app-review
Review and process app submissions for the Pollinations showcase. Parse issues, validate submissions, create PRs, handle user corrections.
Best use case
app-review is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Review and process app submissions for the Pollinations showcase. Parse issues, validate submissions, create PRs, handle user corrections.
Teams using app-review should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/app-review/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How app-review Compares
| Feature / Agent | app-review | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Review and process app submissions for the Pollinations showcase. Parse issues, validate submissions, create PRs, handle user corrections.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# App Review
Process app submissions from GitHub issues. Validation (registration, duplicates, stars) is pre-done by workflow.
---
## Categories
Pick the best fit: `Creative`, `Chat`, `Games`, `Dev_Tools`, `Vibes`, `Social_Bots`, `Learn`
---
## APPS.md Row Format
```
| EMOJI | Name | Web_URL | Description (~80 chars) | LANG | category | @author | github_id | repo_url | ⭐stars | discord | other | Submitted_Date | Issue_URL | Approved_Date |
```
- **Submitted_Date**: Issue creation date (when user submitted)
- **Issue_URL**: Link to original GitHub issue
- **Approved_Date**: PR merge date (when app was approved)
---
## If Validation Failed
Comment helpfully based on error:
- Not registered → Ask to register at enter.pollinations.ai
- Duplicate → Explain and close issue
- Add appropriate label (TIER-APP-INCOMPLETE or TIER-APP-REJECTED)
---
## If Validation Passed
```bash
# 1. Fetch issue
gh issue view $ISSUE_NUMBER --json body,author,title
# 2. Parse fields: name, url, description, category, repo, discord, language
# 3. Pick creative emoji
# 4. Create/update branch
git fetch origin main
# If existing_pr: checkout and reset
# Else: git checkout -b auto/app-${ISSUE_NUMBER}-slug origin/main
# 5. Add row
export NEW_ROW="| EMOJI | NAME | URL | DESC | LANG | CAT | @AUTHOR | GITHUB_ID | REPO | STARS | DISCORD | | SUBMITTED_DATE | ISSUE_URL | $(date +%Y-%m-%d) |"
node .github/scripts/app-prepend-row.js
node .github/scripts/app-update-readme.js
# 6. Commit and push
git add -A && git commit -m "Add NAME to CATEGORY" && git push origin HEAD --force-with-lease
# 7. Create PR if new (label: TIER-APP-REVIEW-PR)
gh pr create --title "Add NAME to CATEGORY" --body "Fixes #$ISSUE_NUMBER" --label "TIER-APP-REVIEW-PR"
# 8. Update issue label
gh issue edit $ISSUE_NUMBER --remove-label "TIER-APP" --add-label "TIER-APP-REVIEW"
```
---
## Labels
| Label | Meaning |
|-------|---------|
| `TIER-APP` | New submission |
| `TIER-APP-INCOMPLETE` | Waiting for user fix |
| `TIER-APP-REVIEW` | PR created |
| `TIER-APP-REJECTED` | Rejected (duplicate, etc.) |Related Skills
osx-review
Use when preparing mobile/desktop apps for App Store submission, before final release, or when user mentions App Store, production readiness, shipping, or needs comprehensive quality review for distribution
ascii-preview-generate
Use AI to create ASCII text-based preview of PDF page layout. Transforms visual and extracted data into structured ASCII representation for HTML generation.
reviewing-documentation
Use when reviewing documentation quality, auditing README or CLAUDE.md files, or standardizing AI instruction files.
review-docs
Review documentation (README.md and CLAUDE.md) for quality, completeness, and consistency. Use when asked to review docs, check documentation, validate README files, or audit CLAUDE.md coverage.
review-changelog
Review and complete new changelog entries after automated PR creation. Use when there's a new changelog PR with entries that have placeholder URLs or empty fields that need review. Triggers on phrases like "review changelog", "complete changelog entries", "fix changelog PR", or when user mentions a PR with changelog updates.
doc-reviewer
Reviews documentation for completeness, accuracy, and consistency with the project's DX_GUIDE.md standards. Validates documentation structure, checks for broken links, ensures examples are up-to-date, and verifies technical accuracy. Use when creating or updating documentation, reviewing doc-heavy PRs, or ensuring doc quality.
amazon-sixpager-reviewer
Review Markdown 기반 Amazon 6-pager(6pager/six pager) 문서의 Context/Goal/Tasks 구성이 원칙에 맞는지 점검하고, 실험/서브태스크의 가설·검증 설계·결정 규칙, 커뮤니케이션 싱크 리스크(정의/범위/의사결정 공백), 문서 검색/추적 앵커(지표명/ID/링크)까지 포함해 5 Whys로 모호함을 제거한 리뷰 문서(`{filename}_reivew.md`)를 생성해야 할 때 사용한다.
hld-review
Evaluate an HLD note against linked ADRs, requirements, and architecture principles across six dimensions
deploy-script-review
배포 스크립트의 보안·안전성 리뷰를 수행한다. 롤백 절차, 장애 대응, 권한 설정을 점검한다.
comprehensive-review-pr-enhance
You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability.
code-review
Mandatory code reviews via /code-review before commits and deploys
agent-ops-docker-review
Docker image reviews, optimization, and step-building guidance. Analyzes Dockerfiles for best practices, security issues, and anti-patterns.