Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Developer Workflow Skill Pack

    1

    Four practical AI-agent skills for pull-request reviews, repository-verified READMEs, Conventional Commit messages, release notes, and SEO content briefs.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Developer Workflow Skill Pack

    Developer Workflow Skill Pack

    Example session with this skill installed

    Review the sample pull request diff for security and correctness. Report only issues supported by file and line evidence, rank findings by severity, suggest practical fixes, and provide a clear merge verdict.

    • Read your context and instructions
    • Compiled the developer workflow

    Pull Request Security Review

    Summary

    The changes introduce user search functionality, a user deletion helper and a DELETE API endpoint.

    Two security issues were identified in the supplied diff.

    Verdict: Request Changes

    Critical findings

    1. SQL Injection

    Location: app/users.py:13

    Problem: The search function concatenates user input directly into an SQL query.

    This can allow malicious input to alter the query.

    Recommended fix:

    query = "SELECT id, email FROM users WHERE name LIKE ?"
    rows = db.execute(query, (f"%{name}%",)).fetchall()
    

    2. Missing Authorization

    Location: app/routes.py and app/users.py

    Problem: The DELETE endpoint passes None as the current user. The deletion function does not verify authorization.

    An unauthenticated request could therefore delete user accounts.

    Recommended fix:

    Require an authenticated user, verify permissions and ensure that only authorized users can delete accounts.

    Major findings

    Missing tests

    No tests were added for the new functionality.

    Recommended tests

    • Search with malicious SQL characters.
    • Delete as an unauthenticated user.
    • Delete another user's account without authorization.
    • Delete an authorized user's own account.

    Minor findings

    • Audit logs should identify the user performing a deletion.
    • The deletion function should verify whether a database record was actually removed.

    Final recommendation

    Do not merge this pull request until the SQL injection and authorization issues have been addressed.

    After implementing the fixes, add the recommended tests and run the complete test suite.

    Review status: Changes required before production merge.

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

    About this skill

    Developer Workflow Skill Pack

    A collection of four specialized AI-agent skills designed to improve software development workflows, code quality, technical documentation, and release management.

    Stop wasting time writing release notes manually, reviewing code without structure, or documenting projects using outdated information.

    This pack helps developers produce more reliable results using evidence from their actual repositories.

    What's included

    1. PR Review Pro

    A structured code review assistant that:

    • Reviews Git diffs and pull requests.
    • Identifies security and correctness issues.
    • Ranks findings by severity.
    • Provides file and line references.
    • Suggests practical fixes and merge recommendations.

    2. README Architect

    A repository-aware documentation assistant that:

    • Scans project manifests and scripts.
    • Identifies frameworks, tests and CI configuration.
    • Generates structured README files.
    • Checks installation and usage instructions against repository evidence.
    • Identifies environment variable names from example configuration files.

    3. Commit & Changelog Writer

    A release management assistant that:

    • Generates Conventional Commit messages.
    • Organizes Git history into release notes.
    • Follows Keep a Changelog conventions.
    • Recommends semantic version updates.
    • Identifies breaking changes.

    4. SEO Content Brief

    A technical content planning assistant that:

    • Identifies search intent.
    • Builds SEO article outlines.
    • Suggests titles and meta descriptions.
    • Maps relevant entities and questions.
    • Provides content quality checks through a bundled SEO linter.
    • Supports optional search-result research when web search is available.

    How it works

    Each skill contains its own SKILL.md instructions, supporting references, examples and Python helper scripts.

    The workflow is simple:

    1. Install the skill in a compatible AI agent.
    2. Give the agent access to the relevant project files.
    3. Describe the task you want to complete.
    4. Review the generated recommendations and deliverables.

    Compatibility

    Designed for AI agents supporting the open SKILL.md format.

    Installation procedures vary depending on the agent.

    Requirements

    • Python 3.8+ for the optional helper scripts.
    • Git for repository history and diff workflows.
    • Access to the relevant project files.
    • Web search is optional for live SEO research.

    The bundled Python scripts use the standard library and do not make network requests or access environment variables.

    Important limitations

    • AI-generated reviews and recommendations should be checked before merging code.
    • Very large pull requests may require review in smaller sections.
    • SEO recommendations do not guarantee search rankings.
    • Live search research depends on the availability of a search tool.

    Who is this for?

    • Software developers.
    • Freelancers.
    • Development agencies.
    • Technical writers.
    • Startup founders.
    • Software engineering teams.

    One practical package for improving everyday development workflows.

    Requires Python for helper scripts. PR reviews cap findings at 10 items for readability. Diffs >800 lines require manual focus prioritization. Versioning assumes SemVer standards.

    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 any payment.

    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 3 days ago

    Requires

    Python
    Git
    Node.js

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Browser
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    This skill pack uses local Python scripts to extract hard data from your git history and manifests before the AI processes it, ensuring that release notes and README instructions are based on actual code rather than AI hallucinations.

    The pack includes four specialized skills: Automated Changelogs, Evidence-Based PR Reviews, Repository-Verified READMEs, and Intent-First SEO Briefs, along with the necessary Python helper scripts for repository scanning.

    While it works with any Git-based project, it features specialized logic for npm, Python, Go, Docker, and standard CI configurations to provide more granular analysis.

    To ensure high-quality, actionable feedback, the PR Review skill is optimized for diffs up to 800 lines; larger pull requests may need to be analyzed in segments for maximum accuracy.

    You will need a local Python environment to run the included helper scripts that scan your repository, which then feed the extracted data to your AI agent for processing.

    Yes, the skills are designed to output markdown files and git messages that strictly adhere to the Conventional Commits and Keep a Changelog standards, making them ready for immediate use in professional pipelines.

    New in Technical Documentation