GitHub Issue to Implementation Planner

    1

    Converts vague GitHub issues into structured implementation plans with acceptance criteria and file-level steps.

    Free

    3 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    GitHub Issue to Implementation Planner

    Example session with this skill installed

    I need to add a password reset feature. Users should be able to request a link via email. Here is the ticket: 'Add forgot password flow to the auth module'.

    • Read your context and instructions
    • Compiled the github issue to

    I have analyzed the request and mapped out the necessary changes for the password reset flow. ## [Implementation Plan] - **Goal:** Implement a secure "Forgot Password" flow that allows users to request a reset link via email and update their password using a unique token. - **Acceptance Criteria:** - [ ] User can submit their email address on a '/forgot-password' page. - [ ] System sends a transactional email with a time-limited (1 hour) signed JWT link. - [ ] User can set a new password via the link, which invalidates the token upon success. - [ ] Appropriate success/error toast notifications are displayed for all states. - **Affected Files:** - `src/api/auth.ts` (New endpoints for request and reset) - `src/pages/ForgotPassword.tsx` (New UI) - `src/pages/ResetPassword.tsx` (New UI) - `src/services/emailService.ts` (Email logic) - `src/middleware/authGuard.ts` (Token validation) - **Execution Steps:** 1. Define the backend API routes for `POST /auth/forgot-password` and `POST /auth/reset-password`. 2. Implement the email service logic using the existing SMTP provider to send reset links. 3. Create the `ForgotPassword` request form with email validation. 4. Create the `ResetPassword` form that handles the token from the URL and submits the new password. 5. Add global state handling for loading and error messages during the flow. - **Edge Cases to Test:** - User submits an email that does not exist in the database (should show generic success to prevent enumeration). - User attempts to use an expired or previously used reset token. **Next steps** 1. Review the proposed file list to ensure no shared components were missed. 2. Confirm if the token expiration time (1 hour) aligns with security requirements. 3. Approve this plan to begin the backend API implementation.

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

    About this skill

    The problem

    AI agents often rush into coding vague requests, leading to out-of-scope diffs and technical debt. Developers waste time reverting messy implementations because the agent lacked a clear execution strategy.

    What it does

    • Extracts core requirements from GitHub issues or Jira tickets into concise goals.
    • Defines specific, testable acceptance criteria to ensure the definition of done is clear.
    • Predicts affected files across the codebase to map out the scope of changes.
    • Generates a logical, step-by-step sequence of operations for implementation.
    • Identifies edge cases and failure points to guide test case creation.

    Why this beats prompting it yourself

    Generic prompts often skip the critical step of file-level discovery and edge case analysis. This skill enforces a professional planning structure that prevents the agent from writing a single line of code until the architectural logic is validated.

    Use cases

    • Translating a vague "fix this bug" ticket into a structured debugging plan.
    • Architecting multi-file feature additions before triggering file edits.
    • Planning refactors by identifying all impacted utility and component files.
    • Scaffolding test-driven development by defining edge cases upfront.

    Known limitations

    Requires the user to provide initial context or a ticket description. Does not execute code changes, it only produces the plan for approval.

    Requires clear initial context or a ticket description. Focuses exclusively on planning and will not generate implementation code until the plan is approved.

    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

    3 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This skill bridges the gap between a brief ticket description and the coding phase by generating a structured blueprint, including file-level predictions and edge case analysis, to prevent AI agents from creating messy or out-of-scope code.

    The skill is designed to work with any high-reasoning LLM or AI agent framework that supports text-based planning, as it outputs structured Markdown plans compatible with all major coding assistants.

    You will receive the proprietary planning logic and structured templates required to transform GitHub issues into actionable roadmaps, along with documentation on how to integrate it into your existing workflow.

    No complex installation is required; simply provide the skill with the text or URL of a GitHub issue or Jira ticket, and it will immediately begin the architectural analysis and step-by-step planning process.

    While the skill is optimized for GitHub issues, it works effectively with Jira tickets, Trello cards, or any text-based project management tool that provides a description of a bug or feature request.

    No, this skill focuses strictly on the 'Architectural Phase' to ensure logic is validated first; once you approve the generated plan, you can then pass it to your coding agent for execution.

    New in Business & Operations