w-review-plan — Claude Code skill: plan review
The w-review-plan Claude Code skill checks a plan’s goals, assumptions, tasks, risks, and references. It compares the plan with project code and docs.
MIT 649 installs ★ 1 updated 2026-10-02
npx skills add blockmatic-icebox/basilic-skills --skill w-review-plan -a claude-codeWhat w-review-plan does
The skill reviews a plan for gaps in its goals, assumptions, tasks, risks, and references. It flags missing deferrals for product scope, secrets, or destructive operations.
It compares the plan with current code and documentation, looking for contradictions and made-up commands. It also checks task dependencies and whether an unfinished plan is being overwritten. The review needs the plan and matching project files, and uses ../w-plan/references/plan-output.md.
Results arrive in chat as a summary, gaps, a suggested task order, and questions. The skill creates no files, branches, or scaffolds; it gives no time estimates and does not grade per-task verification checklists.
What it helps with
- spot missing assumptions and risks in a plan
- compare planned commands and decisions with code and docs
- reorder tasks according to their dependencies
- catch a duplicate backlog or an overwrite of an unfinished plan
Example prompts for the agent
- Review this plan’s goals, assumptions, tasks, risks, and references.
- Compare the plan with the code and docs, flag contradictions, and suggest a task order.
- Find missing decisions about secrets and destructive operations in this plan.
How to install w-review-plan
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-review-plan -a claude-code2Manually: put the files in place
~/.claude/skills/w-review-plan/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/w-review-plan/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-review-plan -a codex2Manually: put the files in place
.agents/skills/w-review-plan/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-review-plan -a cursor2Manually: put the files in place
.cursor/skills/w-review-plan/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install blockmatic-icebox/basilic-skills skills/workflow/w-review-plan2Manually: put the files in place
.github/skills/w-review-plan/SKILL.md1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-review-plan -a gemini-cli2Platform CLI
gemini skills install https://github.com/blockmatic-icebox/basilic-skills --path skills/workflow/w-review-planManually: put the files in place
.devin/skills/w-review-plan/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-review-plan -a opencodeClaude.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 w-review-plan
How do I install w-review-plan in Claude Code?
Run npx skills add blockmatic-icebox/basilic-skills --skill w-review-plan -a claude-code. The skill file is at ~/.claude/skills/w-review-plan/SKILL.md.
What does w-review-plan do?
It checks a plan’s structure against project code and documentation, then returns gaps, a suggested task order, and questions in chat.
Does w-review-plan create files or estimate task duration?
No. It works in chat and creates no files, branches, or scaffolds. It also gives no time estimates.
Source text
SKILL.md · MIT
--- name: w-review-plan description: Review a plan's Goals, Assumptions, Tasks, Risks, and References. disable-model-invocation: true --- Chat only. Do not create files, branches, or scaffolds. Use the attached or in-context plan, matching code/docs, and [plan output](../w-plan/references/plan-output.md). 1. Confirm Goals, Assumptions (3–5), Tasks, Risks, and References (plain paths, no `@`). Flag missing deferrals for product scope, secrets, or destructive ops. 2. Compare the plan to current code and docs. Call out contradictions, invented commands, and any branch or scaffold just to plan. 3. Check dependency order: uncertain work and generated-source ownership come before dependents. Reject a second backlog or overwrite of another unfinished plan. 4. Reply in chat: summary, gaps, suggested reorder, and questions. No time estimates. Do not grade per-task verification checklists.
© blockmatic-icebox · MIT · blockmatic-icebox/basilic-skills