coderabbit-local-dev-loop
Automates local AI-powered code reviews using the CodeRabbit CLI to catch issues before committing.
Install
mkdir -p .claude/skills/coderabbit-local-dev-loop && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4758" && unzip -o skill.zip -d .claude/skills/coderabbit-local-dev-loop && rm skill.zipInstalls to .claude/skills/coderabbit-local-dev-loop
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.
Configure CodeRabbit CLI for local pre-commit code reviews and fastKey capabilities
- →Perform local AI code reviews
- →Integrate reviews into git hooks
- →Review specific files or staged changes
- →Provide interactive feedback via terminal
- →Configure review path instructions
How it works
The CLI runs AI-powered reviews against local git changes, allowing developers to receive feedback before pushing code. It supports integration into git hooks and VS Code tasks for automated workflows.
Inputs & outputs
When to use coderabbit-local-dev-loop
- →Perform pre-commit reviews on local changes
- →Test CodeRabbit configuration changes
- →Review specific files before pushing
- →Streamline git commit workflows with AI checks
About this skill
CodeRabbit Local Review Loop
Overview
Use the native CLI before push and feed findings back into coding. Keep auth, scope, and spend visible.
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
- The CLI reviews local changes before commit.
coderabbit review --plainis the agent-friendly command.- Interactive and Agentic-key login are distinct.
- CLI allowances and billing follow current plan contracts.
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
-
Confirm repo state, diff scope, auth mode, allowance, and excluded files.
-
Run a bounded plain review and capture findings without secrets.
-
Classify findings, fix approved items, and rerun changed scope.
-
Stop on repeats, scope expansion, auth errors, or usage limits.
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 approval before credits, headless keys, wider review scope, or pushing. Keep analysis and drafts local until approval is explicit, and record who approved the action and its scope.
Output
A receipt with scope, mode, dispositions, changed files, rerun result, and risks. 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
Review staged changes before commit and rerun after a race fix.
Example 2
Use Codex integration with injected secret auth.
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
- →Reviewing files without git staging
- →Replacing full PR-based automated reviews
Prerequisites
Limitations
- →Requires internet access for AI review processing
- →Usage-based billing applies per file reviewed
How it compares
This approach provides immediate AI feedback locally before a commit, whereas standard PR reviews only occur after code is pushed to the remote repository.
Compared to similar skills
coderabbit-local-dev-loop side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| coderabbit-local-dev-loop (this skill) | 1 | 2mo | Review | Intermediate |
| subagent-driven-development | 14 | 9mo | No flags | Advanced |
| swarm-coordination | 0 | 7mo | No flags | Advanced |
| resolve-conflicts | 81 | 10mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
subagent-driven-development
davila7
Use when executing implementation plans with independent tasks in the current session
swarm-coordination
joelhooks
Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination.
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.
agent-factory
alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns