superlab 0.1.0 → 0.1.2

package/README.md

@@ -8,7 +8,7 @@ It combines:
 
 - command adapters for Codex and Claude
 - a shared `/lab` skill with stage-specific rules
-- OpenSpec-compatible `spec-driven` artifacts
+- lab-native change artifacts under `.superlab/changes/`
 - bounded Ralph Wiggum style iteration for experiments
 - helper scripts for run registration and evaluation summaries
 
@@ -45,6 +45,8 @@ This writes:
 - `.codex/skills/lab/`
 - `.claude/commands/lab/*.md`
 - `.claude/skills/lab/`
+- `.superlab/config/workflow.json`
+- `.superlab/changes/`
 - `.superlab/templates/`
 - `.superlab/scripts/`
 - `.superlab/examples/`
@@ -77,37 +79,32 @@ superlab init --lang zh
 superlab init --lang en
 ```
 
-This language setting only affects installed command and skill text shown to the user. It does not control experiment outputs, reports, or the final paper language.
+This installer also writes `.superlab/config/workflow.json`, which is the global contract for:
+
+- `workflow_language`
+- `paper_language`
+- `paper_format`
+
+Stages should follow that file rather than guess language locally.
 
 ## Requirements
 
 - Node.js 18+
 - Python 3.10+
 - Git
-- OpenSpec CLI installed and available as `openspec-cn`
-- For `/lab:write`: install the companion `research-paper-writing` skill from `Research-Paper-Writing-Skills`
-
-Check the dependency with:
 
-```bash
-bash .superlab/scripts/check_openspec.sh
-```
-
-`/lab:write` expects the companion skill at one of these locations:
-
-- Codex: `~/.codex/skills/research-paper-writing/`
-- Claude project: `.claude/skills/research-paper-writing/`
+`/lab:write` ships with vendored paper-writing references under the installed `lab` skill, so it does not depend on an extra runtime skill installation.
 
 ## Command Set
 
 - `/lab:idea` researches an idea, critiques it, and writes the initial research framing.
-- `/lab:spec` converts the approved idea into OpenSpec `proposal`, `design`, `spec`, and `tasks` artifacts.
+- `/lab:spec` converts the approved idea into one `.superlab/changes/<change-id>/` directory.
 - `/lab:run` executes a small-scale validation run and establishes the evaluation pipeline.
 - `/lab:iterate` runs bounded experiment loops with fixed mission, explicit thresholds, and per-round reports.
 - `/lab:review` audits documents and results in reviewer mode.
 - `/lab:report` produces the final report from accumulated artifacts.
 - `/lab:write` converts stable report artifacts into paper sections through small writing rounds.
-  It reads the exact upstream section references from the companion `research-paper-writing` skill.
+  It reads vendored section references derived from `Research-Paper-Writing-Skills`.
 
 See the source command docs in [commands/codex/lab.md](/Users/zhouhao119/coding/write/commands/codex/lab.md) and [commands/claude/lab.md](/Users/zhouhao119/coding/write/commands/claude/lab.md). The npm package installs real command assets from `package-assets/`.
 
@@ -125,22 +122,25 @@ See the source command docs in [commands/codex/lab.md](/Users/zhouhao119/coding/
 ## Typical Flow
 
 1. Run `/lab:idea` to produce the initial idea artifact.
-2. Run `/lab:spec` to convert the idea into OpenSpec `spec-driven` artifacts.
+2. Run `/lab:spec` to convert the idea into one self-contained lab change directory.
 3. Run `/lab:run` to verify the experiment path and register the first run.
 4. Run `/lab:iterate` to improve against fixed targets using bounded iterations.
 5. Run `/lab:review` whenever you need reviewer-grade critique.
 6. Run `/lab:report` to synthesize the final report.
 7. Run `/lab:write` to draft paper sections from stable report evidence.
 
-`/lab:write` typically writes:
+`/lab:write` writes final manuscript output to:
+
+- `docs/paper/paper.tex`
+- `docs/paper/sections/*.tex`
+
+Internal writing-control artifacts stay under:
 
-- `docs/lab/paper/plan.md`
-- `docs/lab/paper/sections/*.md`
-- `docs/lab/paper/write-iterations/*.md`
+- `.superlab/write/plan.md`
+- `.superlab/write/iterations/*.md`
 
 ## Helper Scripts
 
-- `scripts/check_openspec.sh` checks whether OpenSpec CLI is available.
 - `scripts/register_run.py` records run metadata in a JSON registry.
 - `scripts/eval_report.py` normalizes metrics into a comparable summary.
 - `scripts/summarize_iterations.py` rolls multiple iteration summaries into one file.
@@ -157,4 +157,4 @@ See the source command docs in [commands/codex/lab.md](/Users/zhouhao119/coding/
 
 ## Attribution
 
-`superlab` is OpenSpec-compatible and borrows workflow discipline ideas from OpenSpec, superpowers, and Ralph Wiggum style bounded iteration. It is an independent workflow package, not an official OpenSpec project.
+`superlab` borrows workflow discipline ideas from OpenSpec, superpowers, and Ralph Wiggum style bounded iteration. Its vendored writing references are adapted from `Research-Paper-Writing-Skills`.

package/README.zh-CN.md

@@ -6,7 +6,7 @@
 
 - Codex 和 Claude 的命令安装入口
 - 共享的 `/lab` skill
-- 兼容 OpenSpec `spec-driven` 的工件模板
+- 基于 `lab` 自己目录约定的 change 工件
 - 带有 Ralph Wiggum 风格边界控制的实验迭代
 - 运行登记、评估汇总和结果校验脚本
 
@@ -43,6 +43,8 @@ npx github:zhouhaoUCAS/superlab init
 - `.codex/skills/lab/`
 - `.claude/commands/lab/*.md`
 - `.claude/skills/lab/`
+- `.superlab/config/workflow.json`
+- `.superlab/changes/`
 - `.superlab/templates/`
 - `.superlab/scripts/`
 - `.superlab/examples/`
@@ -75,37 +77,32 @@ superlab init --lang zh
 superlab init --lang en
 ```
 
-这个语言设置只影响安装到 `.codex/`、`.claude/` 的命令和技能展示文案，不影响实验输出、report 内容或最终论文语言。
+安装器还会写入 `.superlab/config/workflow.json`。这个文件是全局约束，至少控制：
+
+- `workflow_language`
+- `paper_language`
+- `paper_format`
+
+后续 stage 应该按这个配置决定语言和论文格式，而不是各模板自己猜。
 
 ## 依赖
 
 - Node.js 18+
 - Python 3.10+
 - Git
-- OpenSpec CLI，并且命令名为 `openspec-cn`
-- `/lab:write` 还依赖 `Research-Paper-Writing-Skills` 提供的 companion `research-paper-writing` skill
-
-检查 OpenSpec CLI：
 
-```bash
-bash .superlab/scripts/check_openspec.sh
-```
-
-`/lab:write` 预期 companion skill 位于：
-
-- Codex: `~/.codex/skills/research-paper-writing/`
-- Claude 项目: `.claude/skills/research-paper-writing/`
+`/lab:write` 自带 vendored 的 paper-writing 章节参考，不再依赖额外安装一个运行时写作 skill。
 
 ## 命令集合
 
 - `/lab:idea` 调研 idea、文献、数据集、指标和 baseline，并输出初始方案。
-- `/lab:spec` 把批准后的方案转换成 OpenSpec `proposal`、`design`、`spec`、`tasks`。
+- `/lab:spec` 把批准后的方案转换成一个统一的 `.superlab/changes/<change-id>/` 目录。
 - `/lab:run` 执行最小可运行实验，并建立首版评估链路。
 - `/lab:iterate` 以固定 mission、固定阈值和最大轮次做有边界的实验迭代。
 - `/lab:review` 以审稿人模式检查方法、对照、公平性、泄漏和统计问题。
 - `/lab:report` 根据累积工件生成最终实验报告。
 - `/lab:write` 把稳定的 report 工件转成论文 section，并按小步方式逐轮修改。
-  它会直接读取 companion `research-paper-writing` skill 里的原始章节参考。
+  它会读取随 `lab` 一起安装的 vendored 章节参考，这些参考来源于 `Research-Paper-Writing-Skills`。
 
 ## 使用流程
 
@@ -118,11 +115,15 @@ bash .superlab/scripts/check_openspec.sh
 7. 最后用 `/lab:report` 产出总报告。
 8. 用 `/lab:write` 把稳定结果写成论文各 section。
 
-`/lab:write` 通常会写入：
+`/lab:write` 最终只把论文写入：
+
+- `docs/paper/paper.tex`
+- `docs/paper/sections/*.tex`
+
+内部写作控制工件放在：
 
-- `docs/lab/paper/plan.md`
-- `docs/lab/paper/sections/*.md`
-- `docs/lab/paper/write-iterations/*.md`
+- `.superlab/write/plan.md`
+- `.superlab/write/iterations/*.md`
 
 ## 仓库内容
 
@@ -139,4 +140,4 @@ bash .superlab/scripts/check_openspec.sh
 
 ## 致谢
 
-`superlab` 兼容 OpenSpec，并借鉴了 OpenSpec、superpowers 和 Ralph Wiggum 的流程纪律。它是一个独立的开源工作流包，不是 OpenSpec 官方项目。
+`superlab` 借鉴了 OpenSpec、superpowers 和 Ralph Wiggum 的流程纪律。随包提供的写作参考改编自 `Research-Paper-Writing-Skills`。