From 5b1c3a1f67a2b3a7e6dc617064c50f2f9818d7a5 Mon Sep 17 00:00:00 2001
From: JunkaiWang-TheoPhy <1181100960@qq.com>
Date: Thu, 2 Apr 2026 20:55:38 +0800
Subject: [PATCH 1/3] feat: add diversity skills and improve onboarding/status
 guidance

---
 README.en.md                                  |   5 +
 README.md                                     |  14 ++
 openclaw.plugin.json                          |   3 +
 skills/algorithm-selection/SKILL.md           | 103 ++++++++++
 .../references/candidate-template.md          |  13 ++
 .../references/selection-template.md          |  39 ++++
 skills/baseline-runner/SKILL.md               | 103 ++++++++++
 .../references/baseline-matrix-template.md    |   9 +
 .../references/baseline-report-template.md    |  25 +++
 skills/dataset-validate/SKILL.md              | 104 ++++++++++
 .../references/data-validation-template.md    |  38 ++++
 src/commands.ts                               | 180 +++++++++++++++++-
 src/templates/bootstrap.ts                    |  34 +++-
 13 files changed, 668 insertions(+), 2 deletions(-)
 create mode 100644 skills/algorithm-selection/SKILL.md
 create mode 100644 skills/algorithm-selection/references/candidate-template.md
 create mode 100644 skills/algorithm-selection/references/selection-template.md
 create mode 100644 skills/baseline-runner/SKILL.md
 create mode 100644 skills/baseline-runner/references/baseline-matrix-template.md
 create mode 100644 skills/baseline-runner/references/baseline-report-template.md
 create mode 100644 skills/dataset-validate/SKILL.md
 create mode 100644 skills/dataset-validate/references/data-validation-template.md

diff --git a/README.en.md b/README.en.md
index cf163fd..e75c804 100644
--- a/README.en.md
+++ b/README.en.md
@@ -226,6 +226,8 @@ Or invoke a specific skill directly with a slash command:
 /research-pipeline
 /research-collect
 /idea-generation
+/algorithm-selection
+/dataset-validate
 ```
 
 ### 3. Monitor sub-agent progress
@@ -262,7 +264,10 @@ Check status anytime:
 | **research-pipeline** | `/research-pipeline` | Orchestrator. Spawns sub-agents for each phase, verifies outputs between steps. |
 | **research-collect** | `/research-collect` | Search arXiv → filter → download .tex sources → cluster → generate survey report. |
 | **research-survey** | `/research-survey` | Deep analysis of papers: extract formulas, map to code, produce method comparison table. |
+| **algorithm-selection** | `/algorithm-selection` | Choose between 2-3 plausible ML routes, record rejected routes, and keep a fallback. |
 | **research-plan** | `/research-plan` | Create 4-part implementation plan (Dataset/Model/Training/Testing) from survey results. |
+| **dataset-validate** | `/dataset-validate` | Audit data reality, splits, labels, and leakage risk before model review. |
+| **baseline-runner** | `/baseline-runner` | Run or audit strong baselines under the same protocol before headline comparisons. |
 | **research-implement** | `/research-implement` | Implement ML code from plan, run 2-epoch validation with `uv` venv isolation. |
 | **research-review** | `/research-review` | Review implementation. Iterates fix → rerun → review up to 3 times. |
 | **research-experiment** | `/research-experiment` | Full training + ablation experiments. Requires review PASS. |
diff --git a/README.md b/README.md
index 0c848fe..957bf2d 100644
--- a/README.md
+++ b/README.md
@@ -226,8 +226,22 @@ openclaw gateway
 /research-pipeline
 /research-collect
 /idea-generation
+/algorithm-selection
+/dataset-validate
 ```
 
+## 机器学习中段任务的新增技能
+
+- `/algorithm-selection`
+  - 用在 `/research-survey` 之后、`/research-plan` 之前
+  - 作用：把 2-3 条候选路线写清楚，明确 `Chosen Route / Rejected Routes / Fallback Route`
+- `/dataset-validate`
+  - 用在 `plan_res.md` 已经存在、准备实现或审查模型之前
+  - 作用：单独审数据真实性、split、label、leakage 和 mock 风险，把数据质量和模型质量分开
+- `/baseline-runner`
+  - 用在 `plan_res.md` 已经存在、需要真实 baseline 对比时
+  - 作用：统一 baseline、协议、指标和结果记录，产出 `baseline_res.md`
+
 ### 3. 监控子 agent 进度
 
