superlab 0.1.16 → 0.1.17

package/lib/i18n.cjs

@@ -55,7 +55,7 @@ const ZH_CONTENT = {
   [path.join(".codex", "prompts", "lab-report.md")]: codexPrompt(
     "基于验证后的迭代工件生成最终报告",
     "report context",
-    "使用已安装的 `lab` 技能：`.codex/skills/lab/SKILL.md`。\n\n立刻针对用户当前给出的参数执行 `/lab:report`，不要只推荐别的 `/lab` 阶段。只有在缺少阻塞性前提时，才明确指出缺什么，并且一次最多追问一个问题。\n\n本命令运行 `/lab:report` 阶段。它必须汇总标准化摘要、保留失败尝试和局限，并生成最终实验报告。"
+    "使用已安装的 `lab` 技能：`.codex/skills/lab/SKILL.md`。\n\n立刻针对用户当前给出的参数执行 `/lab:report`，不要只推荐别的 `/lab` 阶段。只有在缺少阻塞性前提时，才明确指出缺什么，并且一次最多追问一个问题。\n\n本命令运行 `/lab:report` 阶段。它必须生成给用户直接阅读的最终实验报告和受管的 `main-tables.md`，明确写出主指标、次级指标和必要终局证据，并用白话解释这些指标分别衡量什么、哪些只是健康度或支持性指标、以及每张主表到底证明了什么和没证明什么。"
   ),
   [path.join(".codex", "prompts", "lab-write.md")]: codexPrompt(
     "把验证过的研究工件转成论文 section，并按小步方式修订",
@@ -102,7 +102,7 @@ const ZH_CONTENT = {
     "lab-report",
     "基于验证后的迭代工件生成最终报告",
     "report context",
-    "使用已安装的 `lab` 技能：`.claude/skills/lab/SKILL.md`。\n\n立刻针对用户当前给出的参数执行 `report` 阶段，不要只推荐别的 lab 阶段。只有在缺少阻塞性前提时，才明确指出缺什么，并且一次最多追问一个问题。\n\n本命令运行 lab workflow 的 `report` 阶段。它必须汇总标准化摘要、保留失败尝试和局限，并生成最终实验报告。"
+    "使用已安装的 `lab` 技能：`.claude/skills/lab/SKILL.md`。\n\n立刻针对用户当前给出的参数执行 `report` 阶段，不要只推荐别的 lab 阶段。只有在缺少阻塞性前提时，才明确指出缺什么，并且一次最多追问一个问题。\n\n本命令运行 lab workflow 的 `report` 阶段。它必须生成给用户直接阅读的最终实验报告和受管的 `main-tables.md`，明确写出主指标、次级指标和必要终局证据，并用白话解释这些指标分别衡量什么、哪些只是健康度或支持性指标、以及每张主表到底证明了什么和没证明什么。"
   ),
   [path.join(".claude", "commands", "lab-write.md")]: claudeCommand(
     "lab-write",
@@ -289,11 +289,14 @@ const ZH_SKILL_FILES = {
 
 ## 必要输出
 
+- 给用户看的总结
 - 方法概述
 - 选定指标摘要
+- 指标白话释义
 - 实验设置
 - 已验证主结果
 - 位于 \`<deliverables_root>/main-tables.md\` 的受管主表工件
+- 怎么看主表的阅读指引
 - 消融
 - 失败尝试
 - 局限性
@@ -319,6 +322,8 @@ const ZH_SKILL_FILES = {
 - 主表结构、gate 和最终结果 framing 必须对齐已批准的评估协议。
 - 不要凭记忆重述指标定义、baseline 行为或对比方法实现；直接引用评估协议里记录的来源。
 - 必须把已批准的主指标、次级指标和必要终局证据明确写进 \`report.md\` 与受管的 \`main-tables.md\`。
+- 必须用白话解释选定的主指标和次级指标：每个指标在衡量什么、越高还是越低更好、它是主结果指标还是健康度/支持性指标。
+- 如果出现 coverage、completeness、confidence 或类似健康度指标，必须明确说明这类指标回答的是“实验是否跑稳、证据是否完整”，而不是主要科学效应本身。
 - 如果报告依赖了对原始指标或原始实现的偏差，必须明确写出这个偏差。
 - 如果 workflow language 是中文，\`report.md\` 和 \`<deliverables_root>/main-tables.md\` 也应使用中文，除非文件路径、代码标识符或字面指标名必须保持原样。
 - 解释优先保守，不要写成营销文案。
@@ -327,6 +332,8 @@ const ZH_SKILL_FILES = {
 ## 交互约束
 
