superlab 0.1.38 → 0.1.40

package/lib/i18n.cjs

@@ -1320,11 +1320,65 @@ const ZH_SKILL_FILES = {
 - Terminology consistency:
 - Five-dimension self-review outcome:
 
+## Terminology Clarity
+
+- Key terms introduced or revised this round:
+- Was \`.lab/writing/terminology-glossary.md\` updated:
+- Did first mention use the full form, with an approved short form only after that:
+- Did each concept keep one natural-language paper-facing name throughout the prose:
+- For each term, what it is and why it matters here:
+- Did any internal identifier leak into reader-facing prose:
+- Did any label containing \`_\` or \`-\` remain in reader-facing prose:
+- Were the first mentions explained in the prose:
+- Did any alias drift remain unresolved:
+- Remaining reader-facing jargon risk:
+
+## Language Decision
+
+- Workflow language:
+- Paper language:
+- Finalization decision:
+- Why this decision was chosen:
+- Workflow-language deliverable path:
+
 ## 决策
 
 - Continue or stop:
 - Next writing target:
 - 是否需要回退到 \`review\` 或 \`iterate\`：
+`,
+  [path.join(".lab", ".managed", "templates", "terminology-glossary.md")]:
+`# 术语表
+
+在 \`/lab:write\` 期间用这份 glossary 固定 reader-facing 命名。
+
+## 命名规则
+
+- 第一次出现先写全称；如果后面要复用简称或缩写，就在第一次出现时写成 \`全称（简称）\`。
+- 同一个概念只能有一个自然语言 paper-facing 名称。
+- 正文里只用自然语言全称。
+- 正文里不要使用包含 \`_\` 或 \`-\` 的标签名。
+- 内部标识符、配置键和实验包标签默认不要进正文；若必须出现，也只能先给读者做一次映射，然后移回正文之外。
+
+## Entries
+
+### Entry
+
+- Canonical paper-facing term:
+- Full form at first mention:
+- Approved short form or acronym:
+- Reader-facing explanation:
+- Why this term matters here:
+- First-use section:
+- Approved short natural-language alias, if any:
+- Forbidden aliases or labels:
+- Internal identifiers to avoid in prose:
+
+## Audit
+
+- Naming drift found this round:
+- Terms that still need a clearer explanation:
+- Terms that should move to appendix, tables, or implementation details:
 `,
   [path.join(".lab", "config", "workflow.json")]:
 `{
@@ -1899,7 +1953,13 @@ ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "write.md")] = `# \`/l
 - 如果 \`workflow_language\` 与 \`paper_language\` 不一致，就不要在确认前先把最终论文正文改写成 \`paper_language\`；必须先追问、再持久化、再改稿。
 - 如果 \`workflow_language\` 与 \`paper_language\` 不一致，就要在最新 write iteration artifact 里记录工作流语言、论文语言、最终语言决定、为什么这样决定，以及 workflow-language 交付稿路径。
 - 如果 \`paper_language_finalization_decision\` 是 \`convert-to-paper-language\`，在接受最终定稿前必须保留 workflow-language 交付稿，并把 canonical manuscript 转换到 \`paper_language\`。
+- 把 \`.lab/writing/terminology-glossary.md\` 当成写作期 glossary，用来沉淀全称、批准缩写、对外解释和可接受别名；它和 \`.lab/context/terminology-lock.md\` 的职责不同，不能混用。
 - 无论当前语言是什么，都要满足同一套学术可读性标准；如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就在首次出现时顺手说明它是什么、为什么在这里重要。
+- 第一次出现先写全称；如果后面要复用简称或缩写，就在首次出现时定义。
+- 同一个概念只保留一个自然语言 paper-facing 名称。
+- 正文里使用自然语言全称；如果后面要复用简称，就先在第一次出现时定义。
+- reader-facing prose 里不要使用包含 \`_\` 或 \`-\` 的标签名。
+- 内部标识符、配置键和实验包标签默认不要进正文；若必须出现，也只能给读者映射一次，然后移回正文之外。
 - 不要靠堆术语来制造学术感；如果本轮引入或改写了关键术语，就在用户可见的轮次总结里补一段简短术语说明，并把 terminology-clarity 自检写进 write iteration artifact。
 - 只加载当前 section guide，不要一次加载全部章节参考。
 - 如果当前 section 是 \`abstract\`、\`introduction\` 或 \`method\`，还必须继续读取本地 example bank：\`references/paper-writing/examples/index.md\`、对应的 examples index，以及 1-2 个具体 example 文件。
@@ -2649,7 +2709,9 @@ ZH_CONTENT[path.join(".codex", "skills", "lab", "stages", "auto.md")] = `# \`/la
 - 如果用户选择转换，就持久化 \`paper_language_finalization_decision: convert-to-paper-language\`
 - 如果当前写作目标是最终导出，且语言不一致，就不要在追问前先把最终论文正文改成 \`paper_language\`；先问、先持久化，再改稿
 - 如果当前写作目标是最终导出，且语言不一致，就在最新 write iteration 里记录语言决策审计：工作流语言、论文语言、最终语言决定、为什么这样决定，以及 workflow-language 交付稿路径
+- 把 \`.lab/writing/terminology-glossary.md\` 当成写作期 glossary，用来沉淀全称、批准缩写、对外解释和可接受别名
 - 当循环推进 \`write\` 时，无论 workflow language 还是 paper language，都要满足同一套学术可读性标准；如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就在首次出现时说明它是什么、为什么在这里重要
+- 当循环推进 \`write\` 时，第一次出现先写全称；如果后面要复用简称或缩写，就在首次出现时定义；一个概念只保留一个 paper-facing 名称，并尽量避免新造的连字符拼接标签
 - 不要靠术语堆积来制造学术感；如果本轮引入或改写了关键术语，就在用户可见的总结里补一段简短术语说明，并把 terminology-clarity 自检写进最新 write iteration
 - 不要把 \`sleep 30\`、单次 \`pgrep\` 或一次性的 \`metrics.json\` 探针当成 rung 主命令；这些只能算进度检查。
 - 当真实实验进程还活着时，只允许发进度更新并继续等待，不能把这一 rung 当作已经完成。

