aaronfloreyaaronflorey/agent-skills/skills/qodo-merge/SKILL.md

qodo-merge

Skill2 starsChanged 7 months agoMITView on GitHub

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.

In this repository26 other files it gives its agents.
- other/AGENTS.mdAGENTS.md
- beamng-modsSkill
- bootstrap-vueSkill
- charmbraceletSkill
- depsdotdevSkill
- find-domainSkill
- github-cliSkill
- go-cobraSkill
- goreleaserSkill
- go-viperSkill
- kasettoSkill
- laravel-actionsSkill
- lefthookSkill
- miseSkill
- pelican-panel-pluginsSkill
- php-monorepo-builderSkill
- php-saloonSkill
- prd-todo-slicerSkill
- prd-to-kandev-tasksSkill
- release-pleaseSkill
- rewrite-in-goSkill
- shieldsioSkill
- skill-researcherSkill
- skill-scoutSkill
- taskfileSkill
- website-visual-testingSkill

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Use this skill to install, configure, and troubleshoot Qodo Merge / PR-Agent without pulling large chunks of product docs into the active …
line 11
Very specific:
Prefer repo-local .pr_agent.toml for stable settings and env vars only for secrets or one-off overrides.
line 17
Distinctive:
Read only the reference file that matches the task instead of loading everything.
line 18
Distinctive:
Use description markers when the user wants generated PR bodies to fit a repo template cleanly.
line 40
Distinctive:
Keep answers implementation-focused: pick the right platform path, show the minimal config, and explain only the options that matter to the …
line 64
Distinctive:
Avoid dumping long examples from docs unless the user needs a ready-to-paste workflow or config block.
line 65
Distinctive:
Treat https://qodo-merge-docs.qodo.ai/ as the source of truth for exact option names and current behavior.
line 66

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Qodo Merge

Use this skill to install, configure, and troubleshoot Qodo Merge / PR-Agent without pulling large chunks of product docs into the active context.

Start here

Identify the platform: GitHub Action/App, GitLab, Bitbucket, Azure DevOps, Docker, AWS Lambda, or self-hosted.
Identify the job: install, configure, use a tool command, switch models, or debug a failure.
Prefer repo-local .pr_agent.toml for stable settings and env vars only for secrets or one-off overrides.
Read only the reference file that matches the task instead of loading everything.

Core commands

Command	Use it for
`/describe`	Generate PR title, summary, walkthrough, labels, and optional diagram
`/review`	Review the PR for quality, correctness, security, and ticket alignment
`/improve`	Generate inline code suggestions and rank them by confidence
`/ask "..."`	Ask questions about the diff, files, or intent of the PR
`/add_docs`	Add missing docs for changed code
`/generate_labels`	Infer labels from PR content
`/help_docs "..."`	Answer repo questions from project documentation

High-value rules

Config precedence is: CLI args -> env vars -> .pr_agent.toml -> defaults.
For env var overrides, config keys map with double underscores, for example PR_REVIEWER__REQUIRE_TESTS_REVIEW=false.
AWS Lambda env vars cannot contain .; use __ instead.
Non-OpenAI providers use their own API keys. Do not require OPENAI_KEY for Claude, Gemini, or similar providers.
suggestions_score_threshold controls how aggressive /improve is; raise it to reduce low-value suggestions.
allow_dynamic_context = true helps larger diffs by expanding surrounding code context.
Use description markers when the user wants generated PR bodies to fit a repo template cleanly.
Local Ollama setups generally require a self-hosted runner; hosted CI cannot reach local services.

Troubleshooting shortcuts

Symptom	First check
Model not found	Provider-specific model name format
API key missing	Matching secret/env var name for the selected provider
Permission denied	PR, issue, and contents write permissions in the integration
Bad JSON in provider config	`litellm.extra_body` formatting
Weak context on large PRs	Dynamic context and patch sizing settings

Routing guide

Installation and platform-specific setup: references/installation.md
Tool behavior and per-tool config: references/tools.md
.pr_agent.toml, CLI flags, env vars, model wiring: references/usage-guide.md
Self-reflection, compression, dynamic context, metadata: references/core-abilities.md
Product overview, FAQ, and miscellaneous details: references/other.md
Mirrored documentation index: references/documentation/index.md

Working style

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.
Avoid dumping long examples from docs unless the user needs a ready-to-paste workflow or config block.
Treat https://qodo-merge-docs.qodo.ai/ as the source of truth for exact option names and current behavior.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free