 - 开始前先简洁说明：campaign outcome、选定的主指标和次级指标、最强已支撑 claim、最大的报告风险。
+- 当该阶段由 \`/lab:auto\` 进入时，要主动给出用户可读的白话总结，不要等用户再追问“这些指标是什么意思”或“这些表怎么看”。
+- 把 \`report.md\` 当作给用户看的工件，而不是内部 dump。术语第一次出现时就解释；先讲结论，再讲术语。
 - 如果某个未决前提会改变报告解释，一次只问一个问题。
 - 如果存在多种报告 framing，先给 2-3 个方案、trade-offs 和推荐项，优先最忠于证据的 framing。
 - 如果某种 framing 会实质影响后续论文 claim，要保留 approval gate。
@@ -684,10 +691,12 @@ const ZH_SKILL_FILES = {
   [path.join(".lab", ".managed", "templates", "final-report.md")]:
 `# 最终报告
 
-## 目标
+## 给用户看的总结
 
-- 本轮研究目标：
-- 是否达标：
+- 一句话结论：
+- 已经被验证的内容：
+- 还没有被证明的内容：
+- 当前最大报告风险：
 
 ## 选定指标
 
@@ -695,6 +704,19 @@ const ZH_SKILL_FILES = {
 - 次级指标：
 - 必要终局证据：
 
+## 指标白话释义
+
+- 主指标在衡量什么：
+- 次级指标在衡量什么：
+- 健康度/支持性指标在衡量什么，为什么它们不是主结论：
+
+## 怎么看主表
+
+- Table 1 负责回答什么：
+- Table 2 负责回答什么：
+- Table 3 负责回答什么：
+- Table 4 负责回答什么：
+
 ## 主表工件
 
 - 受管主表路径：\`<deliverables_root>/main-tables.md\`
@@ -719,18 +741,37 @@ const ZH_SKILL_FILES = {
   [path.join(".lab", ".managed", "templates", "main-tables.md")]:
 `# 主表工件
 
+## 给用户看的总结
+
+- 用户可直接复述的结论：
+- 这些主表证明了什么：
+- 这些主表还不能证明什么：
+
 ## 选定指标
 
 - 主指标：
 - 次级指标：
 - 必要终局证据：
 
+## 指标白话释义
+
+- 主指标在衡量什么：
+- 次级指标在衡量什么：
+- 健康度/支持性指标该怎么读：
+
 ## 最终表现摘要
 
 - 主要结果摘要：
 - 最重要数字：
 - 报告边界：
 
+## 怎么看这些表
+
+- Table 1 负责回答什么：
+- Table 2 负责回答什么：
+- Table 3 负责回答什么：
+- Table 4 负责回答什么：
+
 ## Table 1
 
