michaelfu1998-create/PR Code Review
LLM‑powered PR reviews with static analysis, multi‑language support, personas, and learning‑oriented scoring.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Activelast commit May 2, 2026
- License
- MIT
Pinned Snippet
uses: michaelfu1998-create/pr-review-assistant@ead2ee5bc2fcc9f5ebbd70e317639d7c1d7aceec # v1.1.2tags can be moved; commit SHAs can't. why a SHA?
Inputs
| name | description | required | default |
|---|---|---|---|
| openai_api_key | OpenAI API Key (or Anthropic key if using llm_provider: anthropic) | yes | — |
| github_token | GitHub API Token with PR read/write permissions | yes | — |
| github_pr_id | GitHub PR number to review | yes | — |
| openai_model | LLM model name (e.g., gpt-5.4-mini-2026-03-17, gpt-5-nano, claude-sonnet-4-6) | no | gpt-5.4-mini-2026-03-17 |
| openai_temperature | Sampling temperature [0, 1]. Higher values = more creative reviews. | no | 1 |
| openai_max_tokens | Maximum tokens in the LLM response. | no | 32000 |
| llm_provider | LLM provider: openai, anthropic, or openai (with api_base_url for compatible APIs) | no | openai |
| api_base_url | Custom API base URL for OpenAI-compatible APIs (Ollama, vLLM, Azure, etc.) | no | "" |
| anthropic_api_key | Anthropic API Key (required when llm_provider is 'anthropic') | no | "" |
| files | Comma-separated glob patterns for files to review (e.g., '*.py,src/*.ts') | no | * |
| max_files | Maximum number of files to review per PR | no | 10 |
| tools | Tools to run: 'auto' (detect from tech stack), 'none' (LLM only), or comma-separated list (e.g., 'semgrep,ruff,eslint') | no | auto |
| severity_threshold | Minimum severity to report from tools: critical, high, medium, low, info | no | low |
| review_focus | Review focus areas: security, quality, performance, education, all | no | all |
| review_persona | Review style: normal (balanced), mentor (educational), security-auditor. All personas share the same standardized 8-category defect checklist; the persona only changes tone and emphasis. | no | normal |
| custom_instructions | Additional instructions for the LLM reviewer (e.g., 'We use Django REST Framework') | no | "" |
| enable_scoring | Enable educational scoring rubric (true/false). Adds a 0-25 score to each review. | no | false |
| logging | Log level: debug, info, warning, error | no | warning |
Outputs
no outputs