Xpersona
agentCLAWHUBUnverified

tech-content-review-panel

Reviews a tech/AI/industry research or in-depth analysis long-form article before publishing, via a fixed eight-role expert panel (target-reader reps, quality gatekeepers incl. fact+originality check, distribution gatekeeper) in an evaluate-then-optimize loop. Applies to tech/AI/data deep-dives, sector judgment and research pieces — not news, marketing, docs, tutorials, or short opinion posts. Trigger when the user asks to 会审/评审/review a finished deep-analysis draft or wants tech content 接近完美/可发布. Skill: tech-content-review-panel Owner: haiyangchenbj Summary: Reviews a tech/AI/industry research or in-depth analysis long-form article before publishing, via a fixed eight-role expert panel (target-reader reps, quality gatekeepers incl. fact+originality check, distribution gatekeeper) in an evaluate-then-optimize loop. Applies to tech/AI/data deep-dives, sector judgment and research pieces — not news, marketing, d

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.2.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 11, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 11, 2026
Adoption signal
1.1K downloadsadoption · observed Oct 11, 2026
Latest release
1.2.1release · observed Oct 8, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17672gh0nx9qr7sjp84kz7xen83jv7v:tech-content-review-panel
  1. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-haiyangchenbj-tech-content-review-panel/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

105,065 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: tech-content-review-panel
description: Reviews a tech/AI/industry research or in-depth analysis long-form article before publishing, via a fixed eight-role expert panel (target-reader reps, quality gatekeepers incl. fact+originality check, distribution gatekeeper) in an evaluate-then-optimize loop. Applies to tech/AI/data deep-dives, sector judgment and research pieces — not news, marketing, docs, tutorials, or short opinion posts. Trigger when the user asks to 会审/评审/review a finished deep-analysis draft or wants tech content 接近完美/可发布.
version: "1.2.1"
agent_created: true
read_when:
  - "会审 / 评审 / review this article"
  - "多视角挑刺 / 让内容接近完美 / 可发布质量"
  - "tech/AI/行业深度稿成稿后的质量把关"
slug: tech-content-review-panel
displayName: Tech Content Review Panel
description_zh: "技术内容评审委员会：发布前用固定八角色专家小组（目标读者代表、质量门禁含事实与原创检查、分发门禁）以先评估后优化循环，评审技术/AI/行业研究深度长文。"
not_for:
  - Fact-checking a single claim in isolation (use a claim-audit skill instead)
  - Rewriting or restructuring the article itself (review only; revision guidance is advisory)
  - News, marketing copy, documentation, tutorials, or short opinion posts
  - Reviewing content that has no finished draft yet
---

# Tech Content Review Panel

A tech/AI/industry deep-analysis piece aimed at an industry readership and built to establish a professional personal brand is easy to miss with a single perspective. This skill provides a fixed **eight-role expert panel** that reviews a finished draft from multiple angles, giving blunt per-role feedback to push it toward publish-ready quality.

**Design pattern: Evaluator-Optimizer** — the panel evaluates, you revise per the feedback, then re-check to confirm no new problems before finalizing. It is a generate → evaluate → revise loop.

## When to use

**Applies to**: tech / AI / industry research or in-depth analysis **long-form** articles aimed at an industry readership (industry deep-dives, sector judgments, research pieces).
**Does not apply to**: news, marketing copy, product docs, tutorials, or short opinion posts — different goals and criteria mean this panel would mismatch. When such content triggers, tell the user this skill does not apply.

## Review workflow

### Step 1 [Deterministic] Confirm input and applicability
- Confirm there is a finished deep-analysis draft (file path or full text). If none, stop and ask the user to finish a first draft first.
- Judge whether the content type applies (see above). If not, stop and explain.

