dsh-aris-panel 0.1.0

package/skills/skills-codex-claude-review/research-review/SKILL.md

@@ -0,0 +1,149 @@
+---
+name: "research-review"
+description: "Get a deep critical review of research from Claude via claude-review MCP. Use when user says \"review my research\", \"help me review\", \"get external review\", or wants critical feedback on research ideas, papers, or experimental results."
+---
+
+> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
+>
+> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
+>
+> ```yaml
+> review_independence: cross-family
+> acceptance_status: accepted
+> ```
+
+# Research Review via `claude-review` MCP (high-rigor review)
+
+> **Claude overlay assurance:** this route is a different model family from the Codex executor and records `review_independence: cross-family` plus `acceptance_status: accepted`.
+
+Get a multi-round critical review of research work from an external LLM with maximum reasoning depth.
+
+## Constants
+
+- **REVIEWER_MODEL = `claude-review`** — Claude reviewer invoked through the local `claude-review` MCP bridge. Set `CLAUDE_REVIEW_MODEL` if you need a specific Claude model override.
+- **REVIEWER_BACKEND = `claude-review`** — reviews route through the claude-review MCP (Claude family; cross-family for a Codex executor).
+
+## Context: $ARGUMENTS
+
+## Prerequisites
+
+- Install the base Codex-native skills first: copy `skills/skills-codex/*` into `~/.codex/skills/`.
+- Then install this overlay package: copy `skills/skills-codex-claude-review/*` into `~/.codex/skills/` and allow it to overwrite the same skill names.
+- Register the local reviewer bridge:
+  ```bash
+  codex mcp add claude-review -- python3 ~/.codex/mcp-servers/claude-review/server.py
+  ```
+- This gives Codex access to `mcp__claude-review__review_start`, `mcp__claude-review__review_reply_start`, and `mcp__claude-review__review_status`.
+
+
+## Workflow
+
+### Step 1: Gather Research Context
+Before calling the external reviewer, compile a comprehensive briefing:
+1. Read project narrative documents (e.g., STORY.md, README.md, paper drafts)
+2. Read any memory/notes files for key findings and experiment history
+3. Identify: core claims, methodology, key results, known weaknesses
+
+### Step 2: Initial Review (Round 1)
+Send a detailed prompt with ultra reasoning:
+
+```
+mcp__claude-review__review_start:
+  prompt: |
+    [Full research context + specific questions]
+    Please act as a senior ML reviewer (NeurIPS/ICML level). Start from the
+    assumption that the work is broken somewhere — your job is to find where.
+    Be adversarial. Trust nothing the author tells you — verify everything
+    yourself. Identify:
+    1. Logical gaps or unjustified claims
+    2. Missing experiments that would strengthen the story
+    3. Narrative weaknesses
+    4. Whether the contribution is sufficient for a top venue
+    Please be brutally honest.
+```
+
+After this start call, immediately save the returned `jobId` and poll `mcp__claude-review__review_status` with a bounded `waitSeconds` until `done=true`. Treat the completed status payload's `response` as the reviewer output, and save the completed `threadId` for any follow-up round.
+
+### Step 3: Iterative Dialogue (Rounds 2-N)
+Use `mcp__claude-review__review_reply_start` with the saved completed `threadId`, then poll `mcp__claude-review__review_status` with the returned `jobId` until `done=true` to continue the conversation:
+
+```
+mcp__claude-review__review_reply_start:
+  threadId: [saved reviewer id from Step 2]
+  prompt: |
+    Please continue the review using the revised materials below.
+
+    Revised files:
+    - /absolute/path/to/file1
+    - /absolute/path/to/file2
+
+    Focus on unresolved weaknesses and whether the revision actually fixed them.
+```
+
+After this start call, immediately save the returned `jobId` and poll `mcp__claude-review__review_status` with a bounded `waitSeconds` until `done=true`. Treat the completed status payload's `response` as the reviewer output, and save the completed `threadId` for any follow-up round.
+
+For each round:
+1. **Respond** to criticisms with evidence/counterarguments
+2. **Ask targeted follow-ups** on the most actionable points
+3. **Request specific deliverables**: experiment designs, paper outlines, claims matrices
+
+Key follow-up patterns:
+- "If we reframe X as Y, does that change your assessment?"
+- "What's the minimum experiment to satisfy concern Z?"