 编排器 spawn 子 agent 后，你会看到：
diff --git a/openclaw.plugin.json b/openclaw.plugin.json
index b6555ce..38ff131 100644
--- a/openclaw.plugin.json
+++ b/openclaw.plugin.json
@@ -8,6 +8,9 @@
     "properties": {}
   },
   "skills": [
+    "skills/algorithm-selection",
+    "skills/baseline-runner",
+    "skills/dataset-validate",
     "skills/idea-generation",
     "skills/research-pipeline",
     "skills/research-survey",
diff --git a/skills/algorithm-selection/SKILL.md b/skills/algorithm-selection/SKILL.md
new file mode 100644
index 0000000..7cd9531
--- /dev/null
+++ b/skills/algorithm-selection/SKILL.md
@@ -0,0 +1,103 @@
+---
+name: algorithm-selection
+description: "Use this when the user needs to choose between multiple ML routes after survey but before committing to implementation. Compares candidate approaches, selects one, records rejected routes, and keeps a fallback."
+metadata:
+  {
+    "openclaw":
+      {
+        "emoji": "🧭",
+      },
+  }
+---
+
+# Algorithm Selection
+
+**Don't ask permission. Just do it.**
+
+Use this skill after `/research-survey` when there are several plausible ML approaches and the project needs a deliberate route choice instead of jumping straight into implementation.
+
+Outputs go to the workspace root.
+
+## Use This When
+
+- `survey_res.md` already exists
+- there are at least 2 plausible methods or model families
+- the user wants a chosen route plus backups
+
+## Do Not Use This When
+
+- the project has no survey yet
+- the team already decided the model route and only needs implementation details
+
+## Required Inputs
+
+- `SOUL.md`
+- `survey_res.md`
+- `knowledge/paper_*.md` when available
+
+If `survey_res.md` is missing, stop and say: `需要先运行 /research-survey 完成深度分析`.
+
+## Required Output
+
+- `selection_res.md`
+
+## Workflow
+
+### Step 1: Read the Current Project Direction
+
+Read:
+
+- `SOUL.md`
+- `survey_res.md`
+- relevant `knowledge/paper_*.md`
+
+Extract:
+
+- the task and evaluation target
+- method families mentioned in survey
+- constraints such as compute, data, latency, interpretability, or deployment needs
+
+### Step 2: Build 2-3 Candidate Routes
+
+Create 2-3 realistic candidate routes only. For each route, record:
+
+- route name
+- core idea
+- supporting papers
+- expected strengths
+- expected risks
+- implementation cost
+- baseline compatibility
+
+Use `references/candidate-template.md`.
+
+### Step 3: Select One Route and Keep Backups
+
+Choose:
+
+- one `Chosen Route`
+- one or more `Rejected Routes`
+- one `Fallback Route`
+
+The fallback should be the route most likely to work if the chosen route underperforms or proves too expensive to implement.
+
+### Step 4: Write `selection_res.md`
+
+Use `references/selection-template.md`.
+
+The final output must include:
+
+- project goal
+- decision criteria
+- candidate options table
+- chosen route
+- rejected routes
+- fallback route
+- next recommended command
+
+## Rules
+
+1. Do not present only one route unless the survey truly leaves no meaningful alternative.
+2. Every route must cite at least one paper or survey-derived basis.
+3. The chosen route must match the project constraints in `SOUL.md`.
+4. The fallback route must be different from the chosen route.
diff --git a/skills/algorithm-selection/references/candidate-template.md b/skills/algorithm-selection/references/candidate-template.md
new file mode 100644
index 0000000..05ab1bd
--- /dev/null
+++ b/skills/algorithm-selection/references/candidate-template.md
@@ -0,0 +1,13 @@
+# Candidate Route Template
+
+Use one block per route.
+
+```markdown
+## Route A: {name}
+- Core idea:
+- Based on:
+- Expected strengths:
+- Expected risks:
+- Implementation cost: low / medium / high
+- Baseline compatibility:
+```
diff --git a/skills/algorithm-selection/references/selection-template.md b/skills/algorithm-selection/references/selection-template.md
new file mode 100644
index 0000000..c08e4a7
--- /dev/null
+++ b/skills/algorithm-selection/references/selection-template.md
@@ -0,0 +1,39 @@
+# Selection Result Template
+
+```markdown
+# Algorithm Selection
+
+## Project Goal
+- task:
+- main metric:
+- key constraints:
+
+## Decision Criteria
+- criterion 1:
+- criterion 2:
+- criterion 3:
+
+## Candidate Options
+
+| Route | Core idea | Strengths | Risks | Cost | Basis |
+|-------|-----------|-----------|-------|------|-------|
+| A | ... | ... | ... | ... | ... |
+| B | ... | ... | ... | ... | ... |
+
+## Chosen Route
+- route:
+- why this route:
+- what to implement first:
+
+## Rejected Routes
+- route:
+  - why not now:
+
+## Fallback Route
+- route:
+- when to switch:
+
+## Next Step
+- recommended command:
+- expected output:
+```
diff --git a/skills/baseline-runner/SKILL.md b/skills/baseline-runner/SKILL.md
new file mode 100644
index 0000000..e18af44
--- /dev/null
+++ b/skills/baseline-runner/SKILL.md
@@ -0,0 +1,103 @@
+---
+name: baseline-runner
+description: "Use this when the project needs real baseline results before or alongside the main model. Runs classical or literature-aligned baselines under the same protocol and writes a reproducible baseline summary."
+metadata:
+  {
+    "openclaw":
+      {
+        "emoji": "📏",
+        "requires": { "bins": ["python3", "uv"] },
+      },
+  }
+---
+
+# Baseline Runner
+
+**Don't ask permission. Just do it.**
+
+Use this skill when the project needs trustworthy baseline numbers instead of only evaluating the proposed model in isolation.
+
+Outputs go to the workspace root.
+
+## Use This When
+
+- `plan_res.md` already names baselines
+- `project/` already exists or a baseline implementation path is known
+- the experiment stage needs matched comparison numbers
+
+## Do Not Use This When
+
+- the project has not finished survey or planning
+- no baseline method has been identified yet
+
+## Required Inputs
+
+- `plan_res.md`
+- `survey_res.md`
+- `project/` when the current project already has runnable code
+
+If `plan_res.md` is missing, stop and say: `需要先运行 /research-plan 完成实现计划`.
+
+## Required Outputs
+
+- `baseline_res.md`
+- `experiments/baselines/` when runnable artifacts are created
+
+## Workflow
+
+### Step 1: Read the Evaluation Contract
+
+Read:
+
+- `plan_res.md`
+- `survey_res.md`
+- current `experiment_res.md` if it exists
+
+Extract:
+
+- baseline names
+- evaluation metric
+- protocol or guardrail
+- dataset or workload assumptions
+
+### Step 2: Define the Baseline Matrix
+