package/lib/lab_write_contract.json

@@ -1,8 +1,8 @@
 {
   "stage_prompt": {
-    "codex_en": "This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat a readable workflow-language deliverable as a real persisted artifact rather than a review layer. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, explain what they are and why they matter here instead of relying on unexplained jargon density to sound academic, then record the terminology-clarity self-check in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language deliverable first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language deliverable path in the latest write iteration, and only then edit the final manuscript in the chosen language.",
-    "claude_en": "This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat a readable workflow-language deliverable as a real persisted artifact rather than a review layer. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, explain what they are and why they matter here instead of relying on unexplained jargon density to sound academic, then record the terminology-clarity self-check in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language deliverable first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language deliverable path in the latest write iteration, and only then edit the final manuscript in the chosen language.",
-    "codex_zh": "本命令运行 `/lab:write` 阶段。把 `.codex/skills/lab/stages/write.md` 当成模板选择、paper-plan、section 参考、校验 gate、资产覆盖和最终 manuscript 规则的单一来源。读取与当前 section 对应的 paper-writing reference 和 bundled example-bank 文件，一次只修改一个 section；普通草稿轮次把写作校验当 warning，最终定稿或导出轮次必须满足 write-stage 的接受 gate。普通起草轮次先跟随 `workflow_language`，普通 `.tex` section 草稿也必须先停留在 `workflow_language`，不能把 `paper_language` 当成默认草稿语言，并把可阅读的 workflow-language 交付稿当成正式持久化产物，而不是 review 层。无论当前语言是什么，都要满足同一套学术可读性标准：如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就在首次出现时顺手说明它是什么、为什么在这里重要，不要靠堆术语来制造学术感，并把 terminology-clarity 自检写进 write iteration artifact。如果当前稿件将从托管默认 scaffold 开始，且还没有模板决定，就先追问一次：继续使用默认 scaffold，还是先接入模板目录。如果进入最终定稿时 `workflow_language` 与 `paper_language` 不一致，就先完成并保留 workflow-language 交付稿，再追问一次：保持当前语言，还是把 canonical manuscript 转成 `paper_language`；先持久化这个决定，再在最新 write iteration 里记录语言决策和 workflow-language 交付稿路径，最后才允许按该语言修改最终稿。",
-    "claude_zh": "本命令运行 lab workflow 的 `write` 阶段。把 `.claude/skills/lab/stages/write.md` 当成模板选择、paper-plan、section 参考、校验 gate、资产覆盖和最终 manuscript 规则的单一来源。读取与当前 section 对应的 paper-writing reference 和 bundled example-bank 文件，一次只修改一个 section；普通草稿轮次把写作校验当 warning，最终定稿或导出轮次必须满足 write-stage 的接受 gate。普通起草轮次先跟随 `workflow_language`，普通 `.tex` section 草稿也必须先停留在 `workflow_language`，不能把 `paper_language` 当成默认草稿语言，并把可阅读的 workflow-language 交付稿当成正式持久化产物，而不是 review 层。无论当前语言是什么，都要满足同一套学术可读性标准：如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就在首次出现时顺手说明它是什么、为什么在这里重要，不要靠堆术语来制造学术感，并把 terminology-clarity 自检写进 write iteration artifact。如果当前稿件将从托管默认 scaffold 开始，且还没有模板决定，就先追问一次：继续使用默认 scaffold，还是先接入模板目录。如果进入最终定稿时 `workflow_language` 与 `paper_language` 不一致，就先完成并保留 workflow-language 交付稿，再追问一次：保持当前语言，还是把 canonical manuscript 转成 `paper_language`；先持久化这个决定，再在最新 write iteration 里记录语言决策和 workflow-language 交付稿路径，最后才允许按该语言修改最终稿。"
+    "codex_en": "This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat a readable workflow-language deliverable as a real persisted artifact rather than a review layer. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, and do not use labels containing `_` or `-` in reader-facing prose. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language deliverable first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language deliverable path in the latest write iteration, and only then edit the final manuscript in the chosen language.",
+    "claude_en": "This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat a readable workflow-language deliverable as a real persisted artifact rather than a review layer. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, and do not use labels containing `_` or `-` in reader-facing prose. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language deliverable first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language deliverable path in the latest write iteration, and only then edit the final manuscript in the chosen language.",
+    "codex_zh": "本命令运行 `/lab:write` 阶段。把 `.codex/skills/lab/stages/write.md` 当成模板选择、paper-plan、section 参考、校验 gate、资产覆盖和最终 manuscript 规则的单一来源。读取与当前 section 对应的 paper-writing reference 和 bundled example-bank 文件，一次只修改一个 section；普通草稿轮次把写作校验当 warning，最终定稿或导出轮次必须满足 write-stage 的接受 gate。普通起草轮次先跟随 `workflow_language`，普通 `.tex` section 草稿也必须先停留在 `workflow_language`，不能把 `paper_language` 当成默认草稿语言，并把可阅读的 workflow-language 交付稿当成正式持久化产物，而不是 review 层。把 `.lab/writing/terminology-glossary.md` 作为写作期 glossary，用来沉淀全称、批准缩写、对外解释和可接受别名。无论当前语言是什么，都要满足同一套学术可读性标准：如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就先写全称；如果后面要复用短写，就在首次出现时定义；同时说明它是什么、为什么在这里重要，保持一个概念只有一个 paper-facing 名称，并尽量避免新造的连字符拼接标签。内部标识符默认不要进入 reader-facing prose；若必须出现，只能在完成一次读者映射后使用，并把 terminology-clarity 自检写进 write iteration artifact。如果当前稿件将从托管默认 scaffold 开始，且还没有模板决定，就先追问一次：继续使用默认 scaffold，还是先接入模板目录。如果进入最终定稿时 `workflow_language` 与 `paper_language` 不一致，就先完成并保留 workflow-language 交付稿，再追问一次：保持当前语言，还是把 canonical manuscript 转成 `paper_language`；先持久化这个决定，再在最新 write iteration 里记录语言决策和 workflow-language 交付稿路径，最后才允许按该语言修改最终稿。",
+    "claude_zh": "本命令运行 lab workflow 的 `write` 阶段。把 `.claude/skills/lab/stages/write.md` 当成模板选择、paper-plan、section 参考、校验 gate、资产覆盖和最终 manuscript 规则的单一来源。读取与当前 section 对应的 paper-writing reference 和 bundled example-bank 文件，一次只修改一个 section；普通草稿轮次把写作校验当 warning，最终定稿或导出轮次必须满足 write-stage 的接受 gate。普通起草轮次先跟随 `workflow_language`，普通 `.tex` section 草稿也必须先停留在 `workflow_language`，不能把 `paper_language` 当成默认草稿语言，并把可阅读的 workflow-language 交付稿当成正式持久化产物，而不是 review 层。把 `.lab/writing/terminology-glossary.md` 作为写作期 glossary，用来沉淀全称、批准缩写、对外解释和可接受别名。无论当前语言是什么，都要满足同一套学术可读性标准：如果本轮引入或改写了关键术语、缩写、指标名、机制名或系统标签，就先写全称；如果后面要复用短写，就在首次出现时定义；同时说明它是什么、为什么在这里重要，保持一个概念只有一个 paper-facing 名称，并尽量避免新造的连字符拼接标签。内部标识符默认不要进入 reader-facing prose；若必须出现，只能在完成一次读者映射后使用，并把 terminology-clarity 自检写进 write iteration artifact。如果当前稿件将从托管默认 scaffold 开始，且还没有模板决定，就先追问一次：继续使用默认 scaffold，还是先接入模板目录。如果进入最终定稿时 `workflow_language` 与 `paper_language` 不一致，就先完成并保留 workflow-language 交付稿，再追问一次：保持当前语言，还是把 canonical manuscript 转成 `paper_language`；先持久化这个决定，再在最新 write iteration 里记录语言决策和 workflow-language 交付稿路径，最后才允许按该语言修改最终稿。"
   }
 }

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

@@ -7,4 +7,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.claude/skills/lab/SKILL.md`.
 
 Execute the requested `/lab-write` 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 `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat a readable workflow-language deliverable as a real persisted artifact rather than a review layer. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, explain what they are and why they matter here instead of relying on unexplained jargon density to sound academic, then record the terminology-clarity self-check in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language deliverable first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language deliverable path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `write` stage of the lab workflow. Use `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat a readable workflow-language deliverable as a real persisted artifact rather than a review layer. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, and do not use labels containing `_` or `-` in reader-facing prose. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language deliverable first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language deliverable path in the latest write iteration, and only then edit the final manuscript in the chosen language.

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

@@ -6,4 +6,4 @@ argument-hint: section or writing target
 Use the installed `lab` skill at `.codex/skills/lab/SKILL.md`.
 
 Execute the requested `/lab:write` 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:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat a readable workflow-language deliverable as a real persisted artifact rather than a review layer. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, explain what they are and why they matter here instead of relying on unexplained jargon density to sound academic, then record the terminology-clarity self-check in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language deliverable first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language deliverable path in the latest write iteration, and only then edit the final manuscript in the chosen language.
+This command runs the `/lab:write` stage. Use `.codex/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section references, validator gates, asset coverage, and final manuscript rules. Read the matching paper-writing reference and any bundled example-bank files for the requested section, revise only one section, and keep draft rounds warning-only while final-draft or export rounds must satisfy the write-stage acceptance gates. Draft ordinary manuscript rounds in `workflow_language`, and ordinary `.tex` section drafts must stay in `workflow_language` instead of treating `paper_language` as the default draft language. Treat a readable workflow-language deliverable as a real persisted artifact rather than a review layer. Maintain `.lab/writing/terminology-glossary.md` as the write-stage glossary for full forms, approved short forms, reader-facing explanations, and aliases. Apply the same academic readability standard in every language: when the round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, use the full form first, define any short form at first mention, explain what the term is and why it matters here, keep one natural-language paper-facing name per concept, use natural-language full names in prose, and do not use labels containing `_` or `-` in reader-facing prose. Keep internal identifiers out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose, and record the terminology-clarity self-check in the write iteration artifact. If the manuscript would start from the managed scaffold and no template decision is recorded yet, ask once whether to keep the default scaffold or attach a template directory first. If finalization reaches a round where `workflow_language` and `paper_language` differ, finish and preserve the workflow-language deliverable first, then ask once whether to keep the draft language or convert the canonical manuscript to `paper_language`, persist that answer, record both the language decision and the workflow-language deliverable path in the latest write iteration, and only then edit the final manuscript in the chosen language.

package/package-assets/shared/lab/.managed/templates/terminology-glossary.md

@@ -0,0 +1,31 @@
+# Terminology Glossary
+
+Use this glossary during `/lab:write` to keep reader-facing naming stable.
+
+## Naming Rules
+
+- First mention should use the full form. If a short form or acronym will be reused, define it at first mention as `Full Form (Short Form)`.
+- Keep one canonical natural-language paper-facing name per concept.
+- Use natural-language full names in prose.
+- Do not use labels containing `_` or `-` in reader-facing prose.
+- Keep internal identifiers, config keys, and experiment package labels out of prose unless they are mapped once for the reader and then moved back out of prose.
+
+## Entries
+
+### Entry
+
+- Canonical paper-facing term:
+- Full form at first mention:
+- Approved short form or acronym:
+- Reader-facing explanation:
+- Why this term matters here:
+- First-use section:
+- Approved short natural-language alias, if any:
+- Forbidden aliases or labels:
+- Internal identifiers to avoid in prose:
+
+## Audit
+
+- Naming drift found this round:
+- Terms that still need a clearer explanation:
+- Terms that should move to appendix, tables, or implementation details:

package/package-assets/shared/lab/.managed/templates/write-iteration.md

@@ -30,8 +30,14 @@
 ## Terminology Clarity
 
 - Key terms introduced or revised this round:
+- Was `.lab/writing/terminology-glossary.md` updated:
+- Did first mention use the full form, with an approved short form only after that:
+- Did each concept keep one natural-language paper-facing name throughout the prose:
 - For each term, what it is and why it matters here:
+- Did any internal identifier leak into reader-facing prose:
+- Did any label containing `_` or `-` remain in reader-facing prose:
 - Were the first mentions explained in the prose:
+- Did any alias drift remain unresolved:
 - Remaining reader-facing jargon risk:
 
 ## Language Decision

package/package-assets/shared/lab/system/core.md

@@ -26,6 +26,7 @@ For auto-mode orchestration or long-running experiment campaigns, also read:
 
 - `.lab/context/` holds durable project research state plus lightweight workflow state.
 - `.lab/changes/`, `.lab/iterations/`, and `.lab/writing/` hold workflow control artifacts, lightweight manifests, and change-local harnesses.
+- `.lab/writing/terminology-glossary.md` is a write-stage glossary for full forms, approved short forms, reader-facing explanations, and alias discipline; it is separate from `.lab/context/terminology-lock.md`.
 - `.lab/.managed/` holds tool-managed templates and scripts.
 - Durable run outputs belong under the configured `results_root`, not inside `.lab/changes/`.
 - Figures and plots belong under the configured `figures_root`, not inside `.lab/changes/`.

package/package-assets/shared/skills/lab/SKILL.md

@@ -199,6 +199,11 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 - When the languages differ, do not rewrite final manuscript sections in `paper_language` before that question has been answered; ask first, persist the choice, then edit the final manuscript in the chosen language.
 - When the languages differ, record the workflow language, paper language, finalization decision, why the decision was chosen, and the workflow-language deliverable path in the latest write iteration artifact.
 - Apply the same reader-facing standard in both languages: when a round introduces or revises key terms, abbreviations, metrics, mechanism names, or system labels, explain them at first mention by saying what they are and why they matter here.
+- First mention should use the full form. If a short form or acronym will be reused, define it at first mention and then keep usage stable.
+- Keep one canonical natural-language paper-facing name per concept.
+- Use natural-language full names in prose, and define any approved short form once before reusing it.
+- Do not use labels containing `_` or `-` in reader-facing prose.
+- Keep internal identifiers out of prose unless they are mapped once for the reader and then moved back out of prose.
 - Do not rely on unexplained jargon density as a substitute for academic tone.
 - Bind each claim to evidence from `report`, iteration reports, or normalized summaries.
 - Use the write-stage contract in `.codex/skills/lab/stages/write.md` or `.claude/skills/lab/stages/write.md` as the single source of truth for template choice, paper-plan requirements, section-specific references, validator calls, asset coverage, and final manuscript gates.
@@ -207,6 +212,7 @@ Use this skill when the user invokes `/lab:*` or asks for the structured researc
 - Treat section-quality, claim-safety, and manuscript-delivery checks as the canonical acceptance gates for final-draft or export rounds.
 - For each subsection, explicitly cover motivation, design, and technical advantage when applicable.
 - Keep terminology stable across rounds and sections.
+- Maintain `.lab/writing/terminology-glossary.md` as the write-stage source for full forms, approved short forms, reader-facing explanations, allowed aliases, and terms that should stay out of prose.
 - When a round introduces or revises key terms, include a compact terminology note in the user-facing write summary and record the terminology-clarity self-check in the latest write iteration artifact.
 - If a claim is not supported by evidence, weaken or remove it.
 - Treat tables, figures, citations, and bibliography as core manuscript content rather than optional polish.

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

@@ -4,6 +4,7 @@
 
 - stable `report` artifact
 - approved framing artifact at `.lab/writing/framing.md`
+- current terminology glossary at `.lab/writing/terminology-glossary.md` when it already exists
 - iteration reports
 - normalized summaries
 - reviewer notes when available
@@ -26,6 +27,7 @@
 - `.lab/context/evidence-index.md`
 - `.lab/context/data-decisions.md`
 - `.lab/context/terminology-lock.md`
+- `.lab/writing/terminology-glossary.md` when it exists
 
 ## Context Write Set
 
@@ -92,6 +94,11 @@ Run these on every round:
 - Build a compact mini-outline before prose.
 - Academic readability standards are the same in `workflow_language` and `paper_language`; changing languages must not lower external-reader clarity.
 - If the current round introduces or revises key terms, abbreviations, metric names, mechanism names, or system labels, explain them at first mention by briefly stating what they are and why they matter here.
+- First mention should use the full form. If a short form or acronym will be reused later, define it at first mention as `Full Form (Short Form)` before switching to the short form.
+- Keep one canonical natural-language paper-facing name per concept. Do not let one concept drift across paper-facing names, experiment labels, and internal identifiers.
+- Use natural-language full names in prose. If an approved short form is needed later, define it once and reuse it consistently.
+- Do not use labels containing `_` or `-` in reader-facing prose.
+- Keep internal identifiers, config keys, and experiment package labels out of reader-facing prose unless they are mapped once for the reader and then moved back out of prose.
 - Do not use unexplained terminology density as a substitute for academic tone.
 - Build the paper asset plan before prose when the section carries introduction, experimental, method, related-work, or conclusion claims:
   - record the asset coverage targets and gaps for the current paper
@@ -135,6 +142,7 @@ Run these on every round:
 - If the manuscript validator fails, keep editing and asset generation until it passes; do not stop at prose-only completion.
 - Run a LaTeX compile smoke test when a local LaTeX toolchain is available; if not available, record the missing verification in the write iteration artifact.
 - Record what changed and why in a write-iteration artifact.
+- Maintain `.lab/writing/terminology-glossary.md` as the write-stage source for full forms, approved short forms, reader-facing explanations, and aliases whenever terminology changes.
 - When a round introduces or revises key terms, include a compact terminology note in the user-facing round summary and record the terminology-clarity self-check in the write-iteration artifact.
 - When `workflow_language` and `paper_language` differ, record the final manuscript language choice in the write-iteration artifact with the workflow language, paper language, finalization decision, and why that decision was chosen.
 - When `workflow_language` and `paper_language` differ, also record the persisted workflow-language deliverable path in the write-iteration artifact.
@@ -148,6 +156,7 @@ Run these on every round:
 
 - `.lab/writing/framing.md`
 - `.lab/writing/plan.md`
+- `.lab/writing/terminology-glossary.md`
 - `.lab/writing/iterations/<n>.md`
 - `<deliverables_root>/paper/main.tex`
 - `<deliverables_root>/paper/references.bib`
@@ -172,4 +181,4 @@ Run these on every round:
 - If a missing assumption would change the section structure or claim strength, ask one clarifying question at a time.
 - If there are multiple defensible narrative structures for the current section, present 2-3 approaches with trade-offs and recommend one before drafting.
 - Keep an approval gate when the chosen narrative structure would materially affect downstream sections or paper-level framing.
-- If the round introduces or revises key terms, abbreviations, metrics, or mechanism names, include a short terminology note in the final user-facing response that says what each term is and why it matters here, and point to the write iteration artifact for the full terminology-clarity self-check.
+- If the round introduces or revises key terms, abbreviations, metrics, or mechanism names, include a short terminology note in the final user-facing response that says the full form, approved short form if any, what each term is, and why it matters here, and point to `.lab/writing/terminology-glossary.md` plus the write iteration artifact for the full terminology audit.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlab",
-  "version": "0.1.38",
+  "version": "0.1.40",
   "description": "Strict /lab research workflow installer for Codex and Claude",
   "keywords": [
     "codex",