+- "Please design the minimal additional experiment package (highest acceptance lift per GPU week)"
+- "Please write a mock NeurIPS/ICML review with scores"
+- "Give me a results-to-claims matrix for possible experimental outcomes"
+
+### Step 4: Convergence
+Stop iterating when:
+- Both sides agree on the core claims and their evidence requirements
+- A concrete experiment plan is established
+- The narrative structure is settled
+
+### Step 5: Document Everything
+Save the full interaction and conclusions to a review document in the project root:
+- Round-by-round summary of criticisms and responses
+- Final consensus on claims, narrative, and experiments
+- Claims matrix (what claims are allowed under each possible outcome)
+- Prioritized TODO list with estimated compute costs
+- Paper outline if discussed
+
+Update project memory/notes with key review conclusions.
+
+If `— composed: <canonical-report-path>` is explicitly present, fold consensus,
+claims matrix, TODOs, and trace links into that report instead of writing a
+standalone review document. Without the directive, write the standalone review
+as documented; never infer composed mode from an existing file. `— standalone`
+always wins. See
+[`output-composition.md`](../shared-references/output-composition.md).
+
+### Step 6: Review Tracing
+
+Save a trace for every `mcp__claude-review__review_start`, `mcp__claude-review__review_reply_start`, or `oracle-pro` review call following `../shared-references/review-tracing.md`. Record the reviewer route, saved threadId, prompt summary, raw response path, decisions, and action items. This preserves the Claude mainline Review Tracing semantics while using Codex-native reviewer calls.
+
+## Key Rules
+
+- **Always ask the Claude reviewer for strict, high-rigor feedback** in every review round.
+- Send comprehensive context in Round 1 — the external model cannot read your files
+- Be honest about weaknesses — hiding them leads to worse feedback
+- Push back on criticisms you disagree with, but accept valid ones
+- Focus on ACTIONABLE feedback — "what experiment would fix this?"
+- Document the completed `threadId` for potential future resumption
+- The review document should be self-contained (readable without the conversation)
+
+## Prompt Templates
+
+### For initial review:
+"I'm going to present a complete ML research project for your critical review. Please act as a senior ML reviewer (NeurIPS/ICML level)..."
+
+### For experiment design:
+"Please design the minimal additional experiment package that gives the highest acceptance lift per GPU week. Our compute: [describe]. Be very specific about configurations."
+
+### For paper structure:
+"Please turn this into a concrete paper outline with section-by-section claims and figure plan."
+
+### For claims matrix:
+"Please give me a results-to-claims matrix: what claim is allowed under each possible outcome of experiments X and Y?"
+
+### For mock review:
+"Please write a mock NeurIPS review with: Summary, Strengths, Weaknesses, Questions for Authors, Score, Confidence, and What Would Move Toward Accept."

package/skills/skills-codex-gemini-review/README.md

@@ -0,0 +1,176 @@
+# skills-codex-gemini-review
+
+This package is a **thin override layer** for users who want:
+
+- **Codex** as the main executor
+- **Gemini** as the reviewer
+- the local `gemini-review` MCP bridge instead of a second Codex reviewer
+
+It is designed to sit on top of the upstream Codex-native package at `skills/skills-codex/`.
+
+Because the executor is Codex and the reviewer is Gemini, overlay traces and
+audit artifacts record `review_independence: cross-family` and
+`acceptance_status: accepted`. The verifier still decides whether all required
+audits reached accepted assurance.
+
+## What this package contains
+
+- Only the reviewer-aware skill overrides that need a different reviewer backend
+- No duplicate templates or resource directories
+- No replacement for the base `skills/skills-codex/` installation
+
+Current overrides:
+
+- `idea-creator`
+- `idea-discovery`
+- `idea-discovery-robot`
+- `research-review`
+- `novelty-check`
+- `research-refine`
+- `auto-review-loop`
+- `grant-proposal`
+- `paper-plan`
+- `paper-figure`
+- `paper-poster-html`
+- `paper-slides`
+- `paper-write`
+- `paper-writing`
+- `auto-paper-improvement-loop`
+
+## Core 8 vs Full 15
+
+To avoid confusion, there are two useful ways to describe this overlay:
+
+- **Core 8**: the direct reviewer-heavy overlay set that maps one-to-one to the earlier Claude-review route
+- **Full 15**: the current reviewer-aware Codex skill surface routed to Gemini in this repository
+
+The **core 8** are:
+
+- `research-review`
+- `novelty-check`
+- `research-refine`
+- `auto-review-loop`
+- `paper-plan`
+- `paper-figure`
+- `paper-write`
+- `auto-paper-improvement-loop`
+
+The additional **7** routed reviewer-aware entry points are:
+
+- `idea-creator`
+- `idea-discovery`
+- `idea-discovery-robot`
+- `grant-proposal`
+- `paper-writing`
+- `paper-slides`
+- `paper-poster-html`
+
+So when comparing against the Claude overlay, the cleanest statement is:
+
+> The Gemini route preserves the same core 8-skill reviewer overlay shape, but expands the practical reviewer-facing surface to 15 skills in the current repo.
