Back to Details

quality-loop

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Quality Loop

Quality Loop

Iterative drafting system with backpressure from judge personas. Creates high-quality content through systematic source gathering, hook-first drafting, and multi-pass quality gates.
基于评审角色反向约束的迭代式写作系统。通过系统化的源内容收集、钩子先行写作法和多轮质量关卡，打造高质量内容。

When to Use This Skill

何时使用该技能

UNIVERSAL QUALITY GATES: This skill triggers for ALL public-facing content.
通用质量关卡： 该技能适用于所有对外发布的内容。

Trigger Points by Content Type

按内容类型划分的触发节点

Content TypeTrigger PointMode
NewsletterAfter draft, before sendFull 5-judge
Deep Dive/ArticleBefore Webflow publishFull 5-judge
Podcast blogBefore publishFull 5-judge
LinkedIn postAfter draft, before scheduleLite 3-judge
X postAfter draft, before scheduleLite 3-judge
InstagramAfter draft + visualLite 3-judge
FacebookAfter draft, before scheduleLite 3-judge
内容类型触发节点模式
通讯稿草稿完成后，发送前完整5评审模式
深度分析/文章Webflow发布前完整5评审模式
播客配套博文发布前完整5评审模式
LinkedIn帖子草稿完成后，排期前轻量3评审模式
X帖子草稿完成后，排期前轻量3评审模式
Instagram帖子草稿+视觉内容完成后轻量3评审模式
Facebook帖子草稿完成后，排期前轻量3评审模式

Full 5-Judge Mode

完整5评审模式

For long-form content (articles, newsletters, blog posts):
  • Human Detector (BLOCKING)
  • Accuracy Checker (BLOCKING)
  • OpenEd Voice (BLOCKING)
  • Reader Advocate (BLOCKING)
  • SEO Advisor (ADVISORY)
适用于长篇内容（文章、通讯稿、博文）：
  • Human Detector（阻塞型）
  • Accuracy Checker（阻塞型）
  • OpenEd Voice（阻塞型）
  • Reader Advocate（阻塞型）
  • SEO Advisor（建议型）

Lite 3-Judge Mode

轻量3评审模式

For social posts (faster, focused on voice and AI tells):
  • AI-Tell Judge (BLOCKING) - Hard blocks only
  • Voice Judge (BLOCKING) - Brand alignment
  • Platform Judge (ADVISORY) - Platform-specific optimization
See "Lite Quality Loop for Social" section below.
适用于社交平台帖子（更快捷，聚焦语气和AI特征）：
  • AI-Tell Judge（阻塞型）- 仅严重问题会直接驳回
  • Voice Judge（阻塞型）- 品牌调性对齐
  • Platform Judge（建议型）- 平台专属优化
详见下方「社交内容轻量质量循环」章节。

The Quality Loop Process

质量循环流程

SOURCES → HOOK → DRAFT → JUDGES → ITERATE
    ↑                         ↓
    └─────── (if blocked) ────┘
SOURCES → HOOK → DRAFT → JUDGES → ITERATE
    ↑                         ↓
    └─────── (if blocked) ────┘

Phase 1: Source Compilation

阶段1：源内容整合

Before drafting, gather all relevant sources into a single compiled file.
Source Search Order:
  1. Proprietary content first - Search OpenEd podcast transcripts, newsletters, Slack
  2. Content database - Grep 
    Content/
    for related themes (not just exact terms)
  3. External research - Web search for biography, facts, external validation
When no direct coverage exists: Expand the search to related themes. For example, if writing about "Daniel Greenberg":
  • Search for "democratic education"
  • Search for "self-directed"
  • Search for "trust children"
  • Search for related thinkers who discuss him (Peter Gray)
Source File Format:
markdown
undefined
写作前，将所有相关源内容整合到一个单独的文件中。
源内容搜索优先级：
  1. 自有内容优先 - 搜索OpenEd播客文稿、通讯稿、Slack内容
  2. 内容数据库 - 在
    Content/
    目录中搜索相关主题（不限于精确匹配）
  3. 外部调研 - 网页搜索传记、事实、外部验证信息
无直接相关内容时： 扩大搜索范围至相关主题。例如，若撰写关于「Daniel Greenberg」的内容：
  • 搜索「民主教育」
  • 搜索「自主导向」
  • 搜索「信任儿童」
  • 搜索讨论他的相关学者（如Peter Gray）
源内容文件格式：
markdown
undefined

Source: [Topic] Compiled

Source: [Topic] Compiled

Biographical Facts

传记事实

  • Key dates, roles, locations
  • Verified from multiple sources
  • 关键日期、职位、所在地
  • 经多源验证

OpenEd Proprietary Content

OpenEd自有内容

From Podcast [Episode]:
"Direct quote..."
From Newsletter:
"Direct quote..."
来自播客[期数]：
"直接引用内容..."
来自通讯稿：
"直接引用内容..."

Key Themes

核心主题

  • Theme 1 with supporting evidence
  • Theme 2 with supporting evidence
  • 主题1及支撑证据
  • 主题2及支撑证据

SEO Notes

SEO备注

  • Primary keyword: [keyword] ([volume]/mo)
  • Secondary keywords: [list]
  • 主关键词：[关键词]（[搜索量]/月）
  • 次关键词：[列表]

Sources for Verification

验证来源

  • [URL 1]
  • [URL 2]

---
  • [URL 1]
  • [URL 2]

---

Phase 2: Hook First

阶段2：钩子先行

Never draft without user approval of the hook angle. Propose 4-6 hook options with clear differentiation.
Hook Proposal Format:
#HookOpening LineWhy It Works
1[Name]"[First sentence]"[Reasoning]
2[Name]"[First sentence]"[Reasoning]
............
Good hooks:
  • Start with a specific moment, fact, or tension
  • Create curiosity without clickbait
  • Connect to something the reader cares about
  • Differentiate from what's already ranking
Bad hooks:
  • Generic "In today's world..." openings
  • Definition-first approaches ("X is defined as...")
  • Vague statements that could apply to anyone
After user selects a hook, proceed to drafting.
For series content: When writing multiple pieces on similar topics (e.g., profiles of thinkers), ensure each piece has a structurally different approach to avoid sameness. Examples:
  • Profile A: Personal drama narrative
  • Profile B: Scientific/research angle
  • Profile C: Evolution story (phases of career)
  • Profile D: Institutional critique
  • Profile E: Evidence/longevity angle
Track the structural approach used for each piece to ensure variety.
未获得用户对钩子角度的批准前，不得开始写作。提供4-6个差异化明确的钩子选项。
钩子提案格式：
#钩子开篇句优势说明
1[名称]"[第一句话]"[理由]
2[名称]"[第一句话]"[理由]
............
优质钩子：
  • 以特定场景、事实或矛盾点开篇
  • 引发好奇心但不标题党
  • 关联读者关心的内容
  • 与已有的高排名内容形成差异
劣质钩子：
  • 通用的「在当今世界...」开篇
  • 先定义的方式（「X被定义为...」）
  • 可适用于任何内容的模糊表述
用户选定钩子后，方可开始写作。
系列内容注意事项： 撰写同主题系列内容（如人物专访）时，需确保每篇内容结构不同，避免同质化。示例：
  • 专访A：个人叙事风格
  • 专访B：科研视角
  • 专访C：职业发展历程
  • 专访D：机构批判角度
  • 专访E：实证/长期影响力视角
记录每篇内容采用的结构方式，确保多样性。

Phase 3: Draft

阶段3：写作草稿

Create the full draft following OpenEd style guidelines.
Draft Structure:
markdown
undefined
遵循OpenEd风格指南完成完整草稿。
草稿结构：
markdown
undefined

Draft v[N]: [Title]

Draft v[N]: [标题]

