Pr Review logo

Pr Review

Organization
WellApp-ai
pr-review

Automated code review using ReadLints and Shell for technical validation

Overview

PublisherWellApp-ai
RepositoryWell
Skill namepr-review
Stars
342
Forks
48
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by WellApp-ai on GitHub. Read the source before you install it.

Installation

Install the Pr Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/WellApp-ai/Well.git /tmp/Well
mkdir -p .claude/skills
cp -r /tmp/Well/cursor-rules/skills/pr-review .claude/skills/pr-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pr Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pr Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pr Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PR Review Skill

Automated technical validation before commits. Uses ReadLints for lint/type errors and Shell for running validation commands.

When to Use

  • Before every commit (invoked by commit.mdc)
  • Before pushing PR (invoked by push-pr.mdc Phase 1)
  • Manually with "use pr-review skill"

Phase 0: Runtime Check (Auto-Resolve)

Verify development environment is ready. Auto-resolve safe issues, prompt for risky ones.

0.1 Dependencies Check

Check if dependencies are fresh:

bash
# Check if node_modules exists
ls -d node_modules 2>/dev/null

# Check if package-lock.json is newer than node_modules
find package-lock.json -newer node_modules 2>/dev/null

If node_modules missing or stale (auto-resolve):

bash
npm install

Wait for install to complete before proceeding.

0.2 Docker Containers

Check if required containers are running:

bash
docker ps --filter name=well_ --format "{{.Names}}: {{.Status}}"

Expected: well_postgres and well_hasura running

If not running (auto-resolve):

bash
cd apps/api/docker && docker compose up -d

Wait up to 30 seconds for containers to be healthy.

0.3 Database Migrations

Check for pending migrations:

bash
cd apps/api && npm run mikro:up -- --dry-run 2>&1 | head -5

If migrations pending (WARN - do NOT auto-run):

Database migrations may be pending.

Run manually if needed: cd apps/api && npm run mikro:up

Continue without running migrations? (y/n)

Wait for user confirmation before proceeding.

0.4 API Server (port 8080)

bash
curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health --max-time 5

Expected: HTTP 200

If not responding:

  1. Check if process exists: lsof -i :8080
  2. If NO process, prompt user to start:
    API server not running on port 8080.
    
    Start with: npm run dev (in apps/api)
  3. If process EXISTS but unresponsive, ASK user:
    API server on port 8080 is unresponsive (process exists but not responding).
    
    Options:
    A) Kill process and restart (recommended)
    B) Skip and continue anyway
    C) Abort commit
    
    Reply with A, B, or C.
  4. If user chooses A:
    bash
    lsof -ti :8080 | xargs kill -9 2>/dev/null
    Then prompt user to restart: cd apps/api && npm run dev

0.5 Web Server (port 3000)

bash
curl -s -o /dev/null -w "%{http_code}" http://localhost:3000 --max-time 5

Expected: HTTP 200

If not responding:

  1. Check if process exists: lsof -i :3000
  2. If NO process, prompt user to start:
    Web server not running on port 3000.
    
    Start with: npm run dev (in apps/web)
  3. If process EXISTS but unresponsive, ASK user:
    Web server on port 3000 is unresponsive (process exists but not responding).
    
    Options:
    A) Kill process and restart (recommended)
    B) Skip and continue anyway
    C) Abort commit
    
    Reply with A, B, or C.
  4. If user chooses A:
    bash
    lsof -ti :3000 | xargs kill -9 2>/dev/null
    Then prompt user to restart: cd apps/web && npm run dev

0.6 Build Cache (on error only)

If typecheck passes but runtime errors occur (module not found, stale code):

bash
npm run clean

Then prompt user to restart dev servers.

0.7 Runtime Check Output

markdown
### Runtime Environment

| Service | Status | Action |
|---------|--------|--------|
| Dependencies | FRESH/STALE | [installed/skipped] |
| Docker (postgres) | UP/DOWN | [started/already running] |
| Docker (hasura) | UP/DOWN | [started/already running] |
| Migrations | CURRENT/PENDING | [warning shown/current] |
| API Server (8080) | UP/DOWN/STALE | [running/started/killed/skipped] |
| Web Server (3000) | UP/DOWN/STALE | [running/started/killed/skipped] |

**Runtime:** [READY / WAITING - user action needed]

If any service requires manual action, wait for user confirmation before proceeding.