+
+## Direct Consumers vs Wrappers
+
+- **12 direct consumers** call `mcp__gemini-review__review_start` / `review_reply_start` / `review_status` themselves:
+  - `research-review`
+  - `novelty-check`
+  - `research-refine`
+  - `auto-review-loop`
+  - `paper-plan`
+  - `paper-figure`
+  - `paper-write`
+  - `auto-paper-improvement-loop`
+  - `idea-creator`
+  - `grant-proposal`
+  - `paper-slides`
+  - `paper-poster-html`
+- **3 wrappers** mostly orchestrate downstream reviewer-aware skills and pass `REVIEWER_MODEL=gemini-review` through:
+  - `idea-discovery`
+  - `idea-discovery-robot`
+  - `paper-writing`
+
+## Install
+
+Before registering the bridge, prepare the direct Gemini API path:
+
+- **Gemini API**: set `GEMINI_API_KEY` or `GOOGLE_API_KEY` (for example in `~/.gemini/.env`)
+
+Optional fallback only:
+
+- **Gemini CLI**: install `gemini` and complete login/auth if you explicitly want `GEMINI_REVIEW_BACKEND=cli`
+
+1. Install the base Codex-native mirror first:
+
+```bash
+bash ~/aris_repo/tools/install_aris_codex.sh ~/your-project
+```
+
+2. Re-run with the Gemini overlay enabled:
+
+```bash
+bash ~/aris_repo/tools/install_aris_codex.sh ~/your-project --reconcile --with-gemini-review-overlay
+```
+
+3. Register the local reviewer bridge:
+
+```bash
+mkdir -p ~/.codex/mcp-servers/gemini-review
+cp mcp-servers/gemini-review/server.py ~/.codex/mcp-servers/gemini-review/server.py
+codex mcp add gemini-review --env GEMINI_REVIEW_BACKEND=api -- python3 ~/.codex/mcp-servers/gemini-review/server.py
+```
+
+The bridge defaults to the direct Gemini API path. This is the intended reviewer backend for this overlay.
+
+If the default API model is temporarily rate-limited on your current free-tier window, keep the same overlay and bridge, and override only the reviewer model:
+
+```bash
+codex mcp remove gemini-review
+codex mcp add gemini-review --env GEMINI_REVIEW_BACKEND=api --env GEMINI_REVIEW_MODEL=gemini-flash-latest -- python3 ~/.codex/mcp-servers/gemini-review/server.py
+```
+
+## Why this exists
+
+The upstream `skills/skills-codex/` path already supports Codex-native execution with a second Codex reviewer via `spawn_agent`.
+
+This package adds a different split:
+
+- executor: Codex
+- reviewer: Gemini direct API
+- transport: `gemini-review` MCP
+
+For long paper and review prompts, the reviewer path uses:
+
+- `review_start`
+- `review_reply_start`
+- `review_status`
+
+This avoids the observed Codex-hosted timeout issue when Gemini is invoked synchronously through a local bridge.
+
+## Validation Summary
+
+This overlay was validated in two ways:
+
+- **Coverage check**: all `15` predefined reviewer-aware skill overrides in this package were checked to confirm they target `gemini-review`
+- **Runtime check**:
+  - the underlying bridge completed sync, async, threaded follow-up, and multimodal local-image review tests
+  - representative Codex-side runs on a private, non-public research repository confirmed that real skill executions could reach the Gemini reviewer path for research-review, idea-generation, and paper-planning style tasks
+
+Operational note:
+
+- Gemini free tier was usable for this workflow in practice, but bursty stress tests could still produce temporary `429` responses
+- on the same setup, a later retry completed sync review, async `review_start` -> `review_status`, and threaded `review_reply_start` -> `review_status` successfully with `GEMINI_REVIEW_MODEL=gemini-flash-latest`
+- for long prompts, prefer the async `review_start` / `review_reply_start` + `review_status` path
+
+## References
+
+- Upstream overlay pattern from ARIS:
+  - <https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/main/skills/skills-codex-claude-review>
+  - <https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/main/mcp-servers/claude-review>
+- Local Gemini reviewer bridge in this repo:
+  - `mcp-servers/gemini-review/README.md`
+- Gemini backends referenced by this overlay:
+  - Official Gemini API: <https://ai.google.dev/api>
+  - Official Gemini CLI: <https://github.com/google-gemini/gemini-cli>
+  - AI Studio API key entry: <https://aistudio.google.com/apikey>
+
+This package keeps the upstream ARIS skill shape, but swaps the reviewer transport to the local `gemini-review` bridge. It now covers every predefined Codex skill in this repo that previously depended on a secondary Codex reviewer or `mcp__codex__codex` review step. We intentionally did not directly depend on a generic Gemini MCP server package because the ARIS review skills rely on the narrow `review*` tool contract, resumable review-thread behavior, and now optional local-image review for poster PNGs.

package/skills/skills-codex-gemini-review/README_CN.md

@@ -0,0 +1,175 @@
+# skills-codex-gemini-review 说明
+
+这是一个**薄覆盖层**，适用于想采用以下组合的用户：
+
+- **Codex** 作为主执行者
+- **Gemini** 作为审稿人
+- 用本地 `gemini-review` MCP bridge 替代“第二个 Codex reviewer”
+
+它不是新造一套完整技能包，而是叠加在上游已有的 `skills/skills-codex/` 之上。
+
+由于执行者是 Codex、审稿人是 Gemini，本 overlay 的 trace/audit 记录
+`review_independence: cross-family` 与 `acceptance_status: accepted`；最终仍由
+审计汇总器确认所有必需阶段是否都达到 accepted。
+
+## 这个包包含什么
+
+- 只包含需要切换 reviewer backend 的 reviewer-aware skill 覆盖文件
+- 不重复打包模板和资源目录
+- 不替代基础的 `skills/skills-codex/` 安装
+
+当前覆盖的技能：
+
+- `idea-creator`
+- `idea-discovery`
+- `idea-discovery-robot`
+- `research-review`
+- `novelty-check`
+- `research-refine`
+- `auto-review-loop`
+- `grant-proposal`
+- `paper-plan`
+- `paper-figure`
+- `paper-poster-html`
+- `paper-slides`
+- `paper-write`
+- `paper-writing`
+- `auto-paper-improvement-loop`
+
+## 核心 8 个 vs 完整 15 个
+
+为了避免误解，这个 overlay 有两种常用描述方式：
+
+- **核心 8 个**：和早先 Claude-review 路线一一对齐的 reviewer-heavy overlay 核心集合
+- **完整 15 个**：当前这个仓库里实际已经切到 Gemini reviewer 的 reviewer-aware Codex 技能面
+
+其中 **核心 8 个** 是：
+
+- `research-review`
+- `novelty-check`
+- `research-refine`
+- `auto-review-loop`
+- `paper-plan`
+- `paper-figure`
+- `paper-write`
+- `auto-paper-improvement-loop`
+
+额外扩展的 **7 个** reviewer-aware 入口是：
+
+- `idea-creator`
+- `idea-discovery`
+- `idea-discovery-robot`
+- `grant-proposal`
+- `paper-writing`
+- `paper-slides`
+- `paper-poster-html`
+
+所以和 Claude overlay 对比时，最准确的一句话是：
+
+> Gemini 这条路保持了相同的核心 8-skill reviewer overlay 形状，但在当前仓库里把实际 reviewer 入口扩展到了 15 个。
+
+## 直接消费者 vs wrapper
+
+- **12 个直接消费者**：自己直接调用 `mcp__gemini-review__review_start` / `review_reply_start` / `review_status`
+  - `research-review`
+  - `novelty-check`
+  - `research-refine`
+  - `auto-review-loop`
+  - `paper-plan`
+  - `paper-figure`
+  - `paper-write`
+  - `auto-paper-improvement-loop`
+  - `idea-creator`
+  - `grant-proposal`
+  - `paper-slides`
+  - `paper-poster-html`
+- **3 个 wrapper**：主要串联下游 reviewer-aware skill，并传递 `REVIEWER_MODEL=gemini-review`
+  - `idea-discovery`
+  - `idea-discovery-robot`
+  - `paper-writing`
+
+## 安装方式
+
+注册 bridge 之前，请先准备好 direct Gemini API 路径：
+
+- **Gemini API**：设置 `GEMINI_API_KEY` 或 `GOOGLE_API_KEY`（例如写进 `~/.gemini/.env`）
+
+可选 fallback：
+
+- **Gemini CLI**：只有在你明确想用 `GEMINI_REVIEW_BACKEND=cli` 时，才需要本机安装 `gemini` 并完成登录/认证
+
+1. 先安装上游原生 Codex 基座：
+
+```bash
+bash ~/aris_repo/tools/install_aris_codex.sh ~/your-project
+```
+
+2. 再用 Gemini overlay 重跑一次：
+
