coderabbit-review
Evaluate CodeRabbit PR comments and fix or reply
Skill by jeremyeder
Chalk Labs
Need help deploying coderabbit-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jeremyeder-coderabbit-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/coderabbit-review
Tools it pre-approves 16
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(ghprview:*)repoBash(gitremote:*)branch:*)list:*)api:*)Bash(curl:*)Bash(sha256sum:*)Read
Show 4 more
GlobGrepEditAskUserQuestion
What's inside
- Skill name
coderabbit-review- Description
- Evaluate CodeRabbit PR comments and fix or reply
- License
- Apache-2.0
- Compatibility
- Requires gh CLI.
- Allowed tools
- Bash(gh, pr, view:*), Bash(gh, repo, view:*), Bash(git, remote:*), Bash(git, branch:*), Bash(gh, pr, list:*), Bash(gh, api:*), Bash(curl:*), Bash(sha256sum:*), Read, Glob, Grep, Edit, AskUserQuestion
- Instructions
- 198 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
- Instructions call the network
Files (1)
- SKILL.md
SKILL.md (first lines)
# CodeRabbit PR Review Handler Fetch CodeRabbit comments from a GitHub PR, evaluate each one, and take action: apply a code fix or post a reply. **PR:** $ARGUMENTS ## Step 1: Resolve the PR and Repository If `$ARGUMENTS` is provided, use it as the PR number. Get the upstream repo: ```bash gh repo view --json owner,name ``` Store: `owner`, `repo`, `pullNumber`. If `$ARGUMENTS` is empty, detect the PR from the current branch. PRs are often opened from a fork, so `gh pr view` against the upstream may fail. Use this sequence: 1. Get the upstream owner/repo: ```bash gh repo view --json owner,name ``` 2. Try to find the PR on the upstream first: ```bash gh pr view --repo <owner>/<repo> --json number,url,headRefName,baseRefName,title ``` 3. If that fails (exit code non-zero or "no pull requests found"), get the current branch name and list all open PRs, matching by `headRefName` and `headRepositoryOwner`. The `--head fork-user:branch` filter is unreliable with `gh pr list` (returns empty even when the PR exists): ```bash branch=$(git branch --show-current) gh pr list --repo <owner>/<repo> --state open --json number,title,headRefName,headRepositoryOwner --limit 50 ``` Then match the entry where `headRefName == <branch>` AND `headRepositoryOwner.login` matches the expected fork owner. If multiple matches remain, stop and ask the user to pick the PR number explicitly. 4. If still not found (no matching headRefName), ask the user to identify the PR number: ```bash gh pr list --repo <owner>/<repo> --state open --json number,title,headRefName,headRepositoryOwner --limit 20 ``` Store: `owner`, `repo`, `pullNumber`. ## Step 2: Fetch CodeRabbit Comments **Inline review comments** (CodeRabbit's line-level suggestions): ```bash gh api --paginate repos/<owner>/<repo>/pulls/<pullNumber>/comments ``` **PR-level comments** (CodeRabbit's summary/walkthrough): ```bash gh api --paginate repos/<owner>/<repo>/issues/<pullNumber>/comments ``` Filter both lists to only comments where `user.login` equals `coderabbitai[bot]`. For PR-level comments, skip any comment whose body contains `<!-- walkthrough_start -->` or `<!-- This is an auto-generated comment: review in progress` — these are CodeRabbit's walkthrough/summary posts, not actionable review feedback. For inline comments, skip any comment that belongs to a resolved review thread (check the `pull_request_review_id` against resolved threads, or look for the `"resolved": true` marker if available). If no actionable CodeRabbit comments are found, report that and exit. ## Step 3: Evaluate Each Comment For each CodeRabbit comment, analyze it carefully by reading the relevant source file(s). For inline comments: use the `path` field to read the file with the Read tool. Use `line` or `original_line` to find the exact code location. The `diff_hunk` field shows the surrounding context. Evaluate: 1. **Category**: classify as one of: - `bug` — actual code defect or logic error - `security` — security vulnerability - `performance` — inefficiency or resource issue - `style` — formatting, naming, readability - `docs` — missing or incorrect documentation/comments - `nitpick` — minor preference, not a real issue - `question` — CodeRabbit is asking for clarification 2. **Validity**: does the comment point to a real issue? - `valid` — yes, should be addressed - `debatable` — reasonable disagreement exists - `invalid` — the code is correct and CodeRabbit is wrong 3. **Recommended action**: - `fix` — the code should be changed; generate the fix - `reply` — explain why the code is correct, or acknowledge and defer - `dismiss` — noise; briefly acknowledge and move on ## Step 4: Present Summary and Batch Decision Show a summary table first: # CodeRabbit Comments on PR #<N> | # | File | Line | Category | Validity | Recommended Action | Summary | |---|------|------|----------|----------|--------------------|---------| | 1 | src/foo.ts | 42 | bug | valid | fix | "Variable x may be undefined" | | 2 | src/bar.ts | 10 | nitpick | debatable | reply | "Consider using const here" | Then show the full evaluation for each comment (bugs and security first, then performance, then others): --- ## Comment #N — [Category] — [File:Line or PR-level] **CodeRabbit says:** > [exact quote] **Context** (relevant code snippet): ```text [code from the file at that location] ``` **Assessment:** [Your evaluation: why valid/invalid, what the actual issue is] **Proposed action:** `fix` | `reply` | `dismiss` [If `fix`: show the exact code diff to apply]
From jeremyeder/ai-helpers-plugin, Apache-2.0.