+Create a small comparison matrix with:
+
+- baseline name
+- source or basis
+- expected setup
+- metric
+- status: `ready`, `needs adaptation`, or `missing`
+
+Use `references/baseline-matrix-template.md`.
+
+### Step 3: Run or Approximate Baselines Conservatively
+
+For each baseline:
+
+- if code is runnable under the current workspace, run it
+- if only a lightweight adaptation is needed, implement the minimal adapter
+- if a baseline cannot be run honestly, mark it as unavailable instead of inventing numbers
+
+All numeric results must come from actual execution logs or explicit imported evidence.
+
+### Step 4: Write `baseline_res.md`
+
+Use `references/baseline-report-template.md`.
+
+The report must include:
+
+- which baselines were attempted
+- which ones ran successfully
+- the exact metric values
+- the evaluation protocol
+- missing or partial baselines
+- the most comparable baseline for the current project
+
+## Rules
+
+1. Never fabricate baseline numbers.
+2. Keep the protocol aligned with the main experiment whenever possible.
+3. If a baseline is only partly comparable, say so explicitly.
+4. Prefer 2-3 strong baselines over a long weak list.
diff --git a/skills/baseline-runner/references/baseline-matrix-template.md b/skills/baseline-runner/references/baseline-matrix-template.md
new file mode 100644
index 0000000..736ecc3
--- /dev/null
+++ b/skills/baseline-runner/references/baseline-matrix-template.md
@@ -0,0 +1,9 @@
+# Baseline Matrix Template
+
+```markdown
+# Baseline Matrix
+
+| Baseline | Source | Metric | Protocol | Status | Notes |
+|----------|--------|--------|----------|--------|-------|
+| {name} | {paper/repo} | {metric} | {protocol} | ready / needs adaptation / missing | {note} |
+```
diff --git a/skills/baseline-runner/references/baseline-report-template.md b/skills/baseline-runner/references/baseline-report-template.md
new file mode 100644
index 0000000..8b5dd84
--- /dev/null
+++ b/skills/baseline-runner/references/baseline-report-template.md
@@ -0,0 +1,25 @@
+# Baseline Report Template
+
+```markdown
+# Baseline Results
+
+## Evaluation Contract
+- dataset or workload:
+- metric:
+- guardrail or protocol:
+
+## Baselines Attempted
+
+| Baseline | Status | Result | Evidence Source | Notes |
+|----------|--------|--------|-----------------|-------|
+| {name} | ran / partial / missing | {value or N/A} | {log or file} | {notes} |
+
+## Most Comparable Baseline
+- baseline:
+- why this is the main comparison:
+
+## Gaps
+- baseline not run:
+- reason:
+- how to close the gap:
+```
diff --git a/skills/dataset-validate/SKILL.md b/skills/dataset-validate/SKILL.md
new file mode 100644
index 0000000..716b737
--- /dev/null
+++ b/skills/dataset-validate/SKILL.md
@@ -0,0 +1,104 @@
+---
+name: dataset-validate
+description: "Use this when the project needs a dedicated data-quality review before model review. Checks data reality, split correctness, label health, leakage risk, shape consistency, and mock-data disclosure."
+metadata:
+  {
+    "openclaw":
+      {
+        "emoji": "🗂️",
+        "requires": { "bins": ["python3", "uv"] },
+      },
+  }
+---
+
+# Dataset Validate
+
+**Don't ask permission. Just do it.**
+
+Use this skill before or alongside model implementation review when data quality needs to be checked separately from model quality.
+
+Outputs go to the workspace root.
+
+## Use This When
+
+- `plan_res.md` already exists
+- the project is about to implement or has just implemented a model
+- data quality, split quality, or label integrity is still uncertain
+
+## Do Not Use This When
+
+- the project has no concrete plan yet
+- there is no dataset or data-loading path to inspect
+
+## Required Inputs
+
+- `plan_res.md`
+- `project/` if a data pipeline already exists
+- `survey_res.md` when it defines dataset or protocol expectations
+
+If `plan_res.md` is missing, stop and say: `需要先运行 /research-plan 完成实现计划`.
+
+## Required Output
+
+- `data_validation.md`
+
+## Workflow
+
+### Step 1: Read the Data Contract
+
+Read:
+
+- `plan_res.md`
+- `survey_res.md` if present
+- current data-loading code under `project/data/` if present
+
+Extract:
+
+- expected dataset name
+- source
+- split structure
+- label or target format
+- expected shapes
+
+### Step 2: Audit Data Reality
+
+Check:
+
+- whether dataset files actually exist
+- whether the data is real or mock
+- whether mock usage is clearly declared
+- whether row count / sample count is plausible
+
+### Step 3: Audit Data Integrity
+
+Check:
+
+- train / val / test split existence and separation
+- label distribution or target sanity
+- shape / dtype consistency
+- obvious leakage risks
+- preprocessing consistency with `plan_res.md`
+
+If code exists, run lightweight inspection commands under the project environment to verify counts and sample structure.
+
+### Step 4: Write `data_validation.md`
+
+Use `references/data-validation-template.md`.
+
+The report must include:
+
+- dataset identity
+- data reality check
+- split integrity
+- label / target health
+- leakage risk
+- mock-data disclosure
+- verdict: `PASS`, `NEEDS_REVISION`, or `BLOCKED`
+- exact next step
+
+## Rules
+
+1. Keep data quality separate from model quality.
+2. Never infer that data is real if the files or loading path are missing.
+3. If mock data is used, call it out explicitly.
+4. If data leakage is plausible, treat it as blocking until clarified.
diff --git a/skills/dataset-validate/references/data-validation-template.md b/skills/dataset-validate/references/data-validation-template.md
new file mode 100644
index 0000000..ae64151
--- /dev/null
+++ b/skills/dataset-validate/references/data-validation-template.md
@@ -0,0 +1,38 @@
+# Data Validation Template
+
+```markdown
+# Data Validation
+
+## Dataset Identity
+- dataset:
+- source:
+- expected split:
+
+## Reality Check
+- files present:
+- real or mock:
+- evidence:
+
+## Split Integrity
+- train split:
+- val split:
+- test split:
+- leakage risk:
+
+## Label / Target Health
+- label format:
+- distribution or range:
+- obvious anomalies:
+
+## Preprocessing Check
+- expected preprocessing:
+- observed preprocessing:
+- mismatch:
+
+## Verdict
+- PASS / NEEDS_REVISION / BLOCKED
+
+## Next Step
+- recommended command:
+- reason:
+```
diff --git a/src/commands.ts b/src/commands.ts
index 8c34ef8..77085d7 100644
--- a/src/commands.ts
+++ b/src/commands.ts
@@ -10,6 +10,25 @@ interface ResearchAgent {
   workspace: string;
 }
 
