product-review
Skill178 starsChanged 4 months agoMITView on GitHub
Product quality review — UX flows, onboarding, feature completeness, and user value. Use when a user says "product review", "review my product", "UX review", "is my product good", "product quality", "user experience review", "onboarding review", or "feature audit". Different from code review (review-and-iterate) and product roast (roast-my-product) — this is structured, balanced evaluation.
- Sends data out
13 other projects use a version of this.
Adopted by
Most recently taken up by
- tsaol/awesome-claudetheir own version, first seen Nov 15, 2026
- sohaibt/product-modetheir own version, first seen Nov 15, 2026
- salvatorebottiglieri/agentic-dev-kittheir own version, first seen Nov 9, 2026
- victor-falcon/skillstheir own version, first seen Nov 8, 2026
- Bobagi/claude-skillstheir own version, first seen Oct 29, 2026
- jarrheyd/skillstheir own version, first seen Oct 11, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- sohaibt/product-mode★ 171same name
- tsaol/awesome-claude★ 69same name
- victor-falcon/skills★ 16same name
- RizwanZafaris/product-manager-OS★ 4same name
- salvatorebottiglieri/agentic-dev-kit★ 3same name
- vishal-mandhane/divinity★ 3same name
- d-wwei/product-review★ 2same name
- Iteam-company/claude-code-boilerplates★ 2same name
- AlbertFD/AlbertFD-skills★ 1same name
- chawanjoey/claude-skills★ 1same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- animation-reverse-engineeringSkill
- brand-designSkill
- build-data-pipelineSkill
- build-defi-protocolSkill
- build-mobileSkill
- build-with-claudeSkill
- csoSkill
- debug-programSkill
- design-tasteSkill
- frontend-design-guidelinesSkill
- launch-tokenSkill
- navigate-skillsSkill
- number-formattingSkill
- page-load-animationsSkill
- review-and-iterateSkill
- roast-my-productSkill
- scaffold-projectSkill
- verify-humanity-pohSkill
- virtual-solana-incubatorSkill
- colosseum-copilotSkill
- competitive-landscapeSkill
- defillama-researchSkill
- find-next-crypto-ideaSkill
- learnSkill
- solana-beginnerSkill
- validate-ideaSkill
- apply-grantSkill
- create-pitch-deckSkill
- deploy-to-mainnetSkill
- marketing-videoSkill
- submit-to-hackathonSkill
- video-craftSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 5 are distinctive, and 9 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
If TEL_PROMPTED is no: Before starting the skill workflow, ask the user about telemetry.
- Distinctive: line 36
If A: run this bash:
- Distinctive: line 43
If B: run this bash:
- Distinctive: line 71
Do NOT proceed without answers.
- Very specific: line 75
Read .superstack/idea-context.md and .superstack/build-context.md if available.
- Very specific: line 79
Read references/product-quality-rubric.md for the 8 quality dimensions.
- Very specific: line 83
Put yourself in the shoes of the target user described in Step 1.
- Distinctive: line 91
Document every friction point and every moment of clarity.
- Very specific: line 139
If the user wants to continue iterating, write the product review summary to .superstack/build-context.md so other skills can reference it.
- Very specific: line 143
ALWAYS ask about the product before reviewing.
- Very specific: line 149
If no product exists yet, redirect to /scaffold-project or /build-with-claude.
- Distinctive: line 150
Don't confuse "I don't like the design" with "users can't complete the task." Focus on usability over aesthetics.
- Very specific: line 160
If the user wants harsh feedback, suggest /roast-my-product.