### Step 2 [LLM] G1 Fact & originality check (gate first — reject if it fails)
- **Facts**: verify every number / company name / date / policy / event. Foundational facts must be verified online with traceable sources. Distinguish confirmed / to-verify / possibly-stale (watch timeliness — do not present old news as new).
- **Originality**: search (WebSearch) the core argument, framework, and signature phrasing to judge whether it is "independently derived / deepened from public views" (k

README.md

# Tech Content Review Panel

An eight-role expert review panel for tech/AI/industry deep-analysis articles. It critiques a finished draft from multiple angles and pushes it toward publish-ready quality — built for content that aims to establish a professional personal brand with an industry audience.

## What it does

Runs a fixed panel over a finished draft in an **evaluate → revise → re-check** loop:

- **4 target-reader representatives** — a tech decision-maker, a cross-domain senior expert, an investor/strategist, and a blunt veteran. They judge whether the piece is valuable, expert, and free of empty prose.
- **3 quality gatekeepers** — a fact-and-originality checker (web-verifies foundational facts, searches for idea collisions/plagiarism risk), a style red-line scanner, and a structure-and-depth reviewer.
- **1 distribution gatekeeper** — a tech media editor who checks title hooks, opening retention, memorable points, and multi-platform fit.

## When to use

**Applies to**: tech / AI / data industry deep-dives, sector judgment articles, research pieces for an industry readership.

**Does not apply to**: news, marketing copy, product docs, tutorials, or short opinion posts.

## How to use

Trigger it after finishing a deep-analysis draft:

> "Review this article with the panel."

After the panel revision, run a separate **reader-fit test**. It is not a ninth panelist or a second review round: it tests whether selected target readers correctly understand the core message, scope and technical level. Lock the article positioning first, select 3–4 roles that fit the piece, and triage feedback as must-fix / suggested / optional / reject-or-park. Do not adopt every role's opinion.

## Design

- **Pattern**: Evaluator-Optimizer.
- **Hard gate**: style red-lines must be grep-clean before finalizing.
- **Tension handling**: the professional-vs-distribution tension (hook vs restraint) is surfaced explicitly and left for the author to decide, never forced into agreement.

See `references/depth-playbook.md` for the six depth moves used by the structure reviewer.

## License

MIT

_meta.json

{
  "ownerId": "kn70yg6zwmkftx4939qrs89awx82rr9a",
  "slug": "tech-content-review-panel",
  "version": "1.2.1",
  "publishedAt": 1791432298404
}

references/depth-playbook.md

# 专业纵深六套路（G3 评估依据）

判断一篇研究/深度文章有没有"专家级纵深"、能不能碾压编译稿，对照这六个套路。至少命中 3 个才算有纵深。每个套路附一个来自"欧洲 AI·开源即主权"篇的实例。

## ① 点破想当然的因果

找出读者会默认、但其实不成立的因果链，戳破它。
- 实例：多数人默认"权重可下载=拿到主权"。点破：自托管 675B 模型需要 8×H200 节点+运维团队，多数企业最后还是跑在美国云上——权重是自由的，跑权重的底座不是。

## ② 给分层框架拆解被滥用的概念

把一个被当成单一概念、其实被营销滥用的词，拆成清晰的层次。
- 实例："主权"不是一个开关，拆成数据主权/模型主权/运营主权/算力主权四层，指出开源只给足"模型主权"那一层。

## ③ 找出立论对象自身的矛盾

在被分析的对象内部，找一个它自己没解决或自相矛盾的点。这是最显专业的一招。
- 实例：Mistral 靠开源拿 AI Act 合规豁免，但它的旗舰因训练算力超 10²⁵ FLOPs 落进系统性风险区，恰恰不能享开源豁免——真正吃满豁免的是它的小模型。

## ④ 放进历史脉络

把一个看似新的现象，接到一条已有的历史线索上，显出它不是孤立事件。
- 实例：Mistral"开源引流、服务变现"是 Red Hat/MongoDB/Elastic 走了二十年的开源商业化老路，区别是多打了一张欧洲主权牌。