 - 作用：
@@ -2015,6 +2056,7 @@ ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "auto.md")] = `# \`/la
 - 先做输入归一化：把 \`Autonomy level L1/L2/L3\` 视为执行权限级别，把 \`Layer 3\`、\`Phase 1\`、\`Table 2\` 视为论文范围目标。
 - 如果用户同时提了论文层、实验 phase 和自治级别，先用一句话重述：objective、自治级别、terminal goal、scope、allowed modifications。
 - 如果 workflow language 是中文，摘要、清单条目、任务标签和进度更新都应使用中文，除非文件路径、代码标识符或字面指标名必须保持原样。
+- 当循环进入 \`report\` 时，要主动给出用户可读的白话总结，解释主指标、次级指标和主表作用；不要等用户额外发一句“解释这些指标”。
 - 当循环即将进入 \`write\`，且 \`paper_template_root\` 为空时：
   - 如果 \`paper_template_decision\` 是 \`unconfirmed\`，必须先追问一次：继续使用默认 scaffold，还是先接入模板目录
   - 如果用户选择默认 scaffold，就持久化 \`paper_template_decision: default-scaffold\`
@@ -2027,6 +2069,8 @@ ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "auto.md")] = `# \`/la
 
 ZH_CONTENT[path.join(".claude", "skills", "lab", "stages", "auto.md")] =
   ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "auto.md")];
+ZH_CONTENT[path.join(".claude", "skills", "lab", "stages", "report.md")] =
+  ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "report.md")];
 
 function getLocalizedContent(relativePath, lang) {
   if (lang !== "zh") {

package/package-assets/claude/commands/lab-report.md

@@ -7,4 +7,4 @@ argument-hint: report context
 Use the installed `lab` skill at `.claude/skills/lab/SKILL.md`.
 
 Execute the requested `/lab-report` command against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `report` stage of the lab workflow. Follow the installed skill, stage guide, and the project assets under `.lab/`.
+This command runs the `report` stage of the lab workflow. It must produce a user-facing final report plus the managed `main-tables.md` artifact, explicitly carry the approved primary and secondary metrics forward, explain the selected metrics in plain language, say which metrics are only health or support metrics, and explain what each main table proves or does not prove.

package/package-assets/codex/prompts/lab-report.md

@@ -6,4 +6,4 @@ argument-hint: report context
 Use the installed `lab` skill at `.codex/skills/lab/SKILL.md`.
 
 Execute the requested `/lab:report` stage against the user's argument now. Do not only recommend another lab stage. If a blocking prerequisite is missing, say exactly what is missing and ask at most one clarifying question.
-This command runs the `/lab:report` stage. Follow the installed skill, stage guide, and the project assets under `.lab/`.
+This command runs the `/lab:report` stage. It must produce a user-facing final report plus the managed `main-tables.md` artifact, explicitly carry the approved primary and secondary metrics forward, explain the selected metrics in plain language, say which metrics are only health or support metrics, and explain what each main table proves or does not prove.

package/package-assets/shared/lab/.managed/templates/final-report.md

@@ -1,8 +1,11 @@
 # Final Report
 
-## Overview
+## Reader Summary
 
-Summarize the method and overall outcome.
+- One-sentence conclusion:
+- What is validated:
+- What is still unproven:
+- Biggest reporting risk:
 
 ## Selected Metrics
 
@@ -10,6 +13,12 @@ Summarize the method and overall outcome.
 - Secondary metrics:
 - Required terminal evidence:
 
+## Metric Guide
+
+- Primary metric plain-language explanation:
+- Secondary metric plain-language explanation:
+- Health or support metrics and why they are not the main claim:
+
 ## Experiment Setup
 
 - Datasets:
@@ -17,6 +26,13 @@ Summarize the method and overall outcome.
 - Baselines:
 - Metrics:
 
+## How to Read the Main Tables
+
+- Table 1 is for:
+- Table 2 is for:
+- Table 3 is for:
+- Table 4 is for:
+
 ## Main Tables
 
 - Managed main tables artifact: `<deliverables_root>/main-tables.md`

package/package-assets/shared/lab/.managed/templates/main-tables.md

@@ -1,17 +1,36 @@
 # Main Tables
 
+## Reader Summary
+
+- User-facing takeaway:
+- What the tables prove:
+- What the tables do not yet prove:
+
 ## Selected Metrics
 