+interface ProjectSnapshot {
+  hasConfig: boolean;
+  hasSurvey: boolean;
+  hasSelection: boolean;
+  hasPlan: boolean;
+  hasDataValidation: boolean;
+  hasBaseline: boolean;
+  hasImplementationReport: boolean;
+  latestReviewVerdict: "PASS" | "NEEDS_REVISION" | "NEEDS_ALGORITHM_REVIEW" | "BLOCKED" | "MISSING" | "UNKNOWN";
+  hasExperiment: boolean;
+}
+
+interface NextActionState {
+  stage: string;
+  command: string;
+  expectedOutputs: string[];
+  reason: string;
+}
+
 /**
  * List all research agents from openclaw.json.
  */
@@ -38,6 +57,158 @@ function countFiles(dirPath: string, filter?: (name: string) => boolean): number
   }
 }
 
+function fileExists(filePath: string): boolean {
+  try {
+    return fs.existsSync(filePath);
+  } catch {
+    return false;
+  }
+}
+
+function readLatestReviewVerdict(workspace: string): ProjectSnapshot["latestReviewVerdict"] {
+  const iterationsDir = path.join(workspace, "iterations");
+  if (!fileExists(iterationsDir)) return "MISSING";
+
+  try {
+    const files = fs.readdirSync(iterationsDir)
+      .filter((f) => /^judge_v\d+\.md$/.test(f))
+      .sort((a, b) => {
+        const na = Number(a.match(/\d+/)?.[0] ?? "0");
+        const nb = Number(b.match(/\d+/)?.[0] ?? "0");
+        return nb - na;
+      });
+
+    const latest = files[0];
+    if (!latest) return "MISSING";
+
+    const content = fs.readFileSync(path.join(iterationsDir, latest), "utf-8");
+    const verdictMatch = content.match(/##\s+Verdict:\s+([A-Z_]+)/);
+    const verdict = verdictMatch?.[1] as ProjectSnapshot["latestReviewVerdict"] | undefined;
+    return verdict ?? "UNKNOWN";
+  } catch {
+    return "UNKNOWN";
+  }
+}
+
+function buildProjectSnapshot(workspace: string): ProjectSnapshot {
+  return {
+    hasConfig: fileExists(path.join(workspace, "config.json")),
+    hasSurvey: fileExists(path.join(workspace, "survey_res.md")),
+    hasSelection: fileExists(path.join(workspace, "selection_res.md")),
+    hasPlan: fileExists(path.join(workspace, "plan_res.md")),
+    hasDataValidation: fileExists(path.join(workspace, "data_validation.md")),
+    hasBaseline: fileExists(path.join(workspace, "baseline_res.md")),
+    hasImplementationReport: fileExists(path.join(workspace, "ml_res.md")),
+    latestReviewVerdict: readLatestReviewVerdict(workspace),
+    hasExperiment: fileExists(path.join(workspace, "experiment_res.md")),
+  };
+}
+
+function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
+  if (!snapshot.hasConfig) {
+    return {
+      stage: "Bootstrap pending",
+      command: "完成 BOOTSTRAP 配置",
+      expectedOutputs: ["config.json", "SOUL.md"],
+      reason: "项目还没有基础配置，后续 survey、selection 和 experiment 没有统一方向依据。",
+    };
+  }
+
+  if (!snapshot.hasSurvey) {
+    return {
+      stage: "Survey needed",
+      command: "/research-survey",
+      expectedOutputs: ["knowledge/", "survey_res.md"],
+      reason: "当前还没有深度调研结果，无法可靠进入路线选择和实现。",
+    };
+  }
+
+  if (!snapshot.hasSelection && !snapshot.hasPlan) {
+    return {
+      stage: "Route selection",
+      command: "/algorithm-selection",
+      expectedOutputs: ["selection_res.md"],
+      reason: "已经有 survey，但还没有把候选路线收敛成 Chosen / Rejected / Fallback。",
+    };
+  }
+
+  if (!snapshot.hasPlan) {
+    return {
+      stage: "Planning",
+      command: "/research-plan",
+      expectedOutputs: ["plan_res.md"],
+      reason: "还缺 Dataset / Model / Training / Testing 四部分计划。",
+    };
+  }
+
+  if (!snapshot.hasDataValidation) {
+    return {
+      stage: "Dataset validation",
+      command: "/dataset-validate",
+      expectedOutputs: ["data_validation.md"],
+      reason: "先把数据真实性、split、label 和 leakage 风险单独审清楚，再做模型质量判断。",
+    };
+  }
+
+  if (!snapshot.hasBaseline) {
+    return {
+      stage: "Baseline setup",
+      command: "/baseline-runner",
+      expectedOutputs: ["baseline_res.md", "experiments/baselines/"],
+      reason: "当前还缺统一协议下的 baseline 结果，不适合直接写 headline comparison。",
+    };
+  }
+
+  if (!snapshot.hasImplementationReport) {
+    return {
+      stage: "Implementation",
+      command: "/research-implement",
+      expectedOutputs: ["project/", "ml_res.md"],
+      reason: "路线、计划、数据检查和 baseline 契约都已经具备，下一步应进入实现和 2 epoch 验证。",
+    };
+  }
+
+  if (snapshot.latestReviewVerdict !== "PASS") {
+    return {
+      stage: "Review",
+      command: "/research-review",
+      expectedOutputs: ["iterations/judge_v{N}.md"],
+      reason: "实现已经存在，但还没有拿到 review PASS，模型质量还需要单独审。",
+    };
+  }
+
+  if (!snapshot.hasExperiment) {
+    return {
+      stage: "Full experiment",
+      command: "/research-experiment",
+      expectedOutputs: ["experiment_res.md", "experiment_analysis/"],
+      reason: "实现和 review 已通过，下一步应补 full training、ablation 和补充实验。",
+    };
+  }
+
+  return {
+    stage: "Experiment complete",
+    command: "/write-review-paper",
+    expectedOutputs: ["review/"],
+    reason: "核心机器学习主链已经跑完，可以进入总结、综述或对外整理阶段。",
+  };
+}
+
+function formatArtifactPresence(snapshot: ProjectSnapshot): string {
+  const items = [
+    ["survey", snapshot.hasSurvey],
+    ["selection", snapshot.hasSelection],
+    ["plan", snapshot.hasPlan],
+    ["data_validation", snapshot.hasDataValidation],
+    ["baseline", snapshot.hasBaseline],
+    ["implement", snapshot.hasImplementationReport],
+    ["review", snapshot.latestReviewVerdict === "PASS"],
+    ["experiment", snapshot.hasExperiment],
+  ];
+
+  return items.map(([label, ok]) => `${ok ? "yes" : "no"} ${label}`).join(" | ");
+}
+
 /**
  * /research-status - Show workspace status for all research agents
  */
@@ -58,6 +229,8 @@ export function handleResearchStatus(_ctx: PluginCommandContext): PluginCommandR
     const ideasCount = countFiles(path.join(w, "ideas"), (f) => f.endsWith(".md"));
     const topicCount = countFiles(path.join(w, "knowledge"), (f) => f.startsWith("topic-"));
     const hypothesisCount = countFiles(path.join(w, "ideas"), (f) => f.startsWith("hyp-"));
+    const snapshot = buildProjectSnapshot(w);
+    const next = inferNextAction(snapshot);
 
