🔎 CODE · Coding & Dev Level: Intermediate ⏱ 45 MIN Free & Open Source

Automate Pull Request Code Review with GitHub Actions + an LLM

On every PR, read the diff, have an LLM review defects, security and style, and post graded comments back so human reviewers focus on logic and architecture.

CORE TOOLS GitHub Actions, DeepSeek, Claude

BEST FOR Team leads, indie developers, open-source maintainers

REQUIREMENTS A GitHub repo with Actions; an LLM API key; do not send sensitive code to untrusted services

✦ WHY THIS WORKFLOW

Trivial issues drain reviewer attention. Let AI take the first pass so people focus on architecture and business, with instant feedback for newcomers.

✦ Interactive Workflow Animation Preview

Step-by-Step Action Checklist

0 / 4 Completed

✓ Step 1 [Set secrets and permissions]: Store the LLM key in repository secrets and grant the workflow read-code and write-comment only, never push.
✓ Step 2 [Write the trigger workflow]: Trigger on pull_request, read the diff, chunk by file when large and skip lockfiles and build output.
✓ Step 3 [Call the LLM]: Submit the diff with your coding standards and require structured output of severity, file and line, issue and fix.
✓ Step 4 [Post comments and iterate]: Comment on the PR showing medium and high severity only, track false positives and tune the prompt. Humans decide.

READY-TO-USE PROMPT TEMPLATE

Open Official Tool / Repo ↗

You are a senior code reviewer. Review the diff below and output a JSON array only, each item: {"severity":"high|medium|low","file":"","line":0,"issue":"","suggestion":""}.
Focus: logic bugs, edge and null cases, concurrency, security risks (injection, secret leaks, permissions) and deviations from standards.
Skip pure formatting; return an empty array if clean; mark uncertain items as such in issue.
[Standards]
[Diff]

Use Cases & Tags:

Faster team reviewsSolo project qualityOpen-source first-pass reviewMentoring juniors#github actions#code review#pull request#ci

Related AI Workflows

← Describe your idea on Home

CODE · Coding & Dev

20 MIN

NVIDIA SkillSpector: Security Vulnerability Scanner & Benchmark for AI Agent Skills & MCP Tools

An authoritative open-source security scanner and capability benchmark for AI agent skills and MCP servers from NVIDIA, with 22k+ GitHub stars. As autonomous coding and desktop agents gain widespread MCP tool access, indirect prompt injection, tool poisoning, sensitive credential theft, and supply-chain vulnerabilities pose severe enterprise threats. SkillSpector offers static AST analysis, adversarial fuzzing, runtime sandbox interception, and least-privilege permission auditing. It evaluates any candidate MCP server or skill bundle before installation, producing actionable risk scores, vulnerability proofs, and hardening remediations.

NVIDIA SkillSpector (Open Source)Python 3.10+Model Context Protocol (MCP)Docker Sandbox

Best for: AI architects, cybersecurity researchers, SecOps engineers, enterprise agent developers, open-source MCP maintainers

Full guide ↗

CODE · Coding & Dev

25 MIN

Empower AI Coding Agents with Autonomous Binary Reverse Engineering & Decompilation via REA

A jaw-dropping viral sensation with 360k+ stars on GitHub! REA (Reverse Engineering Agent) gives Claude Code, Codex, and Cursor native decompilation and binary disassembly superpowers. Backed by headless Ghidra, Tree-sitter, and control flow graph (CFG) synthesizers, it inspects closed-source Windows PE, Linux ELF, and Electron packages to decode proprietary protocols, reconstruct obfuscated algorithms, and audit security flaws.

REA (Open Source)GhidraTree-sitterClaude Code / Codex

Best for: Security researchers, reverse engineers, systems programmers, open-source clean-room contributors, protocol analysts

Full guide ↗

CODE · Coding & Dev

15 MIN

Convert Giant Codebases into Deterministic AST Knowledge Graphs via Open-Source Graphify

A viral code-understanding breakthrough with 130k+ GitHub stars! Graphify replaces fragile vector chunking with deterministic local AST and Leiden community detection. It parses millions of lines of code, SQL migrations, API specs, and architectural docs into an explicit, explainable knowledge graph over MCP for Claude Code, Cursor, Codex, and Gemini CLI—delivering zero-hallucination refactoring and dependency tracing.

Graphify (Open Source)Tree-sitterModel Context Protocol (MCP)Claude Code / Cursor / Codex

Best for: Full-stack developers, software architects, open-source maintainers, DevOps engineers, Cursor & Claude Code power users

Full guide ↗

CODE · Coding & Dev

15 MIN

Deploy a Free Global Serverless API or Micro-App in 15 Minutes with Cursor + Cloudflare Workers

Skip buying VPS instances for small APIs, webhooks or shorteners. Use Cursor to write a Hono + Cloudflare Workers app backed by free D1 SQLite and deploy globally in one command.

Cloudflare Workers & D1Hono FrameworkCursor

Best for: Indie hackers, frontend developers, automation builders

Full guide ↗

CODE · Coding & Dev

15 MIN

Build a 100% Offline, Free Coding Assistant in VS Code with Continue + Ollama

Working in an air-gapped enterprise or tired of monthly subscriptions? Run `Qwen2.5-Coder` locally via Ollama and connect the open-source Continue extension in VS Code for fast offline autocomplete and chat.

Continue (Open-Source Extension)OllamaQwen2.5-Coder

Best for: Enterprise developers, embedded engineers, students, indie hackers

Full guide ↗

CODE · Coding & Dev

20 MIN

Record Browser Clicks with Playwright Codegen & Let AI Turn Them into Resilient E2E Tests

Run `npx playwright codegen` to record your manual clicks into raw script, then have an LLM refactor it into clean Page Object tests with resilient assertions and failure screenshots.

Playwright Codegen (Open Source)Cursor / Claude

Best for: Frontend developers, QA engineers, indie hackers

Full guide ↗