 - Primary metrics:
 - Secondary metrics:
 - Required terminal evidence:
 
+## Metric Guide
+
+- Primary metric plain-language explanation:
+- Secondary metric plain-language explanation:
+- Health or support metrics and how to read them:
+
 ## Final Performance Summary
 
 - Main result summary:
 - Most important numbers:
 - Reporting caveat:
 
+## How to Read These Tables
+
+- Table 1 is for:
+- Table 2 is for:
+- Table 3 is for:
+- Table 4 is for:
+
 ## Table 1
 
 - Purpose:

package/package-assets/shared/skills/lab/stages/auto.md

@@ -108,6 +108,7 @@
 - Then ask at most one clarifying question if a blocking field is still missing.
 - If `.lab/config/workflow.json` sets the workflow language to Chinese, write summaries, options, checklist items, task labels, and progress updates in Chinese unless a file path, code identifier, or literal metric name must remain unchanged.
 - When the loop reaches `report`, apply the same workflow-language rule to `report.md` and the managed `main-tables.md` artifact.
+- When the loop reaches `report`, proactively deliver a user-facing plain-language summary of the selected metrics, what they mean, what the tables prove, and what remains unproven. Do not wait for a separate user request asking for interpretation.
 - When the loop is about to enter `write` and `paper_template_root` is empty:
   - if `paper_template_decision` is `unconfirmed`, ask one explicit question: continue with the default scaffold or attach a template directory first
   - if the user chooses the default scaffold, persist `paper_template_decision: default-scaffold`

package/package-assets/shared/skills/lab/stages/report.md

@@ -2,11 +2,14 @@
 
 ## Required Output
 
+- reader summary for the user
 - method overview
 - selected metrics summary
+- plain-language metric guide
 - experiment setup
 - validated main results
 - managed main tables artifact under `<deliverables_root>/main-tables.md`
+- how-to-read-the-tables guide
 - ablations
 - failed attempts
 - limitations
@@ -34,6 +37,8 @@
 - Structure tables, gates, and main claims against the approved evaluation protocol.
 - Do not restate metric definitions, baseline behavior, or comparison implementations from memory; use the approved evaluation protocol and its recorded sources.
 - Carry the approved `Primary metrics`, `Secondary metrics`, and `Required terminal evidence` into both the report and the managed main-tables artifact.
+- Explain the selected primary and secondary metrics in plain language for the user: what each metric measures, whether higher or lower is better, and whether it is a main result metric or only a health/support metric.
+- If coverage, completeness, confidence, or similar health metrics appear, explicitly say that they describe experimental reliability rather than the main scientific effect.
 - If the report depends on a deviation from an original metric or implementation, state that deviation explicitly instead of smoothing it over.
 - If `.lab/config/workflow.json` sets the workflow language to Chinese, write `report.md` and `<deliverables_root>/main-tables.md` in Chinese unless a file path, code identifier, or literal metric name must remain unchanged.
 - Prefer conservative interpretation over marketing language.
@@ -42,6 +47,8 @@
 ## Interaction Contract
 
 - Start with a concise summary of the campaign outcome, the selected primary and secondary metrics, the strongest supported claim, and the biggest reporting risk.
+- Proactively deliver a user-readable plain-language summary when the stage is reached from `/lab:auto`; do not wait for a separate follow-up request asking what the metrics or tables mean.
+- Treat `report.md` as a user-facing artifact rather than an internal dump. Prefer plain-language explanations before jargon, and explain each metric the first time it matters.
 - If a missing assumption would change report interpretation, ask one clarifying question at a time.
 - If there are multiple defensible report framings, present 2-3 approaches with trade-offs and recommend the most evidence-faithful framing before writing.
 - Keep an approval gate when the reporting frame would materially affect what the paper later claims.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlab",
-  "version": "0.1.16",
+  "version": "0.1.17",
   "description": "Strict /lab research workflow installer for Codex and Claude",
   "keywords": [
     "codex",