     let currentDay = 0;
     try {
@@ -67,7 +240,12 @@ export function handleResearchStatus(_ctx: PluginCommandContext): PluginCommandR
 
     output += `**${projectId}** (Day ${currentDay})\n`;
     output += `  Workspace: \`${w}\`\n`;
-    output += `  Topics: ${topicCount} | Hypotheses: ${hypothesisCount} | Papers: ${papersCount} | Ideas: ${ideasCount}\n\n`;
+    output += `  Topics: ${topicCount} | Hypotheses: ${hypothesisCount} | Papers: ${papersCount} | Ideas: ${ideasCount}\n`;
+    output += `  Stage: ${next.stage}\n`;
+    output += `  Artifacts: ${formatArtifactPresence(snapshot)}\n`;
+    output += `  Next: \`${next.command}\`\n`;
+    output += `  Why: ${next.reason}\n`;
+    output += `  Expected: ${next.expectedOutputs.map((p) => `\`${p}\``).join(", ")}\n\n`;
   }
 
   return { text: output };
diff --git a/src/templates/bootstrap.ts b/src/templates/bootstrap.ts
index b8c9497..0f2a1ac 100644
--- a/src/templates/bootstrap.ts
+++ b/src/templates/bootstrap.ts
@@ -21,7 +21,24 @@ export function renderBootstrapMd(projectName: string): string {
    - 生成 config.json（参考下方模板）
 5. 询问用户是否立即执行 Day 0（构建初始知识状态）
    - 如果是，执行 /metabolism 完成首轮文献检索和知识库构建（Day 0 模式）
-6. 删除本文件（BOOTSTRAP.md）
+6. 如果用户已经有部分产物，优先走最短路径，不要默认从 Day 0 重头开始：
+   - 已有 papers/ -> /research-survey
+   - 已有 survey_res.md，但路线还没定 -> /algorithm-selection
+   - 已有 survey_res.md -> /research-plan
+   - 已有 plan_res.md，需要先审数据质量 -> /dataset-validate
+   - 已有 plan_res.md，且需要真实对比方法 -> /baseline-runner
+   - 已有实现代码 -> /research-review
+   - 已有 review PASS -> /research-experiment
+7. 在完成首次配置后，告诉用户下一步推荐命令和预期输出文件，再删除本文件（BOOTSTRAP.md）
+
+## 常见入口
+
+- 我只有一个研究方向，没有材料 -> 先完成配置，再运行 /metabolism
+- 我已经有一批论文 -> 直接运行 /research-survey
+- 我已经做完 survey，但还没决定模型路线 -> 运行 /algorithm-selection
+- 我已经有 plan，想先确认数据没问题 -> 运行 /dataset-validate
+- 我已经有 plan，想先把 baseline 跑出来 -> 运行 /baseline-runner
+- 我已经有实现代码 -> 运行 /research-review
 
 ## config.json 模板
 
@@ -131,11 +148,26 @@ $W/
 | /metabolism | Day 0: config.json, knowledge/ / Day 1+: papers/, knowledge/, ideas/hyp-*.md, log/ |
 | /research-collect | papers/ |
 | /research-survey | knowledge/, survey_res.md |
+| /algorithm-selection | selection_res.md |
 | /research-plan | plan_res.md |
+| /dataset-validate | data_validation.md |
+| /baseline-runner | baseline_res.md, experiments/baselines/ |
 | /research-implement | experiments/ |
 | /research-review | experiments/review/ |
 | /research-experiment | experiments/results/ |
 | /idea-generation | ideas/ |
 | /write-review-paper | review/ |
+
+## Common ML Midstream Paths
+
+- Survey exists but route choice is still unclear:
+  - run \`/algorithm-selection\`
+  - expected output: \`selection_res.md\`
+- Plan exists and the project needs a dedicated data-quality check:
+  - run \`/dataset-validate\`
+  - expected output: \`data_validation.md\`
+- Plan exists and the project needs honest comparison numbers:
+  - run \`/baseline-runner\`
+  - expected outputs: \`baseline_res.md\`, optional baseline artifacts under \`experiments/baselines/\`
 `;
 }

From 7c192549d4244a808d1b50dc88ad5292dd130025 Mon Sep 17 00:00:00 2001
From: JunkaiWang-TheoPhy <1181100960@qq.com>
Date: Thu, 2 Apr 2026 21:00:04 +0800
Subject: [PATCH 2/3] chore

---
 skills/algorithm-selection/SKILL.md |   2 +-
 skills/baseline-runner/SKILL.md     |   2 +-
 skills/dataset-validate/SKILL.md    |   2 +-
 src/cli/research.ts                 |   2 +-
 src/commands.ts                     |  22 ++--
 src/templates/bootstrap.ts          | 156 ++++++++++++++--------------
 6 files changed, 93 insertions(+), 93 deletions(-)

diff --git a/skills/algorithm-selection/SKILL.md b/skills/algorithm-selection/SKILL.md
index 7cd9531..c6014c1 100644
--- a/skills/algorithm-selection/SKILL.md
+++ b/skills/algorithm-selection/SKILL.md
@@ -35,7 +35,7 @@ Outputs go to the workspace root.
 - `survey_res.md`
 - `knowledge/paper_*.md` when available
 
-If `survey_res.md` is missing, stop and say: `需要先运行 /research-survey 完成深度分析`.
+If `survey_res.md` is missing, stop and say: `Run /research-survey first to complete the deep analysis.`
 
