Run Proto UI's dynamic comprehension assessment and derive an unsigned local task-fit result. Use when an Agent needs review calibration or a fresh autonomous task and review ceiling. Do not use a self-result as identity, permission, or acceptance evidence.
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。
Produce one snapshot-bound orientation result without publishing an answer key or granting authority.
pnpm agent:assess. Keep the challenge and response outside tracked repository content.pnpm agent:assess:response -- --challenge <path>. Answer every prompt from the bound snapshot, then set submittedAt to the actual RFC 3339 completion time within the challenge window. Separate conclusions, located evidence, unknowns, and any genuinely present attended decision class in the schema's humanGates field.pnpm agent:assess:validate -- --challenge <path> --response <path>. Treat any binding or shape failure as U0.internal/agent-operations/capability-rubric.yaml. Generate the evaluation form with pnpm agent:assess:evaluation, score every dimension from 0 through 4, state the rationale, and record every applicable critical failure.pnpm agent:assess:self-result -- --challenge <path> --response <path> --evaluation <path>. Preserve the output as an unsigned orientation artifact.The response is dynamic because the challenge binds a repository snapshot, nonce, subject, sampled entities, policy, and generator. Never search for or invent a static answer file.
A self-result can derive U0 through C4 without cross-dimension compensation. It is an unsigned, session-scoped self-assessment, not a runtime identity. It explicitly records that human-assisted use is advisory and uncovered autonomous selection is ceiling-bound. Verified owner delegation makes assessment advisory for covered ordinary transitions; do not repeat this leaf merely because a turn or process ended. Live permission and decision authority remain separate; ordinary ready work does not acquire another gate from the score.
Return the challenge ID, response digest, self-assessed band, recommended task and review classes, autonomous ceilings, critical failures, snapshot binding, explicit limitations, and one next transition permitted by the current mode.
Return one handoff conforming to internal/agent-operations/schemas/skill-handoff.schema.json, with fromId set to pui-assess, the registered capability-envelope artifact, and at most one nextSkillId.
Communicate with the user in the user's current language while preserving canonical identifiers.
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。
Implement one governed Proto UI Adapter-profile realization slice. Use when target and runtime range, supported or omitted Module role, Host Capability fidelity, lifecycle translation, failure behavior, compatibility boundary, and evidence scope are fixed by current authority. Use pui-adapter-assess for research or readiness assessment and pui-regression first for a governed failing behavior.
中文简介正在准备中。当前显示原文说明。
Assess one bounded Proto UI Adapter question without changing repository or external state. Use for new-Adapter research, target compatibility, catalog readiness, reviewed Module support or omission evidence, Host Capability fidelity, lifecycle translation, dependency risk, or implementation readiness. Do not catalog, implement, repair, or approve the Adapter slice.
中文简介正在准备中。当前显示原文说明。
Measure the active Agent model with pinned offline ModelTrace sampling and return an unsigned closed-set attribution record. Use before Agent-originated commits, Issue/PR creation or material updates, comments, reviews, and current collaboration writes in either execution mode. Do not treat a fingerprint, declared model label, or record reference as authenticated identity, permission, independent review, or acceptance.
中文简介正在准备中。当前显示原文说明。
Investigate a bounded Proto UI Contract, Prototype, Module, Host Capability, Adapter, schema, or ownership question and turn a genuinely unresolved direction into one semantic decision packet. Use for spec brainstorming, admission questions, competing semantic models, uncataloged behavior, or unresolved cross-layer boundaries.
中文简介正在准备中。当前显示原文说明。
Diagnose one bounded Proto UI Actions or CI failure from an exact workflow run and revision, then route the exact repair, validation, or recheck transition. Use to locate the owning failure and distinguish infrastructure from change failures. This leaf remains read-only.
中文简介正在准备中。当前显示原文说明。
Post one already selected Proto UI work-item claim as a reversible GitHub metadata mutation. Use after pui-select produced a current proposal and the exact claim has authorization, live permission, current readiness, and an idempotent write boundary. Do not select work, decide readiness, release claims, or widen the authorized wording.
中文简介正在准备中。当前显示原文说明。