Executes an existing implementation plan task by task, preserving its interfaces and constraints, running focused checks after each slice, and stopping when the repository differs from the plan. Use when a written plan or approved checklist already exists. Not for inventing the plan, debugging an unexplained failure, or broad unscoped cleanup.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Treat the plan as an executable contract with room for evidence-backed corrections. Do not silently redesign it while implementing.
For each task:
If a test, dependency, or interface contradicts the plan, stop at a checkpoint and re-shape the affected task. Do not delete a check to make the plan green.
completion-verification for the final claim.Execution is complete when every in-scope task has a fresh result, the final diff matches the approved scope, and unverified surfaces are reported.
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。
Designs and runs reproducible evaluations for AI agents, prompts, tools, skills, and model-backed workflows using realistic datasets, isolated baselines, objective assertions, rubric grading, trajectory analysis, cost/latency tracking, and regression comparison. Use when measuring agent quality, optimizing skill triggering, comparing prompts or models, or gating an AI feature release. Not for ordinary deterministic unit tests.
中文简介正在准备中。当前显示原文说明。
Designs or reviews HTTP, REST, GraphQL, RPC, CLI, webhook, event, and service interfaces with explicit inputs, outputs, errors, compatibility, idempotency, pagination, authentication, versioning, and observability. Use when introducing or changing an API or cross-component contract. Not for internal implementation details with no boundary or for debugging one API failure; use root-cause-debugging there.
中文简介正在准备中。当前显示原文说明。
Reviews an existing codebase for structural friction, unclear ownership, leaky or shallow interfaces, excessive coupling, misplaced state, poor testability, and risky dependency direction, then prioritizes evidence-backed improvement candidates. Use for architecture audits, modularization, modernization, or recurring cross-cutting change pain. Not for designing one new interface, simplifying a local function, or fixing a reproduced bug.
中文简介正在准备中。当前显示原文说明。
Validates a running application, CLI, API, service, or generated artifact as a user or operator against a prewritten observable behavior contract while remaining source-blind. Use for acceptance checks, runtime proof, anti-fake probes, release smoke tests, or an independent companion to code review. Not for source-quality findings, root-cause diagnosis, or visual design judgment outside the contract.
中文简介正在准备中。当前显示原文说明。
Closes a completed development branch by checking the final diff and proof, presenting merge, pull-request, keep, or discard options, and cleaning up only after the user or repository workflow chooses a path. Use when feature work is complete and the branch must be integrated or retired. Not for claiming a feature is complete before verification.
中文简介正在准备中。当前显示原文说明。
Tests a real web user flow with a browser by asserting semantic behavior, network and loading states, keyboard access, responsive layouts, and stable visual evidence. Use for browser bugs, end-to-end UI behavior, responsive or accessibility checks, and screenshot baselines. Not for static source review without a browser or for backend-only tests.
中文简介正在准备中。当前显示原文说明。