 ## Required Output
 
diff --git a/skills/baseline-runner/SKILL.md b/skills/baseline-runner/SKILL.md
index e18af44..190e0fd 100644
--- a/skills/baseline-runner/SKILL.md
+++ b/skills/baseline-runner/SKILL.md
@@ -36,7 +36,7 @@ Outputs go to the workspace root.
 - `survey_res.md`
 - `project/` when the current project already has runnable code
 
-If `plan_res.md` is missing, stop and say: `需要先运行 /research-plan 完成实现计划`.
+If `plan_res.md` is missing, stop and say: `Run /research-plan first to complete the implementation plan.`
 
 ## Required Outputs
 
diff --git a/skills/dataset-validate/SKILL.md b/skills/dataset-validate/SKILL.md
index 716b737..a344c1c 100644
--- a/skills/dataset-validate/SKILL.md
+++ b/skills/dataset-validate/SKILL.md
@@ -36,7 +36,7 @@ Outputs go to the workspace root.
 - `project/` if a data pipeline already exists
 - `survey_res.md` when it defines dataset or protocol expectations
 
-If `plan_res.md` is missing, stop and say: `需要先运行 /research-plan 完成实现计划`.
+If `plan_res.md` is missing, stop and say: `Run /research-plan first to complete the implementation plan.`
 
 ## Required Output
 
diff --git a/src/cli/research.ts b/src/cli/research.ts
index be3cb90..feb61bc 100644
--- a/src/cli/research.ts
+++ b/src/cli/research.ts
@@ -71,7 +71,7 @@ function addCronJob(agentId: string): void {
     payload: {
       kind: "agentTurn",
       agentId,
-      message: "执行每日知识新陈代谢。阅读 AGENTS.md 了解工作流，然后使用 /metabolism 技能完成今日代谢。",
+      message: "Run daily knowledge metabolism. Read AGENTS.md for the workflow, then use the /metabolism skill to complete today's cycle.",
     },
     delivery: { mode: "announce" },
     enabled: true,
diff --git a/src/commands.ts b/src/commands.ts
index 77085d7..13ce80b 100644
--- a/src/commands.ts
+++ b/src/commands.ts
@@ -108,9 +108,9 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
   if (!snapshot.hasConfig) {
     return {
       stage: "Bootstrap pending",
-      command: "完成 BOOTSTRAP 配置",
+      command: "complete BOOTSTRAP configuration",
       expectedOutputs: ["config.json", "SOUL.md"],
-      reason: "项目还没有基础配置，后续 survey、selection 和 experiment 没有统一方向依据。",
+      reason: "The project is missing its base configuration, so later survey, selection, and experiment steps do not yet share a stable direction.",
     };
   }
 
@@ -119,7 +119,7 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
       stage: "Survey needed",
       command: "/research-survey",
       expectedOutputs: ["knowledge/", "survey_res.md"],
-      reason: "当前还没有深度调研结果，无法可靠进入路线选择和实现。",
+      reason: "There is no deep survey result yet, so route selection and implementation would be premature.",
     };
   }
 
@@ -128,7 +128,7 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
       stage: "Route selection",
       command: "/algorithm-selection",
       expectedOutputs: ["selection_res.md"],
-      reason: "已经有 survey，但还没有把候选路线收敛成 Chosen / Rejected / Fallback。",
+      reason: "A survey exists, but the project has not yet narrowed candidate approaches into Chosen / Rejected / Fallback routes.",
     };
   }
 
@@ -137,7 +137,7 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
       stage: "Planning",
       command: "/research-plan",
       expectedOutputs: ["plan_res.md"],
-      reason: "还缺 Dataset / Model / Training / Testing 四部分计划。",
+      reason: "The project still needs a concrete Dataset / Model / Training / Testing plan before implementation.",
     };
   }
 
@@ -146,7 +146,7 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
       stage: "Dataset validation",
       command: "/dataset-validate",
       expectedOutputs: ["data_validation.md"],
-      reason: "先把数据真实性、split、label 和 leakage 风险单独审清楚，再做模型质量判断。",
+      reason: "Data reality, splits, labels, and leakage risk should be reviewed separately before judging model quality.",
     };
   }
 
@@ -155,7 +155,7 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
       stage: "Baseline setup",
       command: "/baseline-runner",
       expectedOutputs: ["baseline_res.md", "experiments/baselines/"],
-      reason: "当前还缺统一协议下的 baseline 结果，不适合直接写 headline comparison。",
+      reason: "The project still lacks baseline results under a matched protocol, so headline comparisons would be too early.",
     };
   }
 
@@ -164,7 +164,7 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
       stage: "Implementation",
       command: "/research-implement",
       expectedOutputs: ["project/", "ml_res.md"],
-      reason: "路线、计划、数据检查和 baseline 契约都已经具备，下一步应进入实现和 2 epoch 验证。",
+      reason: "The route, plan, data check, and baseline contract are already in place, so the next step is implementation plus 2-epoch validation.",
     };
   }
 
@@ -173,7 +173,7 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
       stage: "Review",
       command: "/research-review",
       expectedOutputs: ["iterations/judge_v{N}.md"],
-      reason: "实现已经存在，但还没有拿到 review PASS，模型质量还需要单独审。",
+      reason: "Implementation exists, but review has not yet reached PASS, so model quality still needs a dedicated review pass.",
     };
   }
 
@@ -182,7 +182,7 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
       stage: "Full experiment",
       command: "/research-experiment",
       expectedOutputs: ["experiment_res.md", "experiment_analysis/"],
-      reason: "实现和 review 已通过，下一步应补 full training、ablation 和补充实验。",
+      reason: "Implementation and review are ready, so the next step is full training, ablations, and supplementary experiments.",
     };
   }
 