Phase 1: Technical Validation

1.1 Type Check

bash
npm run typecheck

Expected: Exit code 0, no errors

1.2 Lint Check

bash
npm run lint

Expected: Exit code 0, no errors

1.3 ReadLints Integration

Use Cursor's ReadLints tool on changed files:

ReadLints:
  paths: [list of changed files]

Categorize results:

SeverityAction
ErrorBLOCK - must fix before commit
WarningWARN - should fix, can proceed
InfoPASS - informational only

Phase 2: Code Quality Checks

2.1 Console.log Detection

Search changed files for debug statements:

Grep:
  pattern: "console\.(log|debug|warn|error)"
  path: [changed files]

If found: WARN - remove before commit

2.2 TODO/FIXME Detection

Grep:
  pattern: "(TODO|FIXME|HACK|XXX):"
  path: [changed files]

If found: INFO - document or address

2.3 Hardcoded Values

Grep:
  pattern: "(localhost|127\.0\.0\.1|hardcoded)"
  path: [changed files]

If found: WARN - use environment variables

Phase 3: Risk Assessment

Calculate risk score based on:

FactorWeightCriteria
Lines Changed1-3<50=1, 50-200=2, >200=3
Files Changed1-3<5=1, 5-10=2, >10=3
New Dependencies0-2None=0, 1=1, >1=2
API Changes0-2None=0, Internal=1, Public=2
Database Changes0-2None=0, Field=1, Entity=2

Risk Levels:

  • LOW (0-4): Standard review
  • MEDIUM (5-8): Careful review
  • HIGH (9+): Thorough review recommended

Output Format

markdown
## PR Review Report

### Runtime Environment

| Service | Status | Action |
|---------|--------|--------|
| Dependencies | FRESH/STALE | [installed/skipped] |
| Docker (postgres) | UP/DOWN | [started/already running] |
| Docker (hasura) | UP/DOWN | [started/already running] |
| Migrations | CURRENT/PENDING | [warning shown/current] |
| API Server (8080) | UP/DOWN/STALE | [running/killed/skipped] |
| Web Server (3000) | UP/DOWN/STALE | [running/killed/skipped] |

**Runtime:** [READY / WAITING]

### Technical Validation

| Check | Status | Details |
|-------|--------|---------|
| TypeCheck | PASS/FAIL | [error count or "clean"] |
| Lint | PASS/FAIL | [error count or "clean"] |
| ReadLints | PASS/WARN/FAIL | [summary] |

### Code Quality

| Check | Status | Count | Files |
|-------|--------|-------|-------|
| console.log | PASS/WARN | [N] | [files] |
| TODO/FIXME | PASS/INFO | [N] | [files] |
| Hardcoded | PASS/WARN | [N] | [files] |

### Risk Assessment

| Factor | Score |
|--------|-------|
| Lines Changed | [N] |
| Files Changed | [N] |
| New Dependencies | [N] |
| API Changes | [N] |
| Database Changes | [N] |
| **Total Risk** | [N] ([LOW/MEDIUM/HIGH]) |

### Verdict

**[PASS / WARN / BLOCK]**

[If BLOCK: List issues that must be fixed]
[If WARN: List issues that should be addressed]
[If PASS: Ready to commit]

Verdict Logic

ConditionVerdict
Runtime WAITING (user action needed)BLOCK
User chose C (Abort) for stale serverBLOCK
Dependencies installedContinue (auto-resolved)
Migrations pendingWARN (can proceed after confirmation)
Server killed by user (chose A)Continue after user restarts
TypeCheck FAIL or Lint FAILBLOCK
ReadLints has ErrorsBLOCK
console.log foundWARN
Risk >= HIGHWARN
All checks passPASS

Integration

This skill is invoked by:

  • commit.mdc - Before each commit
  • push-pr.mdc - Phase 1.1 validation
  • agent.mdc - Part of commit-level workflow

Tools Used

ToolPurpose
ShellRun npm scripts (typecheck, lint)
ReadLintsGet IDE diagnostic errors
GrepSearch for patterns in code
ReadExamine specific file contents

Quick Mode

For rapid iteration, run minimal checks:

markdown
## Quick Review

- [ ] `npm run typecheck` - PASS
- [ ] `npm run lint` - PASS
- [ ] No console.log - PASS

**Verdict:** PASS - Ready to commit

Use full review before PR push; quick mode acceptable for intermediate commits.

Frequently asked questions

What does the Pr Review AI skill do?

Automated code review using ReadLints and Shell for technical validation

Why use Pr Review on TypingMind?

Because you install it once and use it with any model. Pr Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pr Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/pr-review. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pr Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pr Review?

As many as you like. As long as a model supports skills, you can use Pr Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pr Review AI skill free?

Yes. It is published on GitHub by WellApp-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