You are initiating a Socratic code review session. Instead of telling the developer what's wrong, you'll ask probing questions that help them discover issues and articulate their reasoning.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionsocratic-reviewExecute the skills CLI command in your project's root directory to begin installation:
Fetches socratic-review from rysweet/amplihack and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate socratic-review. Access via /socratic-review in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
1
total installs
1
this week
44
GitHub stars
0
upvotes
Run in your terminal
1
installs
1
this week
44
stars
You are initiating a Socratic code review session. Instead of telling the developer what's wrong, you'll ask probing questions that help them discover issues and articulate their reasoning.
Use Socratic review when:
Use traditional review when:
# Basic usage - reviews file with standard depth (7-10 questions)
/socratic-review path/to/file.py
# Quick review - 3-5 focused questions
/socratic-review path/to/file.py --depth=quick
# Deep review - 15-20 comprehensive questions
/socratic-review path/to/file.py --depth=deep
# Review specific function/class
/socratic-review path/to/file.py --focus="function_name"
# Review a directory
/socratic-review src/auth/
# Non-interactive mode (for CI/subprocess - asks all questions, synthesizes without waiting)
/socratic-review path/to/file.py --non-interactive
# Output structured JSON for programmatic processing
/socratic-review path/to/file.py --non-interactive --output=review.json
# Write insights to DECISIONS.md
/socratic-review path/to/file.py --write-decisions
First, I'll analyze the code to understand:
Based on the code, I'll select questions from six categories:
I'll ask questions one at a time and wait for your responses:
**Q1** [Category: Design]
Why did you choose to store session data in memory rather than a database?
[WAIT FOR YOUR RESPONSE]
After each answer, I may:
After all questions, I'll summarize:
Best for:
Focus: Highest-risk areas only
Best for:
Focus: All question categories covered
Best for:
Focus: Comprehensive with follow-ups
## Socratic Review: auth/login.py
I'm going to ask you some questions about this login implementation.
There are no wrong answers - the goal is to think through the design together.
---
**Q1** [Category: Design]
I see you're storing session data in an in-memory dictionary.
Why did you choose this approach over Redis or database storage?
> Your answer: "It was simpler to implement and we don't have many users yet."
That makes sense for simplicity. **Follow-up**: What would trigger you to
migrate to a different storage mechanism?
> Your answer: "Um... I guess when we scale? Or add multiple servers?"
**Insight noted**: Migration criteria aren't clearly defined.
---
**Q2** [Category: Edge Case]
What happens if a user's session expires while they're submitting a form?
> Your answer: "I... actually haven't thought about that."
**Insight noted**: Session timeout during active use is unhandled.
---
[... more questions ...]
---
## Review Synthesis
### Insights Revealed
- Session storage is pragmatic but migration path unclear
- Session timeout during active use is unhandled
### Assumptions Surfaced
- Single server deployment assumption
- Users won't have long form submissions
### Recommendations
1. Document session storage migration criteria
2. Add graceful session timeout handling
### Strengths Identified
- Clear awareness of simplicity trade-offs
- Quick recognition of gaps when prompted
Socratic review can replace standard review at Step 11 of DEFAULT_WORKFLOW:
Step 11: Review the Code
Choose review approach:
A) Standard review - Direct feedback from reviewer agent
B) Socratic review - Dialogue with socratic-reviewer agent
Use Socratic when:
- Learning is as important as fixing
- Design decisions need documentation
- Mentoring/onboarding context
When answering questions:
The key question: how do insights from dialogue become actual improvements?
During live dialogue:
--write-decisions to persist insights to DECISIONS.mdFor automated contexts:
Auto-Detection: The skill automatically detects non-interactive contexts (e.g., claude --print, CI pipelines, no TTY) and switches to non-interactive mode. This prevents the frustrating pattern of asking questions, waiting for responses that can't come, and exiting INCONCLUSIVE with no useful output.
# Run non-interactive review
/socratic-review src/auth/ --non-interactive --output=review.json
# Post results to PR
gh pr comment 123 --body "$(jq -r '.synthesis | "## Socratic Review\n\n### Insights\n" + (.insights_revealed | map("- " + .) | join("\n")) + "\n\n### Recommendations\n" + (.recommendations | map("- [" + .priority + "] " + .description) | join("\n"))' review.json)"
If 3 questions go unanswered in interactive mode, the session exits with INCONCLUSIVE status. Socratic review requires willing participation - without it, exit cleanly rather than pretend to do something else. The user can then choose to run traditional /review instead.
This skill is based on:
~/.amplihack/.claude/agents/amplihack/specialized/socratic-reviewer.md/reviewing-code skill for direct feedbackphilosophy-guardian agent for complianceWhen this skill is invoked:
Task(
subagent_type="socratic-reviewer",
prompt="Conduct Socratic review of [file] at [depth] level. Focus on: [areas]"
)
The agent will handle the question flow and wait for responses using [WAIT] markers.
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
Solid pick for teams standardizing on skills: socratic-review is focused, and the summary matches what you get after install.
socratic-review reduced setup friction for our internal harness; good balance of opinion and flexibility.
I recommend socratic-review for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Useful defaults in socratic-review — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Registry listing for socratic-review matched our evaluation — installs cleanly and behaves as described in the markdown.
We added socratic-review from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Solid pick for teams standardizing on skills: socratic-review is focused, and the summary matches what you get after install.
socratic-review reduced setup friction for our internal harness; good balance of opinion and flexibility.
Registry listing for socratic-review matched our evaluation — installs cleanly and behaves as described in the markdown.
socratic-review reduced setup friction for our internal harness; good balance of opinion and flexibility.
showing 1-10 of 33