history. It also explains each selection.
What inputs does incremental-review-router need?
It needs an impact map, project history, available skills, and review evidence. Routing quality depends on the impact map being reliable.
Source text
SKILL.md · MIT
--- name: incremental-review-router description: "Select the smallest sufficient set of review skills and product states for a project change." --- # Incremental Review Router Avoid rerunning a full audit when only part of the product changed. ## Required evidence - impact map - project history - available skills and evidence ## Decisions - Route by affected task and artifact - Include regression-sensitive history - Explain every selected skill ## Boundary Routing quality depends on a reliable impact map. Return structured evidence, findings, proposed updates and limitations. Use `needs-evidence` when required inputs or professional review are missing. Never invent an Experience Score or promote a project observation into a universal rule.
© ShuaiMXu · MIT · ShuaiMXu/happyhands