@@ -190,7 +190,7 @@ function inferNextAction(snapshot: ProjectSnapshot): NextActionState {
     stage: "Experiment complete",
     command: "/write-review-paper",
     expectedOutputs: ["review/"],
-    reason: "核心机器学习主链已经跑完，可以进入总结、综述或对外整理阶段。",
+    reason: "The core ML execution chain is complete, so the project can move into synthesis, survey writing, or outward-facing summaries.",
   };
 }
 
diff --git a/src/templates/bootstrap.ts b/src/templates/bootstrap.ts
index 0f2a1ac..696725f 100644
--- a/src/templates/bootstrap.ts
+++ b/src/templates/bootstrap.ts
@@ -6,46 +6,46 @@
 export function renderBootstrapMd(projectName: string): string {
   return `# Research Agent Bootstrap
 
-你刚刚被创建为课题「${projectName}」的研究 agent。你需要完成首次配置。
-
-## 引导流程
-
-1. 向用户问好，说明你是课题「${projectName}」的研究 agent，请用户描述研究方向
-2. 根据用户回答，提取：
-   - 核心域关键词（3-5 个）
-   - 建议的 arXiv 分类（如 cs.LG, cs.AI），如果研究方向不属于 arXiv 覆盖范围则留空
-   - 建议的文献来源偏好（arXiv、OpenAlex、或两者兼用）
-3. 与用户讨论研究方向的边界和重点，确认以上配置，接受调整
-4. 确认后执行以下写入操作：
-   - 更新 SOUL.md：填写研究方向、核心域各字段
-   - 生成 config.json（参考下方模板）
-5. 询问用户是否立即执行 Day 0（构建初始知识状态）
-   - 如果是，执行 /metabolism 完成首轮文献检索和知识库构建（Day 0 模式）
-6. 如果用户已经有部分产物，优先走最短路径，不要默认从 Day 0 重头开始：
-   - 已有 papers/ -> /research-survey
-   - 已有 survey_res.md，但路线还没定 -> /algorithm-selection
-   - 已有 survey_res.md -> /research-plan
-   - 已有 plan_res.md，需要先审数据质量 -> /dataset-validate
-   - 已有 plan_res.md，且需要真实对比方法 -> /baseline-runner
-   - 已有实现代码 -> /research-review
-   - 已有 review PASS -> /research-experiment
-7. 在完成首次配置后，告诉用户下一步推荐命令和预期输出文件，再删除本文件（BOOTSTRAP.md）
-
-## 常见入口
-
-- 我只有一个研究方向，没有材料 -> 先完成配置，再运行 /metabolism
-- 我已经有一批论文 -> 直接运行 /research-survey
-- 我已经做完 survey，但还没决定模型路线 -> 运行 /algorithm-selection
-- 我已经有 plan，想先确认数据没问题 -> 运行 /dataset-validate
-- 我已经有 plan，想先把 baseline 跑出来 -> 运行 /baseline-runner
-- 我已经有实现代码 -> 运行 /research-review
-
-## config.json 模板
+You were just created as the research agent for project "${projectName}". Complete the initial setup before starting downstream work.
+
+## Bootstrap Flow
+
+1. Greet the user, explain that you are the research agent for project "${projectName}", and ask them to describe the research direction.
+2. Based on the user's answer, extract:
+   - core-domain keywords (3-5)
+   - suggested arXiv categories (for example "cs.LG", "cs.AI"); leave empty if the topic is outside arXiv coverage
+   - preferred literature sources ("arxiv", "openalex", or both)
+3. Discuss scope and priorities with the user, confirm the configuration, and accept adjustments.
+4. Once confirmed, write the following files:
+   - update SOUL.md with the project direction and domain fields
+   - generate config.json using the template below
+5. Ask whether the user wants to run Day 0 immediately to build the initial knowledge state.
+   - If yes, run /metabolism to perform the first literature retrieval and knowledge-base construction pass.
+6. If the project already has partial outputs, use the shortest matching path instead of restarting from Day 0:
+   - existing papers/ -> /research-survey
+   - existing survey_res.md, but route still undecided -> /algorithm-selection
+   - existing survey_res.md -> /research-plan
+   - existing plan_res.md, but data quality still needs review -> /dataset-validate
+   - existing plan_res.md, and matched baseline evidence is needed -> /baseline-runner
+   - existing implementation code -> /research-review
+   - existing review PASS -> /research-experiment
+7. After the initial setup, tell the user the recommended next command and expected output files, then delete this file (BOOTSTRAP.md).
+
+## Common Entry Paths
+
+- I only have a research direction and no materials yet -> finish setup, then run /metabolism
+- I already have a batch of papers -> run /research-survey
+- I finished the survey but have not chosen a model route -> run /algorithm-selection
+- I already have a plan and want to validate the data first -> run /dataset-validate
+- I already have a plan and want honest baseline numbers first -> run /baseline-runner
+- I already have implementation code -> run /research-review
+
+## config.json Template
 
 \`\`\`json
 {
   "projectId": "${projectName}",
-  "keywords": ["关键词1", "关键词2"],
+  "keywords": ["keyword-1", "keyword-2"],
   "arxivCategories": ["cs.LG"],
   "sources": ["arxiv", "openalex"],
   "currentDay": 0,
@@ -54,23 +54,23 @@ export function renderBootstrapMd(projectName: string): string {
 }
 \`\`\`
 
-> **注意：** \`arxivCategories\` 和 \`sources\` 根据研究领域灵活配置。
-> 自然科学、社会科学等非 CS 领域可将 \`arxivCategories\` 设为 \`[]\`，主要依赖 OpenAlex。
+> **Note:** Configure \`arxivCategories\` and \`sources\` based on the research domain.
+> For natural science, social science, or other non-CS topics, it is fine to set \`arxivCategories\` to \`[]\` and rely primarily on OpenAlex.
 `;
 }
 
 export function renderSoulMd(projectName: string): string {
   return `# Project Agent — ${projectName}
 
-你是课题「${projectName}」的研究 agent。
+You are the research agent for project "${projectName}".
 
-## 研究方向
-{由 BOOTSTRAP 流程填写}
+## Research Direction
+{Filled during the BOOTSTRAP flow}
 
-## 核心域
-关键词: {由 BOOTSTRAP 流程填写}
-arXiv 分类: {由 BOOTSTRAP 流程填写，不适用则留空}
-文献来源: {arXiv / OpenAlex / 两者兼用}
+## Core Domain
+Keywords: {Filled during the BOOTSTRAP flow}
+arXiv Categories: {Filled during the BOOTSTRAP flow; leave empty if not applicable}
+Literature Sources: {arXiv / OpenAlex / both}
 `;
 }
 
@@ -79,32 +79,32 @@ export function renderAgentsMd(): string {
 
 ## Workspace Layout
 
-本 agent 的工作目录即为项目根目录（\`$W\`）。所有文件相对于 \`$W\` 组织：
+The agent workspace root is the project root (\`$W\`). All files are organized relative to \`$W\`:
 
 \`\`\`
 $W/
-├── SOUL.md                      # 身份 + 研究方向
-├── AGENTS.md                    # 本文档
-├── config.json                  # 项目配置（关键词、分类、当前天数）
+├── SOUL.md                      # identity and project direction
+├── AGENTS.md                    # this document
+├── config.json                  # project config (keywords, categories, current day)
 │
-├── papers/                      # 文献区：下载的论文
-│   ├── {arxiv_id}/              # arXiv 论文源文件
-│   └── {doi_slug}.pdf           # PDF 文件
+├── papers/                      # literature artifacts
+│   ├── {arxiv_id}/              # arXiv source files
+│   └── {doi_slug}.pdf           # PDF files
 │
-├── knowledge/                   # 知识区：持久知识状态
-│   ├── _index.md                # 全景索引
-│   └── topic-*.md               # 主题文件（上限 50）
+├── knowledge/                   # persistent knowledge state
+│   ├── _index.md                # global index
+│   └── topic-*.md               # topic files (limit 50)
 │
-├── ideas/                       # 想法区：假设与研究想法
-│   ├── hyp-*.md                 # 生成的假设
-│   └── selected_idea.md         # 选中的研究想法
+├── ideas/                       # hypotheses and research ideas
+│   ├── hyp-*.md                 # generated hypotheses
+│   └── selected_idea.md         # selected research idea
 │
-├── experiments/                 # 实验代码区
-│   ├── run.py                   # 入口脚本
+├── experiments/                 # experiment code
+│   ├── run.py                   # entry script
 │   ├── requirements.txt
-│   └── results/                 # 实验结果
+│   └── results/                 # experiment outputs
 │
-├── log/                         # 运行日志
+├── log/                         # run logs
 │   └── {YYYY-MM-DD}.md
 │
 └── skills/                      # workspace skills
@@ -112,34 +112,34 @@ $W/
 
 ## Session Context
 
-你可能在不同类型的 session 中被唤醒：
-- **Main session**：与人类直接对话，可触发 research-pipeline 等编排 skill
-- **Cron session**：定时触发，执行周期性任务（如每日 metabolism）
-- **Spawn session**：被 main session 调度（sessions_spawn），执行一次性重任务
+You may be activated in different session types:
+- **Main session**: direct interaction with a human; can trigger orchestration skills such as \`research-pipeline\`
+- **Cron session**: scheduled execution for recurring work such as daily metabolism
+- **Spawn session**: dispatched by the main session (\`sessions_spawn\`) for one-off heavy tasks
 
-任务指令会在 session 启动时注入，按指令执行即可。
+Task instructions are injected when the session starts. Follow the injected instructions for that session.
 
 ## Conventions
 
 ### File Existence = Step Completion
-检查产出文件是否存在再执行。已存在则跳过。支持崩溃恢复和增量推进。
+Check whether the output file already exists before running a step. If it exists, skip it. This enables crash recovery and incremental progress.
 
 ### Immutability
-产出文件一旦写入不修改，除非用户明确要求。例外：\`project/\` 在 implement-review 迭代中可变。
+Do not modify output files once written unless the user explicitly asks you to. Exception: \`project/\` may change during implement-review iteration.
 
 ### Knowledge File Rules
-- knowledge/ 下的文件是持久知识状态，修改需谨慎
-- 每次修改必须先读取当前内容再更新
-- _index.md 是全景索引，必须与 topic 文件保持同步
-- topic 文件数上限 50，低活跃主题应合并归档
+- Files under \`knowledge/\` are persistent knowledge state and must be edited carefully.
+- Always read the current file before updating it.
+- \`_index.md\` is the global index and must stay in sync with the topic files.
+- Limit topic files to 50. Merge or archive low-activity topics when needed.
 
 ## Research Rigor
 
-- 先读原文，再思考，最后作答
-- 不捏造引用或实验结果，每个断言需有来源
-- 不确定时说「不确定」而非猜测
-- 读论文全文（.tex），不能只读 abstract
-- 想法必须扎根于真实论文
+- Read the source material first, think second, answer third.
+- Do not fabricate citations or experiment results. Every claim needs a source.
+- Say "uncertain" when uncertain instead of guessing.
+- Read the full paper source (\`.tex\`) when available; do not rely on the abstract alone.
+- Ground ideas in real papers rather than unsupported intuition.
 
 ## Skill Outputs Summary
 

From 65b7809d36ab1e2af2d27f1f2ea551296498d471 Mon Sep 17 00:00:00 2001
From: JunkaiWang-TheoPhy <1181100960@qq.com>
Date: Thu, 2 Apr 2026 21:10:17 +0800
Subject: [PATCH 3/3] Update README.en.md

---
 README.en.md | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/README.en.md b/README.en.md
index e75c804..34201af 100644
--- a/README.en.md
+++ b/README.en.md
@@ -230,6 +230,18 @@ Or invoke a specific skill directly with a slash command:
 /dataset-validate
 ```
 
+## New Skills for Midstream ML Work
+
+- `/algorithm-selection`
+  - use this after `/research-survey` and before `/research-plan`
+  - purpose: make 2-3 candidate routes explicit and record `Chosen Route / Rejected Routes / Fallback Route`
+- `/dataset-validate`
+  - use this when `plan_res.md` already exists and you want to validate data quality before implementation or model review
+  - purpose: review data reality, splits, labels, leakage risk, and mock-data usage separately from model quality
+- `/baseline-runner`
+  - use this when `plan_res.md` already exists and the project needs real baseline comparisons
+  - purpose: standardize baselines, protocol, metrics, and result recording, then write `baseline_res.md`
+
 ### 3. Monitor sub-agent progress
 
 When the orchestrator spawns sub-agents, you'll see: