Adversarially review a grooming spec before implementation starts. Finds hidden risks, unvalidated assumptions, and missing dependencies. Standalone entry point for the challenger agent.
中文简介正在准备中。当前显示原文说明。
Use this skill when adding or modifying WordPress abilities
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
Always check if the function exists before calling it, to ensure compatibility with WordPress versions prior to 6.9:
if ( ! function_exists( 'wp_register_ability' ) ) {
return;
}
To add a new ability, follow these steps:
AbilitiesInterfaceServiceProviderwp_abilities_api_init hookAn ability name must be unique and follow the format wp-rocket/ability-name, where wp-rocket is the vendor name and ability-name is a descriptive name for the ability. Use hyphens to separate words in the ability name.
The check_permissions()method should always verify against the current user capabilities, using current_user_can( 'rocket_manage_options ) by default, to ensure that only authorized users can execute the ability, except explicitly required otherwise.
An ability must be associated to an ability category. If the category doesn't exist yet, register a new one in the related subscriber using the wp_abilities_api_categories_init hook.
Make the ability available to the REST API and the MCP by adding meta.show_in_rest=true and meta.mcp.public=true when registering the ability, unless explicitly required otherwise.
Annotations should be added to the meta field when registering the ability, as an array of key-value pairs:
An example of an ability class can be found in the /inc/Engine/Abilities/Options/GetOptions.php file.
If an ability requires input parameters, the parameters of the execute() method should always match the input schema defined when registering the ability.
The return value of the execute() method of an ability should always match the output schema defined when registering the ability.
Test only the execute() method of the ability class, which contains the logic to perform the action associated with the ability. Mock any dependencies and assert that the method behaves as expected under different conditions.
An example of unit tests for an ability class can be found in the /tests/Unit/inc/Engine/Abilities/Options/GetOptions/ExecuteTest.php file.
Check for WordPress version compatibility, abilities are available starting WordPress 6.9. Mark skip test if version under test is lower than 6.9.
Set up user to ensure ability permissions are correctly applied. Add scenario where user has the ability and another where they don't, and assert that the expected outcomes occur in both cases.
Test ability execution output by getting the ability WP_Ability object using wp_get_ability( $ability_name ) and calling the execute() method. Assert that the output is correct based on the input parameters and the expected behavior of the ability.
An example of integration tests for an ability class can be found in the /tests/Integration/inc/Engine/Abilities/Options/GetOptions/RegisterGetOptionsAbilityTest.php file.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Adversarially review a grooming spec before implementation starts. Finds hidden risks, unvalidated assumptions, and missing dependencies. Standalone entry point for the challenger agent.
中文简介正在准备中。当前显示原文说明。
Check a change against WordPress.org plugin rules and PHPCS standards.
中文简介正在准备中。当前显示原文说明。
Update developer-facing documentation to reflect code changes on the current branch. Runs as an inline skill inside backend-agent and frontend-agent (step 2.5 of the internal sequence) after implementation and before DOD. Receives the explicit list of changed files from the implementation agent. No-op if no public API changes occurred.
中文简介正在准备中。当前显示原文说明。
Run the Definition of Done checklist for the current wp-rocket branch and report PASS/WARN/FAIL with evidence. Two modes: layer 1 (self-correction inside backend-agent / frontend-agent — resolves FAILs before handoff) and layer 2 (independent orchestrator gate — fresh perspective after handoff). Pass layer: "1" or layer: "2" when invoking.
中文简介正在准备中。当前显示原文说明。
Run a basic E2E behavioral probe — one primary scenario smoke test for the grooming step.
中文简介正在准备中。当前显示原文说明。
Groom a single GitHub issue — produce an implementation spec and optionally post the grooming summary as a GitHub comment. Standalone entry point for the grooming-agent.
中文简介正在准备中。当前显示原文说明。