Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    t2s pull request review

    1

    - **Prioritized Checklists** generates a structured review list categorized by HIGH, MEDIUM, and LOW priority items.

    $1.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    t2s pull request review

    t2s pull request review

    Example session with this skill installed

    Please review this PR diff: 500 lines added to auth_service.go, 10 lines changed in readme.md, and no new test files were added.

    • Read your context and instructions
    • Compiled the t2s pull request

    I have analyzed the provided diff data and calculated the risk profile for this pull request.

    Pull Request Review — Development Team, 2024-05-20

    1. Summary

    • PR Risk Score: 85 (CRITICAL)
    • Files Analyzed: 2
    • Total Lines: 510
    • Test Coverage Indicator: 0% (Missing paired tests)

    2. File Analysis

    PathCategoryAdditionsDeletionsRisk ScoreLevel
    auth_service.gologic/security500085CRITICAL
    readme.mddocumentation555LOW

    3. Review Checklist

    • HIGH: Validate all 500 additions in auth_service.go for authentication bypass vulnerabilities.
    • HIGH: Verify why no test files were created or modified for a major logic change.
    • LOW: Ensure readme.md updates accurately reflect the changes in the service.

    4. Test Coverage

    • Source files without paired tests: auth_service.go
    • Source files with paired tests: None

    5. Warnings and Data Quality

    • W001: No test files detected in diff for high-risk logic changes.

    6. Recommendations and Items for Human Review

    The change to auth_service.go is extensive and lacks supporting tests, resulting in a CRITICAL risk score. This requires a deep dive into the logic flow.

    Management decision required

    Next steps

    1. Request unit tests for the new logic in auth_service.go.
    2. Assign a senior security engineer to review the authentication logic.
    3. Confirm if the readme.md changes cover the new service parameters.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Manual pull request reviews often suffer from inconsistent depth or missed edge cases in high-risk files. This skill automates the risk assessment of PR diffs, calculating scores based on change size, file sensitivity, and test coverage indicators to prioritize human attention.

    What it does

    • Risk Scoring calculates individual file and total PR risk levels based on deterministic weightings of additions, deletions, and file types.
    • Diff Analysis parses pull request metadata and file changes to categorize the scope of work.
    • Prioritized Checklists generates a structured review list categorized by HIGH, MEDIUM, and LOW priority items.
    • Coverage Auditing identifies missing test file pairings for modified source files.
    • Decision Support provides a standardized summary to help teams decide if a PR requires senior oversight or immediate merging.

    How it works

    1. The user provides a PR diff or a list of file changes including line counts.
    2. The skill constructs a request.json payload mapped to the change data.
    3. A self-contained Python script processes the input to calculate scores and identify patterns.
    4. The findings are returned in a structured report including a file analysis table and a prioritized checklist.

    Frameworks & tools

    This skill uses a Python-based logic engine to process JSON-formatted diff data. It is platform-agnostic and works with outputs from GitHub, GitLab, Bitbucket, or local Git diffs.

    Why this beats prompting it yourself

    Generic prompts often hallucinate risk or fail to consistently apply weighting logic across large diffs. This skill uses a deterministic calculation script to ensure that a 500-line change in a controller always receives the same risk score, removing subjective bias from the initial triage.

    Use cases

    • Identify high-risk logic changes that require senior dev approval.
    • Detect modified source files that lack corresponding test updates.
    • Generate a standardized review checklist for team leads.
    • Quantify PR complexity to better estimate review time.

    Known limitations

    This skill assesses risk and priority, not code quality or stylistic correctness. It does not perform actual test execution or security vulnerability scanning.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.

    Assessments are based on diff metadata, not code logic or runtime behavior. Does not execute tests or scan for security vulnerabilities. Requires file paths and line counts.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed today

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listedtoday

    What's inside

    Frequently Asked Questions

    The skill uses a deterministic scoring engine that evaluates the size of the diff, the sensitivity of the files modified (e.g., config vs. documentation), and the presence of corresponding test updates to generate a consistent risk profile.

    Yes, the skill is platform-agnostic; as long as you provide the diff data or file change metadata in the required JSON format, it can analyze PRs from GitHub, GitLab, Bitbucket, or local Git environments.

    The skill focuses on 'Risk and Complexity'—it excels at identifying where human reviewers should focus their attention and detecting missing tests, but it does not perform linting, style checks, or active security vulnerability scanning.

    You will receive the core logic engine (Python-based), the schema for the request payload, and documentation on how to integrate the skill into your existing AI agent workflows or CI/CD pipelines.

    Unlike basic prompts that may provide inconsistent feedback, this skill uses a structured Python logic engine to ensure that the same code changes always result in the same risk score and checklist, removing AI hallucination from the triage process.

    New in Code Quality & Review