Expert code review identifying security vulnerabilities, performance issues, and quality problems.
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
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
Submit your Claude Code skill and start earning
epx add shubhamsaboo/awesome-llm-apps --skill code-reviewerCompatible with
Supported agents
Organizes findings by priority: security (critical), performance (high), correctness (high), maintainability (medium), and testing
Covers five core vulnerability categories: SQL injection, XSS, authentication bypasses, hardcoded secrets, and insecure dependencies
Detects performance bottlenecks including N+1 queries, missing indexes, inefficient algorithms, and memory leaks
Provides
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versioncode-reviewerExecute the skills CLI command in your project's root directory to begin installation:
epx add shubhamsaboo/awesome-llm-apps --skill code-reviewerFetches code-reviewer from shubhamsaboo/awesome-llm-apps 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:
.cursor/skills/code-reviewer
Restart Cursor to activate code-reviewer. Access via /code-reviewerin your agent's command palette.
Learn more:View source on GitHubSkills CLI docsAbout CursorWhat are agent skills?
Time estimate: 30-60 minutes to see productivity improvements
Prerequisites
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.
improve
shadcn/improve · code · tag: code
no-mistakes
kunchenguid/no-mistakes · devops · tag: code
yt-dlp
lwmxiaobei/yt-dlp-skill · Productivity · same category
find-skills
kimyx0207/findskill · Productivity · same category
pwa-expert
erichowens/some_claude_skills · Productivity · same category
lua
mindrally/skills · Productivity · same category
Registry listing for code-reviewer matched our evaluation — installs cleanly and behaves as described in the markdown.
code-reviewer reduced setup friction for our internal harness; good balance of opinion and flexibility.
I recommend code-reviewer for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Keeps context tight: code-reviewer is the kind of skill you can hand to a new teammate without a long onboarding doc.
code-reviewer has been reliable in day-to-day use. Documentation quality is above average for community skills.
code-reviewer fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
code-reviewer is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Keeps context tight: code-reviewer is the kind of skill you can hand to a new teammate without a long onboarding doc.
Useful defaults in code-reviewer — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Registry listing for code-reviewer matched our evaluation — installs cleanly and behaves as described in the markdown.
showing 1-10 of 66