Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Pull Request Analysis Automation · lloydchang | DecimalAI

code reviewby lloydchang

Pull Request Analysis Automation

lloydchang/pr-analysis

Source lloydchang/agentic-reconciliation-engine ↗License AGPL-3.0

Analyzes GitHub pull requests for code quality, security vulnerabilities, performance implications, and best practices. Provides automated code review insights and recommendations.

SkillScore82Maintained

Automatic

QA & Test Engineering pack

Last verified 8/4/2026

What it changes

Passed 18 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill82%

Checks it passed that the model alone missed

Skills list includes pr-analysis
Repository parameter input is octocat/hello-world
Security rating inside metrics uses the security_score key

and 13 more in the full report

10 fixed8 passed either way2 still failing2 broke

Pass-rate lift: +36 pp
Tokens: -9%
Agent turns: 0%
Response time: -46%

Model gemini-3.6-flashMeasured 8/4/2026v118 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/lloydchang-pr-analysis/SKILL.md https://app.decimal.ai/s/lloydchang-pr-analysis/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add lloydchang-pr-analysis, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/lloydchang-pr-analysis/ and pins it in .decimal/skills.lock

decimalai skills add lloydchang-pr-analysis

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/lloydchang-pr-analysis/SKILL.md https://app.decimal.ai/s/lloydchang-pr-analysis/SKILL.md

Raw file: /s/lloydchang-pr-analysis/SKILL.md ↗ · machine-readable summary at /s/lloydchang-pr-analysis.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

List all three supported depth levels for the `ANALYSIS_DEPTH` environment variable when configuring PR review depth.

What was checked, without and with the skill
Checked	Without skill	With skill
Supported depth values are Basic, standard, and comprehensive	Missed	Passed

case-07 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md89 linessingle file

Pull Request Analysis Automation

This skill automates the analysis of GitHub pull requests, providing comprehensive code review insights including:

Analysis Capabilities

1. Code Quality Assessment

Complexity Analysis: Identifies overly complex functions and classes
Code Smells: Detects common anti-patterns and poor practices
Readability Metrics: Assesses code clarity and maintainability
Best Practices: Validates adherence to coding standards

2. Security Review

Vulnerability Detection: Scans for known security vulnerabilities
Input Validation: Checks for proper sanitization of user inputs
Authentication/Authorization: Reviews access control implementations
Data Exposure: Identifies potential data leakage points

3. Performance Impact

Algorithm Complexity: Analyzes time/space complexity changes
Resource Usage: Evaluates memory and CPU usage implications
Database Queries: Reviews query efficiency and optimization
Caching Strategy: Assesses caching implementations

4. Architectural Impact

Dependency Changes: Evaluates impact of new dependencies
API Changes: Reviews breaking changes to public interfaces
Data Model Changes: Assesses database schema modifications
System Integration: Evaluates integration points and coupling

Integration Points

GitHub Webhooks: Automatically triggered on PR creation/updates
CI/CD Pipeline: Integrated into existing build workflows
Temporal Orchestration: Durable execution for long-running analyses
Dashboard Integration: Results displayed in PR comments and dashboards

Usage

Track record

Benchmark

18 / 22

test cases passed, vs 10 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

lloydchang / agentic-reconciliation-engine

core/ai/skills/pr-analysis/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 8/1/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Pull Request Analysis Automation

Analysis Capabilities

1. Code Quality Assessment

2. Security Review

3. Performance Impact

4. Architectural Impact

Integration Points

Usage

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills