scientify 1.11.0 → 1.12.0

package/skills/metabolism-init/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: metabolism-init
+description: "Initialize knowledge metabolism for a research topic: broad literature survey, build baseline knowledge state, set up metabolism workspace"
+user-invokable: true
+---
+
+# Metabolism Initialization — Day 0 Baseline Building
+
+你正在为一个研究方向执行知识新陈代谢的初始化。这是 Day 0：构建领域基线知识。
+
+## 准备
+
+1. 检查 `metabolism/config.json` 是否存在
+   - 如果不存在：询问用户研究方向，创建 `metabolism/config.json`（包含 `keywords`, `categories`, `currentDay: 0`, `processed_ids: []`）
+   - 如果已存在且 `currentDay > 0`：提示用户已完成初始化，无需重复执行
+2. 创建目录结构（如不存在）：
+   ```
+   metabolism/
+     knowledge/
+     hypotheses/
+     experiments/
+     conversations/
+     log/
+   ```
+
+## Step 1: 宽泛调研
+
+委托 /research-collect 执行宽泛调研（不限日期），构建初始知识：
+
+```
+sessions_spawn({
+  task: "/research-collect\n研究主题: {从 config.json 的 keywords 提取}\n这是 Day 0 基线构建，请做宽泛调研（不限日期），覆盖领域经典工作和近期进展。\n预期产出: papers/_meta/*.json + papers/_downloads/",
+  label: "Day 0 Baseline Survey",
+  runTimeoutSeconds: 1800
+})
+```
+
+spawned session 共享工作目录，无需传路径。等待完成后，读取 `papers/_meta/*.json` 获取论文列表。
+
+## Step 2: 阅读与知识提取
+
+对每篇论文：
+- 读 .tex 源码（优先）或 PDF
+- 提取：核心方法、关键结论、领域现状
+
+将每篇论文的 arXiv ID / DOI 追加到 `metabolism/config.json` 的 `processed_ids`。
+
+## Step 3: 构建初始知识状态
+
+创建 `metabolism/knowledge/_index.md`：
+- Research Goal（从 config.json 提取）
+- Topics 表格（按论文主题聚类）
+- Cross-topic Links（如有）
+- Timeline（记录 Day 0）
+
+为每个识别出的主题创建 `metabolism/knowledge/topic-{name}.md`：
+- 已知方法
+- 关键论文与结论
+- 开放问题
+
+## Step 4: 记录日志
+
+写入 `metabolism/log/{YYYY-MM-DD}-init.md`：
+
+```markdown
+# Day 0 — Initialization
+
+日期: {YYYY-MM-DD}
+论文: {N} 篇
+主题: {列出识别的主题}
+状态: 基线构建完成
+```
+
+更新 `metabolism/config.json`：`currentDay` 设为 1。
+
+## 行为约束
+
+1. 不捏造论文中未出现的事实性声明
+2. 自主运行，不向人类提问（除初始配置外）
+3. 修改知识文件前必须先读取当前内容（如存在）

package/skills/{literature-survey → research-collect}/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: literature-survey
-description: "Use this when the user wants to find, download, or collect academic papers on a topic. Searches arXiv, filters by relevance, downloads PDFs and sources, clusters by research direction."
+name: research-collect
+description: "[Read when prompt contains /research-collect]"
 metadata:
   {
     "openclaw":
@@ -14,10 +14,12 @@ metadata:
 
 **Don't ask permission. Just do it.**
 
+**Workspace:** `$W` = working directory provided in task parameter.
+
 ## Output Structure
 
 ```
-~/.openclaw/workspace/projects/{project-id}/
+$W/
 ├── survey/
 │   ├── search_terms.json      # 检索词列表
 │   └── report.md              # 最终报告
@@ -38,17 +40,13 @@ metadata:
 
 ### Phase 1: 准备
 
+确保工作目录结构存在：
+
 ```bash
-ACTIVE=$(cat ~/.openclaw/workspace/projects/.active 2>/dev/null)
-if [ -z "$ACTIVE" ]; then
-  PROJECT_ID="<topic-slug>"
-  mkdir -p ~/.openclaw/workspace/projects/$PROJECT_ID/{survey,papers/_downloads,papers/_meta}
-  echo "$PROJECT_ID" > ~/.openclaw/workspace/projects/.active
-fi
-PROJECT_DIR="$HOME/.openclaw/workspace/projects/$(cat ~/.openclaw/workspace/projects/.active)"
+mkdir -p "$W/survey" "$W/papers/_downloads" "$W/papers/_meta"
 ```
 
-生成 4-8 个检索词，保存到 `survey/search_terms.json`。
+生成 4-8 个检索词，保存到 `$W/survey/search_terms.json`。
 
 ---
 
@@ -76,13 +74,13 @@ arxiv_search({ query: "<term>", max_results: 30 })
 ```
 arxiv_download({
   arxiv_ids: ["<有用的论文ID>"],
-  output_dir: "$PROJECT_DIR/papers/_downloads"
+  output_dir: "papers/_downloads"
 })
 ```
 
 #### 2.4 写入元数据
 
-为每篇下载的论文创建元数据文件 `papers/_meta/{arxiv_id}.json`：
+为每篇下载的论文创建元数据文件 `$W/papers/_meta/{arxiv_id}.json`：
 
 ```json
 {
@@ -105,7 +103,7 @@ arxiv_download({
 
 #### 3.1 选择高分论文
 
-读取 `papers/_meta/` 下得分 ≥4 的论文，选出 **Top 5** 最相关论文。
+读取 `$W/papers/_meta/` 下得分 ≥4 的论文，选出 **Top 5** 最相关论文。
 
 #### 3.2 搜索参考仓库
 
@@ -116,41 +114,32 @@ arxiv_download({
 
 使用 `github_search` 工具：
 ```javascript
-// 示例：
 github_search({
   query: "{paper_title} implementation",
   max_results: 10,
   sort: "stars",
-  language: "python"  // 可选：根据论文领域选择语言
-})
-
-// 如果有具体方法名：
-github_search({
-  query: "{method_name} {author_last_name}",
-  max_results: 5
+  language: "python"
 })
 ```
 
-**提示**：如果需要 GitHub API 高频率限制，设置环境变量 `GITHUB_TOKEN`。
-
 #### 3.3 筛选与 clone
 
 对搜索到的仓库，评估：
 - Star 数（建议 >100）
 - 代码质量（有 README、有 requirements.txt、代码结构清晰）
-- 与论文的匹配度（README 中引用了论文 / 实现了论文中的方法）
+- 与论文的匹配度
 
-选择 **3-5 个**最相关的仓库，clone 到 `repos/`：
+选择 **3-5 个**最相关的仓库，clone 到 `$W/repos/`：
 
 ```bash
-mkdir -p "$PROJECT_DIR/repos"
-cd "$PROJECT_DIR/repos"
+mkdir -p "$W/repos"
+cd "$W/repos"
 git clone --depth 1 <repo_url>
 ```
 
 #### 3.4 写入选择报告
 
-创建 `$PROJECT_DIR/prepare_res.md`：
+创建 `$W/prepare_res.md`：
 
 ```markdown
 # 参考仓库选择
@@ -179,7 +168,7 @@ git clone --depth 1 <repo_url>
 #### 4.1 读取所有元数据
 
 ```bash
-ls $PROJECT_DIR/papers/_meta/
+ls $W/papers/_meta/
 ```
 
 读取所有 `.json` 文件，汇总论文列表。
@@ -191,15 +180,15 @@ ls $PROJECT_DIR/papers/_meta/
 #### 4.3 创建文件夹并移动
 
 ```bash
-mkdir -p "$PROJECT_DIR/papers/data-driven"
-mv "$PROJECT_DIR/papers/_downloads/2401.12345" "$PROJECT_DIR/papers/data-driven/"
+mkdir -p "$W/papers/data-driven"
+mv "$W/papers/_downloads/2401.12345" "$W/papers/data-driven/"
 ```
 
 ---
 
 ### Phase 5: 生成报告
 
-创建 `survey/report.md`：
+创建 `$W/survey/report.md`：
 - 调研概要（检索词数、论文数、方向数）
 - 各研究方向概述
 - Top 10 论文
@@ -222,3 +211,4 @@ mv "$PROJECT_DIR/papers/_downloads/2401.12345" "$PROJECT_DIR/papers/data-driven/
 |------|---------|
 | `arxiv_search` | 搜索论文（无副作用） |
 | `arxiv_download` | 下载 .tex/.pdf（需绝对路径） |
+| `github_search` | 搜索参考仓库 |

package/skills/research-experiment/SKILL.md

@@ -15,7 +15,7 @@ metadata:
 
 **Don't ask permission. Just do it.**
 
-**Workspace:** See `../_shared/workspace-spec.md`. Set `$W` to the active project directory.
+**Workspace:** `$W` = working directory provided in task parameter.
 
 ## Prerequisites
 

package/skills/research-implement/SKILL.md

@@ -15,7 +15,7 @@ metadata:
 
 **Don't ask permission. Just do it.**
 
-**Workspace:** See `../_shared/workspace-spec.md`. Set `$W` to the active project directory.
+**Workspace:** `$W` = working directory provided in task parameter.
 
 ## Prerequisites
 

package/skills/research-pipeline/SKILL.md

@@ -94,22 +94,17 @@ task 必须以 `/skill-name` 开头（触发 slash command 解析），后续行
 
 ## Workspace
 
-See `../_shared/workspace-spec.md`. Set `$W` to the active project directory.
+`$W` = agent workspace root (see AGENTS.md for layout).
 
 ---
 
 ## Step 0: 初始化
 
-```bash
-ACTIVE=$(cat ~/.openclaw/workspace/projects/.active 2>/dev/null)
-```
+`$W` 即当前 agent 的工作目录（AGENTS.md 中定义）。
 
-如果没有 active project：
-1. 问用户：研究主题是什么？
-2. 创建项目目录
-3. 写入 `task.json`
+检查 `$W/SOUL.md` 是否包含研究方向信息。如果没有（BOOTSTRAP 未完成），提示用户先完成 BOOTSTRAP 配置。
 
-设置 `$W = ~/.openclaw/workspace/projects/{project-id}`
+确保 `$W` 下存在必要的子目录（如 `survey/`, `papers/` 等）。
 
 ---
 
@@ -122,8 +117,8 @@ ACTIVE=$(cat ~/.openclaw/workspace/projects/.active 2>/dev/null)
 **检查:** `$W/papers/_meta/` 目录存在且有 `.json` 文件？
 
 **如果缺失，调用 sessions_spawn 工具（然后停止，等待完成通知）：**
-- task: `"/literature-survey\n工作目录: {$W绝对路径}\n研究主题: {从task.json提取}\n请搜索、筛选、下载论文到工作目录的 papers/ 下。"`
-- label: `"Literature Survey"`
+- task: `"/research-collect\n工作目录: {$W绝对路径}\n研究主题: {从task.json提取}\n请搜索、筛选、下载论文到工作目录的 papers/ 下。"`
+- label: `"Research Collect"`
 - runTimeoutSeconds: `1800`
 
 **验证:** `ls $W/papers/_meta/*.json` 至少有 3 个文件

package/skills/research-plan/SKILL.md

@@ -14,7 +14,7 @@ metadata:
 
 **Don't ask permission. Just do it.**
 
-**Workspace:** See `../_shared/workspace-spec.md`. Set `$W` to the active project directory.
+**Workspace:** `$W` = working directory provided in task parameter.
 
 ## Prerequisites
 
@@ -23,8 +23,8 @@ metadata:
 | `$W/task.json` | /research-pipeline or user |
 | `$W/survey_res.md` | /research-survey |
 | `$W/notes/paper_*.md` | /research-survey |
-| `$W/repos/` | /literature-survey Phase 3 |
-| `$W/prepare_res.md` | /literature-survey Phase 3 |
+| `$W/repos/` | /research-collect Phase 3 |
+| `$W/prepare_res.md` | /research-collect Phase 3 |
 
 **If `survey_res.md` is missing, STOP:** "需要先运行 /research-survey 完成深度分析"
 

package/skills/research-review/SKILL.md

@@ -15,7 +15,7 @@ metadata:
 
 **Don't ask permission. Just do it.**
 
-**Workspace:** See `../_shared/workspace-spec.md`. Set `$W` to the active project directory.
+**Workspace:** `$W` = working directory provided in task parameter.
 
 ## Prerequisites
 

package/skills/research-survey/SKILL.md

@@ -14,7 +14,7 @@ metadata:
 
 **Don't ask permission. Just do it.**
 
-**Workspace:** See `../_shared/workspace-spec.md`. Set `$W` to the active project directory.
+**Workspace:** `$W` = working directory provided in task parameter.
 
 ## Prerequisites
 
@@ -22,12 +22,12 @@ Read and verify these files exist before starting:
 
 | File | Source |
 |------|--------|
-| `$W/papers/_meta/*.json` | /literature-survey |
-| `$W/papers/_downloads/` or `$W/papers/{direction}/` | /literature-survey |
-| `$W/repos/` | /literature-survey Phase 3 |
-| `$W/prepare_res.md` | /literature-survey Phase 3 |
+| `$W/papers/_meta/*.json` | /research-collect |
+| `$W/papers/_downloads/` or `$W/papers/{direction}/` | /research-collect |
+| `$W/repos/` | /research-collect Phase 3 |
+| `$W/prepare_res.md` | /research-collect Phase 3 |
 
-**If papers are missing, STOP:** "需要先运行 /literature-survey 完成论文下载"
+**If papers are missing, STOP:** "需要先运行 /research-collect 完成论文下载"
 
 **Note:** 如果 `prepare_res.md` 中注明"无可用参考仓库"，代码映射步骤可跳过，但需在 survey_res.md 中标注。
 

package/skills/write-review-paper/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: write-review-paper
-description: "Use this when the user wants to write a literature review, survey paper, or thesis chapter from existing papers. Guides reading strategy, note-taking, synthesis, and academic writing. NOT for searching new papers (/literature-survey) or generating ideas (/idea-generation)."
+description: "Use this when the user wants to write a literature review, survey paper, or thesis chapter from existing papers. Guides reading strategy, note-taking, synthesis, and academic writing. NOT for searching new papers (/research-collect) or generating ideas (/idea-generation)."
 metadata:
   {
     "openclaw":
@@ -16,18 +16,18 @@ metadata:
 
 Guide for writing a structured literature review or survey paper from papers you've already collected. This skill helps with reading strategy, note organization, and academic writing.
 
-**Workspace:** See `../_shared/workspace-spec.md` for directory structure. Outputs go to `$WORKSPACE/review/`.
+**Workspace:** `$W` = working directory provided in task parameter. Outputs go to `$W/review/`.
 
 ## Prerequisites
 
 Before starting, ensure you have:
-1. Papers collected in `$WORKSPACE/papers/`
-2. Ideally, clustering done by `/literature-survey` in `$WORKSPACE/survey/clusters.json`
+1. Papers collected in `$W/papers/`
+2. Ideally, clustering done by `/research-collect` in `$W/survey/clusters.json`
 
-Check active project:
+Check workspace:
 ```bash
-cat ~/.openclaw/workspace/projects/.active 2>/dev/null
-ls $WORKSPACE/papers/
+ls $W/papers/
+ls $W/survey/ 2>/dev/null
 ```
 
 ---
@@ -44,7 +44,7 @@ Based on clusters from survey, prioritize reading:
 | P2 (重要) | 主要方法论、重要实验结果 | 读摘要+方法+实验 |
 | P3 (参考) | 辅助材料、边缘相关 | 仅读摘要 |
 
-Create `$WORKSPACE/review/reading_plan.md`:
+Create `$W/review/reading_plan.md`:
 
 ```markdown
 # Reading Plan
@@ -62,7 +62,7 @@ Create `$WORKSPACE/review/reading_plan.md`:
 
 ### 1.2 Reading Notes Template
 
-For each paper, create `$WORKSPACE/review/notes/{paper_id}.md` using template in `references/note-template.md`.
+For each paper, create `$W/review/notes/{paper_id}.md` using template in `references/note-template.md`.
 
 ---
 
@@ -70,7 +70,7 @@ For each paper, create `$WORKSPACE/review/notes/{paper_id}.md` using template in
 
 ### 2.1 Build Comparison Table
 
-Create `$WORKSPACE/review/comparison.md`:
+Create `$W/review/comparison.md`:
 
 ```markdown
 # Method Comparison
@@ -83,7 +83,7 @@ Create `$WORKSPACE/review/comparison.md`:
 
 ### 2.2 Timeline Analysis
 
-Create `$WORKSPACE/review/timeline.md`:
+Create `$W/review/timeline.md`:
 
 ```markdown
 # Research Timeline
@@ -106,7 +106,7 @@ Create `$WORKSPACE/review/timeline.md`:
 
 ### 2.3 Taxonomy Design
 
-Create `$WORKSPACE/review/taxonomy.md`:
+Create `$W/review/taxonomy.md`:
 
 ```markdown
 # Taxonomy of Approaches
@@ -140,7 +140,7 @@ Create `$WORKSPACE/review/taxonomy.md`:
 
 ### 3.1 Survey Paper Template
 
-Create `$WORKSPACE/review/draft.md` using template in `references/survey-template.md`.
+Create `$W/review/draft.md` using template in `references/survey-template.md`.
 
 Key sections: Abstract → Introduction → Background → Taxonomy → Comparison → Datasets → Future Directions → Conclusion
 
@@ -198,7 +198,7 @@ For a thesis chapter:
 ## Output Files
 
 ```
-$WORKSPACE/review/
+$W/review/
 ├── reading_plan.md       # 阅读计划
 ├── notes/                # 阅读笔记
 │   ├── {paper_id}.md

package/skills/_shared/workspace-spec.md

@@ -1,164 +0,0 @@
-# Workspace Directory Specification
-
-All Scientify skills share a unified project-based workspace structure.
-
-## Base Path
-
-```
-~/.openclaw/workspace/projects/
-├── .active                      # Current project ID (plain text)
-├── {project-id}/                # Each research topic has its own project
-│   └── ...
-└── {another-project}/
-```
-
-## Project Structure
-
-```
-~/.openclaw/workspace/projects/{project-id}/
-├── project.json                 # Project metadata
-├── task.json                    # Research task definition
-│
-├── survey/                      # /literature-survey outputs
-│   ├── search_terms.json        # Generated search keywords
-│   ├── raw_results.json         # All search results
-│   ├── filtered_papers.json     # Papers with relevance scores
-│   ├── clusters.json            # Clustered by research direction
-│   └── report.md                # Final survey report
-│
-├── papers/                      # Downloaded paper sources
-│   ├── {direction-1}/           # Organized by cluster
-│   │   ├── paper_list.md
-│   │   └── {arxiv_id}/          # .tex source files
-│   ├── {direction-2}/
-│   └── uncategorized/
-│
-├── repos/                       # Cloned reference repositories
-│   ├── {repo-name-1}/
-│   └── {repo-name-2}/
-│
-├── ideas/                       # /idea-generation outputs
-│   ├── gaps.md                  # Identified research gaps
-│   ├── idea_1.md ... idea_5.md  # Generated ideas
-│   ├── selected_idea.md         # Enhanced best idea
-│   ├── implementation_report.md # Code mapping
-│   └── summary.md               # Final summary
-│
-├── review/                      # /write-review-paper outputs
-│   ├── reading_plan.md          # Prioritized reading list
-│   ├── notes/                   # Per-paper reading notes
-│   │   └── {paper_id}.md
-│   ├── comparison.md            # Method comparison table
-│   ├── timeline.md              # Research timeline
-│   ├── taxonomy.md              # Classification system
-│   ├── draft.md                 # Survey paper draft
-│   └── bibliography.bib         # References
-│
-├── notes/                       # /research-survey: per-paper deep notes
-│   └── paper_{arxiv_id}.md
-├── survey_res.md                # /research-survey: deep analysis + method comparison
-├── plan_res.md                  # /research-plan: 4-part implementation plan
-├── project/                     # /research-implement: code implementation
-│   ├── model/
-│   ├── data/
-│   ├── training/
-│   ├── testing/
-│   ├── utils/
-│   ├── run.py
-│   └── requirements.txt
-├── ml_res.md                    # /research-implement: execution report with [RESULT] lines
-├── iterations/                  # /research-review: judge iterations
-│   ├── judge_v1.md
-│   └── judge_v2.md
-├── experiment_res.md            # /research-experiment: full training + ablation results
-└── knowledge_state/             # scheduled research state artifacts
-    ├── knowledge/
-    ├── paper_notes/
-    ├── daily_changes/
-    ├── hypotheses/
-    ├── logs/
-    ├── state.json
-    └── events.jsonl
-```
-
-## Conventions
-
-### File Existence = Step Completion
-
-Check output file before executing any step. If exists, skip.
-
-Enables:
-- **Crash recovery**: resume from last completed step
-- **Incremental progress**: rerunning skips completed work
-- **Transparency**: inspect progress by listing directory
-
-### Project Metadata
-
-**project.json:**
-```json
-{
-  "id": "battery-rul-prediction",
-  "name": "Battery RUL Prediction",
-  "created": "2024-01-15T10:00:00Z",
-  "topics": ["battery", "remaining useful life", "prediction"]
-}
-```
-
-**task.json:**
-```json
-{
-  "domain": "battery health",
-  "focus": "RUL prediction using transformer",
-  "date_limit": "2024-01-01",
-  "created": "2024-01-15"
-}
-```
-
-### Immutability
-
-Once written, do NOT modify outputs unless user explicitly asks.
-Exception: `project/` is mutable during implement-review-iterate loop.
-
-### Active Project
-
-```bash
-# Read active project
-cat ~/.openclaw/workspace/projects/.active
-
-# Set active project
-echo "battery-rul-prediction" > ~/.openclaw/workspace/projects/.active
-
-# Set $WORKSPACE variable
-WORKSPACE=~/.openclaw/workspace/projects/$(cat ~/.openclaw/workspace/projects/.active)
-```
-
-### Scheduled Subscription Storage
-
-`research-subscription` writes both global incremental state and project-level knowledge_state files.
-
-- Scheduled jobs are stored in OpenClaw cron storage.
-- Incremental dedupe state/logs are stored under `~/.openclaw/workspace/scientify/`:
-  - `literature-state.json`
-  - `literature-push-log.jsonl`
-- Project-level research state is stored under:
-  - `~/.openclaw/workspace/projects/{project-id}/knowledge_state/`
-  - Includes `knowledge/`, `paper_notes/`, `daily_changes/`, `hypotheses/`, `logs/`, `state.json`, `events.jsonl`
-  - `paper_notes/` stores per-paper deep-reading records (domain/subdomains/cross-domain links/research goal/approach/design/contributions/practical insights/must-understand points/limitations/evidence anchors).
-- Use `openclaw cron list --all --json` for global inspection.
-- Use `/research-subscriptions` for scope-aware inspection within Scientify.
-- Use `/research-unsubscribe` to remove jobs for the current sender/channel scope.
-
-## Skill Outputs Summary
-
-| Skill | Primary Outputs |
-|-------|-----------------|
-| `/literature-survey` | `survey/`, `papers/` |
-| `/research-survey` | `notes/paper_*.md`, `survey_res.md` |
-| `/research-plan` | `plan_res.md` |
-| `/research-implement` | `project/`, `ml_res.md` |
-| `/research-review` | `iterations/judge_v*.md` |
-| `/research-experiment` | `experiment_res.md` |
-| `/research-pipeline` | Orchestrator — spawns the above 5 skills in sequence |
-| `/idea-generation` | `ideas/` |
-| `/write-review-paper` | `review/` |
-| `research-subscription` | Creates OpenClaw cron jobs, updates global incremental state (`~/.openclaw/workspace/scientify/`), and persists project-level `knowledge_state/` artifacts for traceability |