Automated summary
This skill critiques the plan produced in plan mode, asking the user clarifying questions one at a time to surface gaps, risks, and unresolved decisions before implementation begins.
Strengths
- Reviews seven explicit dimensions: completeness, technical feasibility, implementation clarity, dependencies, testing, documentation, and security
- Asks one clarifying question at a time through AskUserQuestion instead of dumping a checklist, keeping the dialogue usable
- Prioritises critical gaps and project-derailing risks over cosmetic improvements
- Knows when to stop: once critical decisions are settled it confirms the plan is comprehensive
Limitations
- Requires an existing plan in context; otherwise it only tells the user to create one in plan mode
- Tied to Claude Code via its AskUserQuestion tool and plan-mode dependency
- Does not rewrite the plan or produce code — it critiques and questions, leaving revisions to the user
Immediately after drafting a plan in plan mode, before starting implementation, to catch blind spots.
For reviewing already-written code, or when no plan has been created yet in the session.
Security analysis
SafeThe skill only provides guidance for reviewing a plan and asking clarifying questions. It does not declare or use any execution tools, file modifications, network access, or shell commands, and contains no destructive or exfiltration instructions.
No concerns found
How this analysis is madeExamples
Review plan — I just finished the plan for migrating our auth service to JWT. Critique it before I start coding.Critique this plan for the new billing webhook handler and tell me what's missing, especially around error handling and testing.Check my plan against my security and dependency requirements, and ask me the questions I haven't answered yet.name: review-plan description: Use after creating a plan in plan mode to critique it for gaps, risks, and clarifying questions before implementation. Triggers on "review plan", "critique plan", "check my plan".
Review Current Plan
Conduct a thorough review of the plan created in the current session. Act as a meticulous technical reviewer and strategic advisor.
Prerequisites
This skill requires an active plan from plan mode. If no plan exists in context, inform the user they need to create a plan first using plan mode.
Review Dimensions
Systematically analyze the plan across:
- Completeness: Missing components, edge cases, error handling, dependencies not addressed
- Technical feasibility: Technical challenges, performance bottlenecks, architectural concerns
- Implementation clarity: Does each step have sufficient detail? Any ambiguity?
- Dependencies & prerequisites: External deps, tools, libraries, infrastructure requirements documented?
- Testing strategy: Testing approaches, validation criteria, quality checks defined?
- Documentation: Documentation requirements and knowledge transfer needs addressed?
- Security & compliance: Security considerations, compliance requirements noted?
(Enterprise-only dimensions — deployment/rollout, timeline realism, resource allocation/budget — were dropped for the solo-dev profile.)
Output Format
-
Brief summary: Overall quality assessment and critical gaps (2-3 sentences max)
-
Iterative questions: Ask clarifying questions one at a time using AskUserQuestion tool:
- Context: What aspect you're questioning and why it matters
- Current state: What the plan says (or doesn't say) about this
- Impact: Why this decision matters for success
- Provide multiple-choice options where applicable
-
After each answer, either:
- Ask the next critical question, or
- Confirm the plan is comprehensive
Guidelines
- Be direct and concise in feedback
- Prioritize critical gaps over minor improvements
- Focus on risks that could derail the project
- Don't ask about things already clearly addressed in the plan
- Stop questioning when all critical decisions are resolved
Reference Files
references/question-examples.md- Sample clarifying questions with context
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/plan-review-msba3mcl/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/plan-review-msba3mcl' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/plan-review-msba3mcl/download' --output '.skill-downloads/plan-review-msba3mcl/SKILL.md.part' && mv '.skill-downloads/plan-review-msba3mcl/SKILL.md.part' '.skill-downloads/plan-review-msba3mcl/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Original excerpt: Prerequisites
This skill requires an active plan from plan mode. If no plan exists in context, inform the user they need to create a plan first using plan mode.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/plan-review-msba3mcl/SKILL.md' && test -s '.skill-downloads/plan-review-msba3mcl/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/review-plan' && cp -R '.skill-downloads/plan-review-msba3mcl' '.claude/skills/review-plan'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/plan-review-msba3mcl'openskills read 'plan-review-msba3mcl'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/plan-review-msba3mcl/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.