More from jeremyeder/ai-helpers-plugin
- 0.414score
jira-activity
jeremyeder
Summarize Jira ticket activity, including child tickets, to detect stale tickets in the backlog.
SkillDFreshness: DClaude Code +9 - 0.414score
gitlab-pipeline-debugger
jeremyeder
Debug and monitor GitLab CI/CD pipelines for merge requests.
SkillDFreshness: DClaude Code +9 - 0.414score
python-full-deps
jeremyeder
Resolve the full install-time dependency tree for a Python package.
SkillDFreshness: DClaude Code +9 - 0.411score
python-packaging-license-finder
jeremyeder
Deterministically find license information for Python packages by checking PyPI metadata first, then falling back to Git repository LICENSE files using…
SkillDFreshness: DClaude Code - 0.411score
python-packaging-env-finder
jeremyeder
Investigate environment variables that can be set when building Python wheels for a given project.
SkillDFreshness: DClaude Code +9 - 0.411score
jira-upload-chat-log
jeremyeder
Export and upload the current chat conversation as a markdown file attachment to a JIRA ticket for later review and documentation.
SkillDFreshness: DClaude Code +9 - 0.411score
python-packaging-source-finder
jeremyeder
Locate source code repositories for Python packages by analyzing PyPI metadata, project URLs, and code hosting platforms like GitHub, GitLab, and Bitbucket.
SkillDFreshness: DClaude Code - 0.411score
python-packaging-complexity
jeremyeder
Analyze Python package build complexity by inspecting PyPI metadata.
SkillDFreshness: DClaude Code +9 - 0.409score
ai-bug-fix-triage
jeremyeder
Triage JIRA bugs against repository code to classify AI fixability.
SkillDFreshness: DClaude Code +9 - 0.409score
jira-aipcc-create
jeremyeder
Create Jira issues in the AIPCC project.
SkillDFreshness: DClaude Code +9 - 0.409score
torchtalk-analyzer
jeremyeder
Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server.
SkillDFreshness: DClaude Code +9 - 0.408score
vllm-slack-summary
jeremyeder
Generate slack summaries of vLLM CI SIG Slack channel activity for the RHAIIS midstream release team
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 30, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/jeremyeder/ai-helpers-plugin
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jeremyeder
- 0.414score
jira-activity
jeremyeder
Summarize Jira ticket activity, including child tickets, to detect stale tickets in the backlog.
SkillDFreshness: DClaude Code +9 - 0.414score
gitlab-pipeline-debugger
jeremyeder
Debug and monitor GitLab CI/CD pipelines for merge requests.
SkillDFreshness: DClaude Code +9 - 0.414score
python-full-deps
jeremyeder
Resolve the full install-time dependency tree for a Python package.
SkillDFreshness: DClaude Code +9 - 0.411score
python-packaging-complexity
jeremyeder
Analyze Python package build complexity by inspecting PyPI metadata.
SkillDFreshness: DClaude Code +9 - 0.411score
jira-upload-chat-log
jeremyeder
Export and upload the current chat conversation as a markdown file attachment to a JIRA ticket for later review and documentation.
SkillDFreshness: DClaude Code +9 - 0.411score
python-packaging-env-finder
jeremyeder
Investigate environment variables that can be set when building Python wheels for a given project.
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get coderabbit-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
coderabbit-review skill. Agent Mart. https://agentmart.dev/skills/jeremyeder-coderabbit-review (last updated 2026-10-24)