+```bash
+bash ~/aris_repo/tools/install_aris_codex.sh ~/your-project --reconcile --with-gemini-review-overlay
+```
+
+3. 注册本地 reviewer bridge：
+
+```bash
+mkdir -p ~/.codex/mcp-servers/gemini-review
+cp mcp-servers/gemini-review/server.py ~/.codex/mcp-servers/gemini-review/server.py
+codex mcp add gemini-review --env GEMINI_REVIEW_BACKEND=api -- python3 ~/.codex/mcp-servers/gemini-review/server.py
+```
+
+bridge 默认直接走 Gemini API。这也是这套 overlay 预期使用的 reviewer backend。
+
+如果默认 API 模型在你当前免费层窗口里临时被限流，不需要改 overlay 和 bridge 结构，只需要覆盖 reviewer model：
+
+```bash
+codex mcp remove gemini-review
+codex mcp add gemini-review --env GEMINI_REVIEW_BACKEND=api --env GEMINI_REVIEW_MODEL=gemini-flash-latest -- python3 ~/.codex/mcp-servers/gemini-review/server.py
+```
+
+## 为什么需要这个包
+
+上游 `skills/skills-codex/` 已经支持 Codex 原生执行，并通过 `spawn_agent` 使用第二个 Codex 做 reviewer。
+
+这个覆盖层新增的是另一种分工：
+
+- 执行者：Codex
+- 审稿人：Gemini direct API
+- 传输层：`gemini-review` MCP
+
+对于长论文和长 review prompt，这条 reviewer 路径会改用：
+
+- `review_start`
+- `review_reply_start`
+- `review_status`
+
+这样可以绕开 Codex 宿主下，本地 Gemini bridge 同步等待时更容易出现的超时问题。
+
+## 验证结果摘要
+
+这套 overlay 做了两类验证：
+
+- **覆盖检查**：本包里的 `15` 个预定义 reviewer-aware skill override 都核对过，确认目标都是 `gemini-review`
+- **运行时检查**：
+  - 底层 bridge 已完成同步、异步、thread 续聊、本地图像多模态审查等测试
+  - 在一个私有、未公开的研究仓库上，代表性的 Codex 实跑已经确认：真实 skill 执行可以进入 Gemini reviewer 路径，覆盖研究审稿、idea 生成、论文规划这几类工作流
+
+实际使用上的结论：
+
+- Gemini 免费层对这条工作流是可用的，但密集压测时仍可能出现临时 `429`
+- 在同一套环境上的后续重试里，把 `GEMINI_REVIEW_MODEL` 设为 `gemini-flash-latest` 后，同步 review、异步 `review_start` -> `review_status`、以及带 thread 的 `review_reply_start` -> `review_status` 都已跑通
+- 对长 prompt，优先使用异步 `review_start` / `review_reply_start` + `review_status`
+
+## 引用与来源
+
+- 上游 ARIS 的 overlay 组织方式：
+  - <https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/main/skills/skills-codex-claude-review>
+  - <https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/main/mcp-servers/claude-review>
+- 本仓库里的本地 Gemini reviewer bridge：
+  - `mcp-servers/gemini-review/README.md`
+- 本覆盖层依赖的 Gemini 官方后端：
+  - 官方 Gemini API：<https://ai.google.dev/api>
+  - 官方 Gemini CLI：<https://github.com/google-gemini/gemini-cli>
+  - AI Studio API key：<https://aistudio.google.com/apikey>
+
+这个包保持了上游 ARIS review skill 的组织和调用形状，但把 reviewer transport 换成了本地 `gemini-review` bridge。现在它覆盖了本仓库里所有原先依赖第二个 Codex reviewer 或 `mcp__codex__codex` 审稿步骤的预定义 Codex skill。这里没有直接依赖通用的 Gemini MCP server 成品包，因为 ARIS 这组 review skills 依赖的是特定的 `review*` 工具契约、可恢复的 review thread 语义，以及 poster PNG 这类本地图像审查入口。