Code Review Github logo

Code Review Github

Organization
initializ
code-review-github

GitHub PR workflow orchestration for code review — list PRs, post comments, apply labels, and guarded auto-merge

Overview

Publisherinitializ
Repositoryforge
Skill namecode-review-github
Stars
242
Forks
14
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by initializ on GitHub. Read the source before you install it.

Installation

Install the Code Review Github AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/code-review-github
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/initializ/forge.git /tmp/forge
mkdir -p .claude/skills
cp -r /tmp/forge/forge-skills/local/embedded/code-review-github .claude/skills/code-review-github
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code Review Github in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Code Review Github on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Code Review Github is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Code Review GitHub Integration

Orchestrates GitHub PR workflows for AI code review. Provides tools to list pull requests, post inline review comments, apply labels based on review findings, and (with explicit opt-in) auto-merge clean PRs.

All GitHub API interactions go through the gh CLI. Direct HTTP requests and web searches are denied to ensure all operations are auditable and respect GitHub's rate limiting.

Authentication

bash
export GH_TOKEN="ghp_..."

The token needs read-write access since this skill posts comments, applies labels, and can merge PRs:

Scope (classic PAT)Fine-grained permissionWhy
repoPull requests: Read & WriteList PRs, post review comments, merge
repoContents: ReadRead PR diff and file contents
repoIssues: WriteApply and remove labels
read:org (optional)Organization: ReadOrg-level label policies

Minimum fine-grained token permissions: pull_requests: write, contents: read, issues: write on the target repository.

For read-only review without GitHub interaction, use the code-review skill instead — it only needs read access.

Environment Variables

VariableRequiredDescription
GH_TOKENyesGitHub personal access token or fine-grained token
REVIEW_AUTO_MERGEnoSet to true to enable guarded auto-merge. Default: disabled
REVIEW_LABEL_PREFIXnoPrefix for review labels (default: review/). Labels: review/approved, review/needs-changes, review/security-concern

Tool: review_github_list_prs

List open pull requests for a repository, optionally filtered by author or label.

Input:

ParameterTypeRequiredDescription
repostringyesRepository in owner/repo format
authorstringnoFilter by PR author username
labelstringnoFilter by label
limitintegernoMaximum PRs to return (default: 10, max: 100)

Output: JSON array of pull requests with number, title, author, url, labels, created_at, updated_at, mergeable_state.

Detection Heuristics

The agent selects this tool when it detects:

  • Requests to "list PRs", "show open pull requests", "what PRs need review"
  • Requests to find PRs by a specific author or with specific labels

Tool: review_github_post_comments

Post inline review comments on a GitHub pull request based on code review findings.

Input:

ParameterTypeRequiredDescription
repostringyesRepository in owner/repo format
pr_numberintegeryesPull request number
findingsarrayyesArray of findings from code_review_diff output
submit_reviewbooleannoSubmit as a formal review (not just individual comments). Default: true
review_eventstringnoReview event type: COMMENT, APPROVE, REQUEST_CHANGES. Default: COMMENT

Each finding in the array should have: file, line, severity, title, description, suggestion.

Output: JSON object with comments_posted, review_url, and any errors for comments that failed.

Detection Heuristics

The agent selects this tool when it detects:

  • Requests to "post review comments", "comment on the PR", "submit review"
  • After running code_review_diff, user asks to post findings to GitHub

Comment Format

Comments are posted as inline review comments with this format:

**[severity] category: title**

description

💡 **Suggestion:** suggestion

Tool: review_github_apply_labels

Apply review-status labels to a pull request based on review findings.

Input:

ParameterTypeRequiredDescription
repostringyesRepository in owner/repo format
pr_numberintegeryesPull request number
risk_levelstringyesOverall risk level from review: low, medium, high, critical
has_security_findingsbooleannoWhether security issues were found. Default: false

Output: JSON object with labels_applied and labels_removed.

Label Mapping

Risk LevelLabel Applied
lowreview/approved
mediumreview/needs-changes
highreview/needs-changes
criticalreview/security-concern

If has_security_findings is true, review/security-concern is always applied regardless of risk level.

Previous review labels (with the configured prefix) are removed before applying new ones.

Detection Heuristics

The agent selects this tool when it detects:

  • Requests to "label the PR", "apply review labels", "mark PR as approved"
  • After completing a review, user asks to update PR status

Tool: review_github_auto_merge

Merge a pull request after verifying safety conditions. Requires explicit opt-in via REVIEW_AUTO_MERGE=true.

Input:

ParameterTypeRequiredDescription
repostringyesRepository in owner/repo format
pr_numberintegeryesPull request number
merge_methodstringnoMerge method: merge, squash, rebase. Default: squash
require_clean_reviewbooleannoRequire no error-severity findings before merging. Default: true
review_resultobjectnoReview result from code_review_diff to verify cleanliness

Output: JSON object with merged, sha, message, or blocked_reason if merge was prevented.

Detection Heuristics

The agent selects this tool when it detects:

  • Requests to "merge the PR", "auto-merge if clean"
  • Requests to "merge after review passes"

Safety Guards

This tool enforces multiple safety layers:

  1. Env var gate: REVIEW_AUTO_MERGE must be explicitly set to true. If unset or any other value, merge is blocked with a clear message.
  2. Clean review required: By default, the PR must have no error-severity findings. Override with require_clean_review: false.
  3. CI checks: All required status checks must pass (enforced by GitHub's branch protection).
  4. No dismissed reviews: The tool never dismisses existing review requests or approvals.
  5. Merge conflicts: GitHub API rejects merges with conflicts — the tool surfaces this clearly.

Workflow: Full PR Review Cycle

A typical end-to-end review workflow using all three code-review skills:

  1. List PRs → review_github_list_prs to find PRs needing review
  2. Run review → code_review_diff with the PR URL to generate findings
  3. Post comments → review_github_post_comments to post findings as inline comments
  4. Apply labels → review_github_apply_labels to set status labels
  5. Auto-merge (optional) → review_github_auto_merge if review is clean and opt-in is enabled

Safety Constraints

This skill MUST:

  • Never merge without REVIEW_AUTO_MERGE=true explicitly set
  • Never dismiss existing reviews or review requests
  • Never force-push or modify PR branch contents
  • Never delete branches (leave that to GitHub's auto-delete setting)
  • Never bypass branch protection rules
  • Never approve its own PRs (if the token belongs to the PR author)
  • Post comments as the authenticated user — never impersonate
  • All GitHub operations go through gh CLI — http_request and web_search tools are denied
  • Rate-limit awareness: back off on 403/429 responses from GitHub API

Autonomous Compatibility

This skill is designed to work in automated pipelines:

  • All inputs and outputs are structured JSON
  • Error states return JSON with error field and descriptive messages
  • Idempotent: re-running label application or comment posting produces consistent results
  • Labels are prefix-scoped to avoid conflicting with other label systems

Frequently asked questions

What does the Code Review Github AI skill do?

GitHub PR workflow orchestration for code review — list PRs, post comments, apply labels, and guarded auto-merge

Why use Code Review Github on TypingMind?

Because you install it once and use it with any model. Code Review Github is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Code Review Github in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/code-review-github. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Code Review Github?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Code Review Github?

As many as you like. As long as a model supports skills, you can use Code Review Github with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Code Review Github AI skill free?

Yes. It is published on GitHub by initializ under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