- Very specific: line 217
After the skill workflow completes (success, error, or abort), log the telemetry event.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Preamble (run first)
_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"telemetryTier": *"[^"]*"' | head -1 | sed 's/.*"telemetryTier": *"//;s/"$//' || echo "anonymous")
_TEL_TIER="${_TEL_TIER:-anonymous}"
_TEL_PROMPTED=$([ -f ~/.superstack/.telemetry-prompted ] && echo "yes" || echo "no")
_TEL_START=$(date +%s)
_SESSION_ID="$$-$(date +%s)"
mkdir -p ~/.superstack
echo "TELEMETRY: $_TEL_TIER"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
if [ "$_TEL_TIER" != "off" ]; then
_TEL_EVENT='{"skill":"product-review","phase":"build","event":"started","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}'
echo "$_TEL_EVENT" >> ~/.superstack/telemetry.jsonl 2>/dev/null || true
_CONVEX_URL=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"convexUrl":"[^"]*"' | head -1 | cut -d'"' -f4 || echo "")
[ -n "$_CONVEX_URL" ] && curl -s -X POST "$_CONVEX_URL/api/mutation" -H "Content-Type: application/json" -d '{"path":"telemetry:track","args":{"skill":"product-review","phase":"build","status":"success","version":"0.2.0","platform":"'$(uname -s)-$(uname -m)'","timestamp":'$(date +%s)000'}}' >/dev/null 2>&1 &
true
fiIf TEL_PROMPTED is no: Before starting the skill workflow, ask the user about telemetry.
Use AskUserQuestion:
Help superstack get better! We track which skills get used and how long they take — no code, no file paths, no PII. Change anytime in
~/.superstack/config.json.
Options:
- A) Sure, help superstack improve (anonymous)
- B) No thanks
If A: run this bash:
echo '{"telemetryTier":"anonymous"}' > ~/.superstack/config.json
_TEL_TIER="anonymous"
touch ~/.superstack/.telemetry-promptedIf B: run this bash:
echo '{"telemetryTier":"off"}' > ~/.superstack/config.json
_TEL_TIER="off"
touch ~/.superstack/.telemetry-promptedThis only happens once. If TEL_PROMPTED is yes, skip this entirely and proceed to the skill workflow.
Wrong skill? See SKILL_ROUTER.md for all available skills.
Overview
Structured product quality evaluation. Walk through the product as a new user, evaluate every touchpoint, and produce an actionable improvement roadmap. Balanced — highlight strengths AND weaknesses.
This is NOT a code review (use /review-and-iterate for that) and NOT a harsh roast (use /roast-my-product for that). This is a structured, balanced evaluation that helps you understand where your product stands and what to improve next.
Workflow
Step 1: Gather Context
Always start by asking — use AskUserQuestion:
- What is the product? (URL, description, or demo)
- Who is the target user?
- What's the core use case — the ONE thing users should be able to do?
- What stage? (prototype, MVP, beta, launched)
Do NOT proceed without answers. You need to understand what you're reviewing and through whose eyes.
Step 2: Read Existing Context
Read .superstack/idea-context.md and .superstack/build-context.md if available. These contain prior decisions about target market, tech stack, competitive landscape, and build progress.
Step 3: Load the Evaluation Framework
Read references/product-quality-rubric.md for the 8 quality dimensions. This is your scoring framework.
Step 4: Walk Through as a First-Time User
Put yourself in the shoes of the target user described in Step 1. Use references/onboarding-checklist.md to systematically evaluate the first-time experience:
- What do you see first?
- How quickly do you understand what this product does?
- How many steps to the first meaningful action?
- Where do you get confused?
- Where do you get delighted?
Document every friction point and every moment of clarity.
Step 5: Evaluate Each Quality Dimension
Go through each dimension from references/product-quality-rubric.md:
- Onboarding Flow
- Core Experience
- Error Handling
- Information Architecture
- Visual Design & Polish
- Performance
- Accessibility
- Feature Completeness
For each dimension:
- Score 1-10 with specific evidence
- Note what's working well
- Note what needs improvement
- Suggest a specific fix for the biggest issue in this dimension
Step 6: Reference Web3 Best Practices
Cross-reference the product against references/crypto-ux-patterns.md for web3-specific best practices. Note which patterns are implemented well and which are missing.
