1---2name: qodo-merge3description: Configure and use Qodo Merge, formerly PR-Agent, for AI-powered pull request reviews, descriptions, inline suggestions, labels, docs, and ticket checks across GitHub, GitLab, Bitbucket, and Azure DevOps. Use this skill whenever the user mentions Qodo Merge, PR-Agent, `.pr_agent.toml`, `pr_agent`, PR review bots, `/describe`, `/review`, `/improve`, GitHub App or Action setup, model configuration, or debugging PR-Agent automation.4license: MIT5---67# Qodo Merge89Use this skill to install, configure, and troubleshoot Qodo Merge / PR-Agent without pulling large chunks of product docs into the active context.1011## Start here12131. Identify the platform: GitHub Action/App, GitLab, Bitbucket, Azure DevOps, Docker, AWS Lambda, or self-hosted.142. Identify the job: install, configure, use a tool command, switch models, or debug a failure.153. Prefer repo-local `.pr_agent.toml` for stable settings and env vars only for secrets or one-off overrides.164. Read only the reference file that matches the task instead of loading everything.1718## Core commands1920| Command | Use it for |21|---|---|22| `/describe` | Generate PR title, summary, walkthrough, labels, and optional diagram |23| `/review` | Review the PR for quality, correctness, security, and ticket alignment |24| `/improve` | Generate inline code suggestions and rank them by confidence |25| `/ask "..."` | Ask questions about the diff, files, or intent of the PR |26| `/add_docs` | Add missing docs for changed code |27| `/generate_labels` | Infer labels from PR content |28| `/help_docs "..."` | Answer repo questions from project documentation |2930## High-value rules3132- Config precedence is: CLI args -> env vars -> `.pr_agent.toml` -> defaults.33- For env var overrides, config keys map with double underscores, for example `PR_REVIEWER__REQUIRE_TESTS_REVIEW=false`.34- AWS Lambda env vars cannot contain `.`; use `__` instead.35- Non-OpenAI providers use their own API keys. Do not require `OPENAI_KEY` for Claude, Gemini, or similar providers.36- `suggestions_score_threshold` controls how aggressive `/improve` is; raise it to reduce low-value suggestions.37- `allow_dynamic_context = true` helps larger diffs by expanding surrounding code context.38- Use description markers when the user wants generated PR bodies to fit a repo template cleanly.39- Local Ollama setups generally require a self-hosted runner; hosted CI cannot reach local services.4041## Troubleshooting shortcuts4243| Symptom | First check |44|---|---|45| Model not found | Provider-specific model name format |46| API key missing | Matching secret/env var name for the selected provider |47| Permission denied | PR, issue, and contents write permissions in the integration |48| Bad JSON in provider config | `litellm.extra_body` formatting |49| Weak context on large PRs | Dynamic context and patch sizing settings |5051## Routing guide5253- Installation and platform-specific setup: `references/installation.md`54- Tool behavior and per-tool config: `references/tools.md`55- `.pr_agent.toml`, CLI flags, env vars, model wiring: `references/usage-guide.md`56- Self-reflection, compression, dynamic context, metadata: `references/core-abilities.md`57- Product overview, FAQ, and miscellaneous details: `references/other.md`58- Mirrored documentation index: `references/documentation/index.md`5960## Working style6162- Keep answers implementation-focused: pick the right platform path, show the minimal config, and explain only the options that matter to the user's case.63- Avoid dumping long examples from docs unless the user needs a ready-to-paste workflow or config block.64- Treat https://qodo-merge-docs.qodo.ai/ as the source of truth for exact option names and current behavior.
aaronflorey