Date: [YYYY-MM-DD] Type: [New / Enhancement] Target: ~[X] words
日期： [YYYY-MM-DD] 类型： [全新内容 / 内容优化] 目标字数： ~[X]字

META ELEMENTS

元数据

Title Options:
  1. [Option 1] ([char count])
  2. [Option 2] ([char count]) ...
Meta Description (155 chars): [Description]
URL: /blog/[slug]
标题选项：
  1. [选项1]（[字符数]）
  2. [选项2]（[字符数]） ...
元描述（155字符）： [描述内容]
URL： /blog/[slug]

ARTICLE

文章正文

[Full article content]
[完整文章内容]

NOTES FOR JUDGES

评审备注

Word count: ~[X] words Internal links: [N] External links: [N] Target keywords: [list] OpenEd connection: [what makes this ours] Unique angle: [what differentiates from competitors]

---
字数： ~[X]字 内部链接数： [N] 外部链接数： [N] 目标关键词： [列表] OpenEd关联点： 内容专属特色 独特视角： 与竞品的差异点

---

Phase 4: Five Judges

阶段4：五大评审

Run every draft through all five judges in order. If ANY blocking judge fails, fix and re-run that judge before proceeding.
Full judge references: See 
references/
folder for expanded criteria.
按顺序将所有草稿提交给五位评审。若任何阻塞型评审未通过，需修改后重新提交该评审，方可推进后续流程。
完整评审标准： 详见
references/
文件夹中的扩展准则。

Judge 1: Human Detector (BLOCKING)

评审1：Human Detector（阻塞型）

See: 
references/human-detector.md
Scans for AI tells. Zero tolerance for:
  • Correlative constructions ("X isn't just Y - it's Z")
  • Dramatic contrast reveals ("Not X. Y.")
  • AI vocabulary (delve, comprehensive, crucial, landscape, journey, tapestry, myriad)
  • Staccato patterns ("No fluff. No filler. Just results.")
  • Triple Threat Syndrome (forced three-adjective stacks)
VERDICT: PASS only if zero AI tells found.
参考：
references/human-detector.md
扫描AI生成特征。零容忍以下内容：
  • 关联句式（「X不只是Y——更是Z」）
  • 戏剧性反转表述（「不是X，是Y」）
  • AI专属词汇（delve、comprehensive、crucial、landscape、journey、tapestry、myriad）
  • 断句排比（「无冗余，无填充，只讲干货」）
  • 三重形容词堆砌（强行使用三个形容词的组合）
评审结果： 仅当未发现任何AI特征时，判定为通过。

Judge 2: Accuracy Checker (BLOCKING)

评审2：Accuracy Checker（阻塞型）

See: 
references/accuracy-checker.md
Verifies all factual claims against compiled sources:
  • Dates, names, quotes must match sources exactly
  • Statistics need citations
  • Timeline events in correct order
  • No unverifiable claims presented as fact
VERDICT: PASS only if all facts verified.
参考：
references/accuracy-checker.md
对照整合的源内容验证所有事实性声明：
  • 日期、姓名、引用内容必须与源内容完全一致
  • 统计数据需标注引用来源
  • 时间线事件顺序正确
  • 不得将未验证的声明作为事实呈现
评审结果： 仅当所有事实均验证通过时，判定为通过。

Judge 3: OpenEd Voice (BLOCKING)

评审3：OpenEd Voice（阻塞型）

See: 
references/opened-voice.md
Core stance: Pro-child, not anti-school.
  • Describes, doesn't prescribe
  • Practical takeaways present
  • 3+ internal links
  • Uses proprietary OpenEd content
VERDICT: PASS only if aligned with stance.
参考：
references/opened-voice.md
核心立场：支持儿童，而非反对学校。
  • 客观描述，不强行说教
  • 包含实用要点
  • 至少3个内部链接
  • 使用OpenEd自有内容
评审结果： 仅当内容符合核心立场时，判定为通过。