## ⑤ 给横向参照系

用同类对象的对比，凸显分析对象的独特性。
- 实例：同样是开源，Meta 为打 OpenAI 商业模式、中国为突破生态围堵、欧洲为主权合规——同一动作三种战略。

## ⑥ 点破判断的边界

给出核心判断后，主动指出它的适用边界和失效条件，拒绝绝对化。
- 实例：规则主权是防御性的，守得住本地市场但抢不了全球；且压在"算力差距还没大到不可接受"的前提上，一旦前沿能力鸿沟拉开，控制权的溢价会失效。

## 使用提示

- 这六招不必全用，但优质深度稿通常命中 3-4 个。
- ③（自身矛盾）和 ①（想当然因果）最能拉开与编译稿的差距，优先找。
- 每一招都要落到具体事实和数据，不能空转成"看似深刻的正确废话"。

README_zh.md

# 科技内容多角色会审

针对科技/AI/产业深度稿的八角色专家评审团。对成稿从多视角挑刺，逼近可发布质量——面向"用内容建立专业个人 IP、读者是行业人"的场景。

## 它做什么

对成稿跑一套固定的评审团，走"评估 → 修订 → 复审"循环：

- **4 位目标读者代表** —— 技术决策者、跨域资深专家、投资人/战略分析师、专业毒舌老兵。判断内容有没有价值、够不够专业、有没有空话。
- **3 位质量守门人** —— 事实与原创核查（联网核实立论基石、检索比对防撞车洗稿）、风格红线扫描、结构与专业纵深评估。
- **1 位传播守门人** —— 技术媒体编辑，看标题钩子、开头留人、可传播记忆点、多平台适配。

## 何时使用

**适用**：科技/AI/数据产业的深度解读、产业判断、研究稿，面向行业读者。

**不适用**：新闻资讯、营销文案、产品文档、技术教程、纯观点短评。

## 怎么用

在深度稿成稿后触发：

> "用评审团会审这篇文章。"

八角色会审完成后，另跑一次 **reader-fit 阅读测试**：它不是第九个角色，也不是第二轮会审，而是测试目标读者能否正确理解文章的核心信息、范围和技术层级。先锁文章定位，再按文章需要选择 3–4 个代表角色；意见分为必改 / 建议改 / 可选 / 拒绝或停放，不能一概采用。

## 设计

- **模式**：Evaluator-Optimizer（评估-优化）。
- **硬门槛**：定稿前风格红线必须 grep 扫描清零。
- **张力处理**：专业与传播的张力（钩子 vs 克制）显性列出、交给作者拍板，不强行统一。

结构评审用到的"六个纵深套路"见 `references/depth-playbook.md`。

## 许可

MIT

Related agents

Same protocol, similar job.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/haiyangchenbj/skills/tech-content-review-panel",
      "sourceUrl": "https://clawhub.ai/haiyangchenbj/skills/tech-content-review-panel",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T14:07:51.198Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-haiyangchenbj-tech-content-review-panel/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-haiyangchenbj-tech-content-review-panel/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-11T14:07:51.198Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.1K downloads",
      "href": "https://clawhub.ai/haiyangchenbj/tech-content-review-panel",
      "sourceUrl": "https://clawhub.ai/haiyangchenbj/tech-content-review-panel",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T14:07:51.198Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.2.1",
      "href": "https://clawhub.ai/haiyangchenbj/tech-content-review-panel",
      "sourceUrl": "https://clawhub.ai/haiyangchenbj/tech-content-review-panel",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-10-08T04:04:58.404Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-haiyangchenbj-tech-content-review-panel/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-haiyangchenbj-tech-content-review-panel/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.2.1",
      "description": "Add title-anchor gate: editor role must verify headline carries a concrete anchor (who/scenario/problem); abstract or filename-style titles are must-fix",
      "href": "https://clawhub.ai/haiyangchenbj/tech-content-review-panel",
      "sourceUrl": "https://clawhub.ai/haiyangchenbj/tech-content-review-panel",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-10-08T04:04:58.404Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 11, 2026.

Sponsored

Ads related to tech-content-review-panel and adjacent AI workflows.