coderabbit-core-workflow-a
Configures automated PR reviews and feedback loops using CodeRabbit's core workflow.
Install
mkdir -p .claude/skills/coderabbit-core-workflow-a && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5445" && unzip -o skill.zip -d .claude/skills/coderabbit-core-workflow-a && rm skill.zipInstalls to .claude/skills/coderabbit-core-workflow-a
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Execute CodeRabbit primary workflow: automated PR code review with configuration.Key capabilities
- →Configure review profiles for automated PR analysis
- →Generate walkthrough summaries and line-level comments
- →Enable or disable auto-review for draft PRs
- →Trigger specific commands like 'full review' or 'generate-docstrings'
- →Configure finishing touch recipes for automated code improvements
How it works
CodeRabbit analyzes the diff of a pull request based on the `.coderabbit.yaml` configuration, then posts a walkthrough summary and line-level comments. Developers address feedback, and CodeRabbit performs incremental re-reviews on new commits.
Inputs & outputs
When to use coderabbit-core-workflow-a
- →Setting up automated PR reviews
- →Configuring review feedback profiles
- →Establishing PR review workflows
- →Managing CodeRabbit review status
About this skill
CodeRabbit Pull Request Review
Overview
Operate one evidence-backed review cycle. Separate walkthroughs, inline findings, incremental review, full review, CI, and human merge ownership.
Prerequisites
- Identify the CodeRabbit organization, Git provider, repository, plan, and accountable owner.
- Read
references/official-docs.mdand re-check any time-sensitive contract before execution. - Use synthetic or read-only evidence until the approval boundary is satisfied.
- Preserve the repository's independent CI, security, and human-review requirements.
Current Contract
- Eligible pull requests are reviewed automatically unless configuration excludes them.
- The walkthrough is separate from inline findings.
- Incremental and full reviews are distinct commands.
- CodeRabbit supplements rather than replaces required CI and human judgment.
Authentication
Treat Git-provider sessions, CodeRabbit web sessions, CLI credentials, and CodeRabbit API keys as separate credentials. Use only an already-approved session or secret-manager reference, never print a secret, and do not place credentials in .coderabbit.yaml, source files, logs, or deliverables.
Instructions
-
Verify installation, eligibility, feature-branch config, and independent CI.
-
Group walkthrough and inline findings by severity, file, and evidence.
-
Resolve valid findings in bounded commits and explain declined findings.
-
Request the appropriate documented review and confirm closure before handoff.
Tool Discipline
- Use Glob to locate candidate configuration and evidence files without widening scope.
- Use Grep to find relevant fields, commands, identifiers, and stale claims.
- Use Read to inspect the smallest required files and authoritative evidence.
- Use Write only for a new approved local draft or evidence artifact.
- Use Edit only for a bounded approved change whose rollback is known.
- Do not use these file tools as a substitute for authenticated CodeRabbit or provider operations.
Approval Boundaries
Require human approval before pushing fixes, dismissing security findings, requesting approval, or merging. Keep analysis and drafts local until approval is explicit, and record who approved the action and its scope.
Output
A finding ledger with evidence, dispositions, commits, residual risk, and merge recommendation. Include source dates, unknowns, and the exact boundary between observed fact and recommendation.
Error Handling
| Condition | Response |
|---|---|
| Current contract is unclear or docs disagree | Stop mutation, cite both sources, and request owner resolution. |
| Required access or approval is missing | Produce a draft and evidence plan only. |
| Validation or pilot behavior differs from expectation | Restore the prior state and retain the failed evidence. |
| Output contains secrets or private code | Stop, quarantine the artifact, redact it, and notify the data owner. |
Examples
Example 1
Process an incremental review after a narrow bug fix.
Example 2
Decline a false positive with repository evidence retained in the PR thread.
Validation
- Confirm every claim against the dated sources in
references/official-docs.md. - Verify the requested scope, owner, approval, happy path, failure path, and rollback.
- Re-read the effective configuration or provider state after any approved change.
- Report unsupported fields, undocumented endpoints, and unverified assumptions as failures.
Resources
- Official documentation and contract notes
- Re-check the dated contract before any live operation.
- Treat unresolved or changed vendor behavior as a stop condition.
When not to use it
- →When the PR targets a non-configured branch
- →When the `.coderabbit.yaml` file has a syntax error
- →When the PR has over 1000 changed lines and a quick review is needed
Prerequisites
Limitations
- →Reviews may take up to 15 minutes for PRs with over 1000 changed lines
- →Reviews are not posted if the PR targets a non-configured branch
- →Generated files may be reviewed if `path_filters` are missing
How it compares
This workflow automates code review and feedback generation directly within pull requests, unlike manual review processes that require human intervention for initial analysis and comment generation.
Compared to similar skills
coderabbit-core-workflow-a side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| coderabbit-core-workflow-a (this skill) | 1 | 2mo | Review | Intermediate |
| resolve-conflicts | 81 | 10mo | Review | Intermediate |
| claude-automation-recommender | 47 | 4mo | Review | Beginner |
| codex-skill | 12 | 6mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
resolve-conflicts
antinomyhq
Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.
claude-automation-recommender
anthropics
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
codex-skill
feiskyer
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.
git-advanced-workflows
wshobson
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
subagent-driven-development
davila7
Use when executing implementation plans with independent tasks in the current session
validate-openapi-specs
epieczko
Validates and registers hook manifest files (YAML) in the Hook Registry for versioned hook management.