Step 7: Synthesize Findings
Compile your evaluation into a structured report:
- Executive Summary — 2-3 sentences on the product's overall quality
- Scorecard — all 8 dimensions with scores
- Top 3 Strengths — what's working well (be specific)
- Top 3 Improvements — highest-impact changes to make
- Detailed Dimension Reviews — full analysis of each dimension
- Improvement Roadmap — prioritized list of fixes by impact and effort
Step 8: Prioritized Improvement Roadmap
Categorize improvements into:
- Quick wins (< 1 day, meaningful impact)
- Medium effort (1-3 days, significant improvement)
- Major investment (1+ week, transformative change)
Order by impact within each category.
Step 9: Save Context (Optional)
If the user wants to continue iterating, write the product review summary to .superstack/build-context.md so other skills can reference it.
Non-Negotiables
- ALWAYS ask about the product before reviewing. Use
AskUserQuestion. Never assume. - Be balanced — acknowledge what's working well, not just what's broken.
- Walk through as a REAL first-time user — document every friction point.
- Score with evidence — "onboarding: 6/10 because step 3 requires wallet but doesn't explain why."
- Prioritize fixes by impact: what fixes will retain the most users?
- Distinguish between "nice to have" and "users are bouncing here."
- If no product exists yet, redirect to
/scaffold-projector/build-with-claude. - Don't confuse "I don't like the design" with "users can't complete the task." Focus on usability over aesthetics.
Distinction from Other Review Skills
| Skill | Focus | Tone |
/review-and-iterate | Code quality, security, production readiness | Technical, engineering-focused |
/roast-my-product | Find every weakness, deliberately harsh | Brutal, provocative |
/product-review | Balanced product quality evaluation | Structured, constructive |
If the user wants harsh feedback, suggest /roast-my-product. If they want code review, suggest /review-and-iterate. This skill is for structured, actionable product evaluation.
Output Format
## Executive Summary
[2-3 sentences on overall product quality]
## Scorecard
| Dimension | Score | Summary |
|-----------|-------|---------|
| Onboarding Flow | X/10 | ... |
| Core Experience | X/10 | ... |
| Error Handling | X/10 | ... |
| Information Architecture | X/10 | ... |
| Visual Design & Polish | X/10 | ... |
| Performance | X/10 | ... |
| Accessibility | X/10 | ... |
| Feature Completeness | X/10 | ... |
| **Overall** | **X/10** | |
## Top 3 Strengths
1. **[Strength]**: [Specific evidence]
2. **[Strength]**: [Specific evidence]
3. **[Strength]**: [Specific evidence]
## Top 3 Improvements
1. **[Improvement]**: [What to change and expected impact]
2. **[Improvement]**: [What to change and expected impact]
3. **[Improvement]**: [What to change and expected impact]
## Detailed Reviews
### Onboarding Flow (X/10)
**Working well**: ...
**Needs improvement**: ...
**Suggested fix**: ...
[Repeat for each dimension]
## Improvement Roadmap
### Quick Wins (< 1 day)
- [ ] [Fix]: [Expected impact]
### Medium Effort (1-3 days)
- [ ] [Fix]: [Expected impact]
### Major Investment (1+ week)
- [ ] [Fix]: [Expected impact]Tone
Think of yourself as a thoughtful product manager doing a quarterly product review. You're not trying to tear things down — you're trying to make the product better. Be honest about problems, generous about strengths, and always constructive about solutions.
Telemetry (run last)
After the skill workflow completes (success, error, or abort), log the telemetry event.
Determine the outcome from the workflow result: success if completed normally, error
if it failed, abort if the user interrupted.
Run this bash:
_TEL_END=$(date +%s)
_TEL_DUR=$(( _TEL_END - ${_TEL_START:-$_TEL_END} ))
_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"telemetryTier": *"[^"]*"' | head -1 | sed 's/.*"telemetryTier": *"//;s/"$//' || echo "anonymous")
if [ "$_TEL_TIER" != "off" ]; then
echo '{"skill":"product-review","phase":"build","event":"completed","outcome":"OUTCOME","duration_s":"'"$_TEL_DUR"'","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","platform":"'$(uname -s)-$(uname -m)'"}' >> ~/.superstack/telemetry.jsonl 2>/dev/null || true
true
fiReplace OUTCOME with success/error/abort based on the workflow result.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

