菜单
Implement a given improvement or bug ticket's implementation plan, previously generated by either the 'brainstorm' or 'troubleshoot' commands. This command will execute the implementation plan, making the necessary changes to the codebase, configuration, or infrastructure as specified in the plan.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use this skill whenever a task would benefit from authoritative, technology-specific input beyond generalist knowledge — for example during code review, implementation planning, or troubleshooting, whenever the code, design, or issue touches Rust, Bun runtime TypeScript/JavaScript, Java/Spring Cloud microservices, GIS/geospatial processing, web front-end code, or Datadog observability data. This skill identifies the relevant expert sub-agent(s) for the technology or domain in scope, delegates to them via the Task tool, and synthesizes their findings into a single, actionable answer for the calling skill or user.
Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or extract structured data from HTML. Trigger whenever you are about to write an inline script (python3 heredoc, node -e, regex over HTML) or a bare curl for one-off web fetching, scraping, or page exploration.
This skill analyzes a given improvement ticket or idea and provides a detailed plan on how to implement it. It gathers relevant information from the ticket or request, including context, requirements, and constraints, and generates a step-by-step implementation plan. The skill also identifies potential challenges, required tests, and validation steps, and can assist in creating prototypes or breaking down the implementation into smaller tasks or milestones. When the implementation touches a technology with a dedicated expert (e.g. Rust, Bun/TypeScript, Java/Spring Cloud, GIS, web front-end, or Datadog observability), it consults the `ask-the-expert` skill to validate the proposed approach, risks, and tradeoffs before finalizing the plan.
Use this skill when the user wants recently written or modified code reviewed, needs targeted feedback on code quality, security, performance, idiomatic usage, or architecture, or has specific technical questions about their codebase. This skill delegates to the `ask-the-expert` skill to identify the languages and technologies involved and consult the appropriate specialized experts, then synthesizes their findings into a single, prioritized review.
This skill analyzes a given problem or issue and provides a detailed troubleshooting plan to resolve it. It gathers relevant information from the problem description, including context, symptoms, and constraints, and generates a step-by-step troubleshooting plan. The skill also identifies potential causes, required tests, and validation steps, and can assist in creating prototypes or breaking down the troubleshooting into smaller tasks or milestones. When the issue touches a technology with a dedicated expert (e.g. Rust, Bun/TypeScript, Java/Spring Cloud, GIS, web front-end, or Datadog observability), it consults the `ask-the-expert` skill for root-cause input before finalizing the plan.
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
基于 SOC 职业分类
| name | implement |
| description | Implement a given improvement or bug ticket's implementation plan, previously generated by either the 'brainstorm' or 'troubleshoot' commands. This command will execute the implementation plan, making the necessary changes to the codebase, configuration, or infrastructure as specified in the plan. |
| argument-hint | Please provide the GitHub Issue id for the improvement or bug ticket you would like to implement. |
| disable-model-invocation | true |
This skill is designed to help users implement a given improvement or bug ticket's implementation plan, previously generated by either the 'brainstorm' or 'troubleshoot' commands. It takes into account the context, requirements, and constraints provided in the ticket or request, and executes the implementation plan by making the necessary changes to the codebase, configuration, or infrastructure as specified in the plan.
Verify if the provided input refers to an open GitHub Issue by utilizing the GitHub MCP.
If it doesn't match a valid GitHub Issue, or the GitHub Issue does not contain an implementation plan, inform the user to use the brainstorm or troubleshoot skills to generate an implementation plan for the issue first, and end the conversation here.
With the implementation plan and any relevant context gathered from the GitHub Issue, execute the implementation plan by making the necessary changes to the codebase, configuration, or infrastructure as specified in the plan as follows:
check if the codebase is up-to-date with the latest changes from the main branch, and if not, pull the latest changes and try to resolve any merge conflicts. if not possible, inform the user to resolve the conflicts manually and end the conversation here.
check if we have a local branch for the GitHub Issue (following the naming convention: feature/gh-{GITHUB_ISSUE_ID}), and if not, create a new branch for the issue locally
apply the changes specified in the implementation plan to the codebase, configuration, or infrastructure, following best practices for code quality, security, and maintainability. If the codebase contains an AGENTS.md file, or any *.instructions.md file, parse it to extract any explicit instructions or constraints that may affect the implementation. Those instructions should be treated as authoritative and incorporated into the implementation process with higher priority. They overrule any implicit assumptions you might make about the codebase.
check for missing tests, documentation, or other artifacts that are required by the implementation plan, and create them as needed (use the write-tests skill if available). If the implementation plan specifies any new dependencies or configuration changes, ensure that they are properly documented and integrated into the codebase.
make sure to run any necessary tests, linters, or build processes to ensure that the changes are valid and do not introduce new issues. If any issues are detected, fix them before proceeding. For integration tests you may need to set up specific test environments or mock services (refer to the run-tests skill for guidance if available).
commit the changes to the local branch, push the branch to the remote repository, and create a GitHub Pull Request for review (use create-pr skill if available). Include a clear description of the changes made, referencing the GitHub Issue id and any relevant context.
Finally, run a thorough code review via the code-review skill for the new branch and publish the review results to the GitHub Pull Request.
