菜单
Render AutoResearch experiment reports from manifests, logs, W&B data, Prometheus evidence, and formal Verl case outputs. Use when building or diagnosing report HTML, Chinese report copy, bundle-local artifact loading, validation matrix explanations, or missing metric diagnostics.
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。
基于 SOC 职业分类
Enforce AutoResearch loop cadence, attempt, token, time, sub-agent, remote-compute, and kill-switch limits.
Load and enforce AutoResearch loop constraints before triage, edits, remote work, or external writes.
Read AutoResearch run evidence and loop state, then propose one bounded next experiment or escalate. L1 is report-only.
从 Verl examples 脚本和示例 YAML 中维护“可控参数即特性”的中文情报库与 Excel 台账。Use when Codex needs to scan Verl examples/run scripts, extract all user-adjustable parameters and Hydra overrides, create or update per-parameter markdown explanation files under docs/verl/features/lists, use subagents to research unclear parameters from local explanation files, official Verl docs, and repo docs, and produce docs/verl/features/verl-example-parameters.xlsx with parameter name, category, Chinese explanation, common values, performance impact, accuracy impact, and example count.
Generate RMB task cost reports from Codex/OpenAI-style token usage, including total input tokens, cached input tokens, uncached input tokens, output tokens, and GPT plus DeepSeek API cost estimates. Use when the user asks to统计 token 消耗, API 费用, 人民币成本, cache hit 成本, GPT/DeepSeek 对比, or to produce an `RMB-Cost.md` report for a task, goal, session, or experiment. Use by default for any goal, experiment, remote run, long command, or automation whose expected or actual runtime exceeds 20 minutes.
Verl GRPO formal case adapter for AutoResearch. Use when building, running, or diagnosing autoresearch run verl-case; preparing Qwen/geo3k GRPO matrices; wiring Verl containers to model/data assets, W&B, Prometheus, reports, provenance, and numbered evidence bundles; or explaining val-only versus real GRPO training boundaries.
| name | experiment-report |
| description | Render AutoResearch experiment reports from manifests, logs, W&B data, Prometheus evidence, and formal Verl case outputs. Use when building or diagnosing report HTML, Chinese report copy, bundle-local artifact loading, validation matrix explanations, or missing metric diagnostics. |
单页 HTML 报告 (log / wandb / prom 三视图)。
| Use | Don't Use |
|---|---|
| 读 manifest (调 datalake/manifest) | 任何采集 (这是 07) |
| 渲染 wandb 曲线截图 / 表格 | 跑用例 / 跑 stack |
| 渲染 prom 资源曲线 | 改配置 / 改密钥 |
| 渲染 log 关键事件 timeline | |
| 展示本次使用的 repo skill 和交付件完整性 | 修改训练脚本行为 |
| 对 val-only / train 模式、0 分原因、Prometheus 缺指标给出诊断 | 把诊断当成新的实验结论 |
trainer_val_only=True；.agents/skills/01..08 和 workspace-adapter/verl。trainer_val_only=True，报告必须明确标为“验证矩阵”，并提示不会更新模型参数。rows/*/validation/0.jsonl 的 output/gts/acc；严格 reward 可能因未输出 \\boxed{} 或抽取失败记为 0。python3 .agents/skills/08-experiment-report/scripts/render_report.py \
--run-id 2026-06-06-smoke-001 --open
✅ Phase 10 已具备 formal case 中文报告骨架；后续补资源曲线后继续扩展 Prometheus 图表。