review
Interactive markdown review with web UI. Use when:- User says "review this", "check this plan", "/review"- User wants to give feedback on a plan or document- User says "let me review", "피드백", "검토해줘"- User specifies a file path to review (e.g., "review /path/to/file.md")
When & Why to Use This Skill
This Claude skill provides an interactive web-based interface for structured markdown content review. It streamlines the feedback loop by allowing users to visually approve, reject, or comment on specific sections of documents, plans, or code, ensuring precise revisions and efficient project alignment.
Use Cases
- 1. Project Plan Validation: Reviewing complex implementation plans or roadmaps step-by-step to ensure all stakeholders agree on the path forward before execution.
- 2. Technical Documentation Review: Providing granular feedback on README files, API documentation, or technical guides with specific comments on individual paragraphs or instructions.
- 3. Content Approval Workflows: Using the interactive UI to quickly sign off on AI-generated drafts, marketing copy, or reports through a simple checkbox and comment system.
- 4. Collaborative Editing: Facilitating a clear 'review-and-revise' cycle where the AI processes structured feedback to automatically update documents based on user rejections or suggestions.
| name | review |
|---|---|
| description | Interactive markdown review with web UI. Use when user says "review this", "check this plan", "피드백", "검토해줘" or specifies a file path to review. |
Interactive Review Skill
This skill opens an interactive web UI where users can review content with checkboxes and comments.
How It Works
- Determine the content source:
- If user specifies a file path: Use the
Readtool to get the file contents - If user provides content directly: Use that content as-is
- Otherwise: Collect the most recent relevant content from the conversation
- If user specifies a file path: Use the
- Call
mcp__interactive_review__start_reviewwith the content - A browser window opens automatically with the review UI
- User reviews each item:
- Check/uncheck to approve/reject
- Add optional comments
- User clicks Submit
- Process the feedback and respond accordingly
Content Sources (Priority Order)
- Explicit file path: User says "review /path/to/file.md" or "이 파일 리뷰해줘: README.md"
- Read the file using
Readtool and use its contents
- Read the file using
- Direct content: User provides or references specific content to review
- Use the provided content directly
- Conversation context: Extract relevant content from recent conversation
- Plans, documents, code, etc. that were recently discussed
Usage
When the user wants to review content:
# If file path is specified, read it first:
Read({ "file_path": "/path/to/file.md" })
# Then start the review:
mcp__interactive_review__start_review({
"content": "<content from file or conversation>",
"title": "<descriptive title>"
})
Processing Results
The tool returns a JSON with review items. Handle each item based on:
| checked | comment | Action |
|---|---|---|
| true | empty | Approved - proceed as planned |
| true | has text | Approved with note - consider the feedback |
| false | has text | Rejected - modify according to comment |
| false | empty | Rejected - remove or reconsider this item |
Example Flow
User: "Review this implementation plan"
- Extract the plan content from recent output
- Call start_review with the content
- Wait for user feedback (tool blocks until submit)
- Present summary of feedback
- Ask if user wants you to proceed with approved items or revise rejected items
Response Template
After receiving feedback:
## Review Summary
**Approved**: X items
**Needs revision**: Y items
### Items requiring changes:
- [Item]: [User's comment]
Would you like me to:
1. Proceed with approved items
2. Revise the rejected items based on feedback
3. Both - revise then proceed