grade-iterate
当已上线的托管智能体需要按评分标准进行评分并改进时使用（“给我的智能体评分”“它是否足够好”）。用 outcome_builder.py 构建结果，用 verdict_reader.py 读取判定，并从 eval_scaffold.py 运行留出评估。
机器翻译查看英文原文
Use when a launched managed agent needs grading against a rubric and improving ('grade my agent', 'is it good enough'). Builds the outcome with outcome_builder.py, reads verdicts with verdict_reader.py and runs held-back evals from eval_scaffold.py.
适用对象：对象待分类。自动收录 · 待核查。
原作者说明节选
从固定版本的 SKILL.md 提取，保留原文语言。以下内容属于作者说明，本站尚未验证安装、兼容或运行结果。
查看英文原文
原文涵盖的主题
- Phase 3 — Grade → Iterate (the bounded loop)
- Workflow
- Hard rules
- Forcing-question library (recommend + cite)
- Tools
This is the plugin's loop: CMA's outcome primitive self-grades the agent's work in an isolated context and feeds failing verdicts back for the next attempt. It is always bounded by maxiterations (1..20) — never "improve forever". See ../../references/loops-and-workflows.md and the outcome section of ../../references/cma-primitives.md. 1. Define the outcome. The rubric is required; maxiterations is clamped to 1..20. Send the payload as a user.defineoutcome event (append to the running session). 2. Read every verdict first. Tables the rubric outcome and recommends: SHIP (satisfied), SHARPEN then re-run (needsrevision), ESCALATE (maxiterationsreached / failed), RESUME (interrupted). With ≤1 iteration left it flips to "make the single highest-value fix or escalate now". 3. Loop invariant. Each iteration must move ≥1 rubric line fail→pass, or the run halts at the cap and escalates. Don't burn the budget on cosmetic edits. 4. Once a version passes, run held-back eval. Held-back cases (never seen during iteration) run in parallel, capped at the 25-thread CMA ceiling, each graded against the same rubric. 5. Decide. SHIP as v0, or promote to a scheduled deployment (Phase 4). Record the verd
这里只展示节选，请以完整原文和当前要求为准。
- 来源仓库
- alirezarezvani/claude-skills
- 源文件
- agent-launcher/skills/grade-iterate/SKILL.md
- 固定版本
- 8f082544116fc0d014188e521ca40304cdfc86b0
准备条件
- 本条仅收录原作者的技能元数据；请阅读完整说明，确认依赖、许可与使用条件。
第一件可以尝试的小事
先阅读原作者说明，再决定是否在自己的 AI 工具中使用。
对应 AI 工具说明
作者有说明不等于本站实机验证。没有证据时，不自动标为兼容、安全或免费。
来源与内容状态
本条为自动发现的元数据，尚未完成人工文档核查；适用性与运行结果待核查。
原作者：alirezarezvani/claude-skills · 原作者仓库元数据。文档核查：未核查。最近来源检查：2026-11-09T14:01:45.923Z。
分类由名称、说明与路径规则生成，分类不代表已核实适配。
许可与权利归属
MIT。第三方内容及版权归原作者，使用条件以原文为准。
许可原文 ↗本站没有因同步、复制或用户自报成功而将资源标为运行验证通过。
限制与注意事项
- 元数据收录不代表本站已经安装、适配、实测或进行安全审查。