Judge 4: Reader Advocate (BLOCKING)

评审4：Reader Advocate（阻塞型）

See: 
references/reader-advocate.md
Assesses engagement:
  • Hook creates curiosity (not definitions)
  • Logical section flow
  • Scannable structure
  • Appropriate length
  • Strong ending
VERDICT: PASS only if engaging throughout.
参考：
references/reader-advocate.md
评估内容吸引力：
  • 钩子能引发好奇心（而非定义式开篇）
  • 章节逻辑流畅
  • 结构易于扫描阅读
  • 篇幅合适
  • 结尾有力
评审结果： 仅当全程保持吸引力时，判定为通过。

Judge 5: SEO Advisor (ADVISORY)

评审5：SEO Advisor（建议型）

See: 
references/seo-advisor.md
Evaluates search optimization. Does not block.
  • Keyword in title, first 100 words, H2s
  • Meta elements optimized
  • 5+ internal links, 2-3 external
  • Featured snippet opportunities
VERDICT: Advisory feedback only.
参考：
references/seo-advisor.md
评估搜索优化效果，不做阻塞性限制：
  • 关键词出现在标题、前100字、二级标题中
  • 元数据优化到位
  • 至少5个内部链接、2-3个外部链接
  • 具备获得精选摘要的潜力
评审结果： 仅提供建议性反馈。

Phase 5: Iterate

阶段5：迭代优化

If any blocking judge fails:
  1. Make the specific fixes identified
  2. Re-run ONLY the failed judge
  3. If pass, continue to next judge
  4. If fail again, make additional fixes and repeat
After all judges pass:
  • Update status in tracking document
  • Move to next piece or finalize for publication
若任何阻塞型评审未通过：
  1. 根据评审意见进行针对性修改
  2. 仅重新提交未通过的评审
  3. 若通过，继续推进下一个评审
  4. 若仍未通过，再次修改并重复流程
所有评审通过后：
  • 在跟踪文档中更新状态
  • 进入下一篇内容创作或最终发布环节

Folder Structure

文件夹结构

The folder structure depends on the project type. Organize sources and drafts logically.
Example for profile series:
project/
├── sources/
│   ├── person-a/compiled-sources.md
│   └── person-b/compiled-sources.md
├── drafts/
│   ├── person-a/v1.md
│   └── person-b/v1.md
└── TRACKING.md
Example for guide project:
project/
├── sources/compiled-sources.md
├── drafts/
│   ├── v1.md
│   ├── v2.md
│   └── final.md
└── TRACKING.md
文件夹结构取决于项目类型。需合理组织源内容和草稿文件。
人物专访系列示例：
project/
├── sources/
│   ├── person-a/compiled-sources.md
│   └── person-b/compiled-sources.md
├── drafts/
│   ├── person-a/v1.md
│   └── person-b/v1.md
└── TRACKING.md
指南项目示例：
project/
├── sources/compiled-sources.md
├── drafts/
│   ├── v1.md
│   ├── v2.md
│   └── final.md
└── TRACKING.md

Tracking Progress

进度跟踪

Maintain a tracking document showing status of each piece.
Tracking Table Format:
ItemSourcesHookDraftHDACOVRASEOStatus
[Name]DONE[Hook name]v1PASSPASSPASSPASSPASSCOMPLETE
[Name]DONEpending------NEEDS HOOK
Legend:
  • HD = Human Detector
  • AC = Accuracy Checker
  • OV = OpenEd Voice
  • RA = Reader Advocate
  • SEO = SEO Advisor
维护跟踪文档，记录每篇内容的状态。
跟踪表格格式：
内容项源内容钩子草稿HDACOVRASEO状态
[名称]已完成[钩子名称]v1通过通过通过通过通过已完成
[名称]已完成待确认------待确认钩子
缩写说明：
  • HD = Human Detector
  • AC = Accuracy Checker
  • OV = OpenEd Voice
  • RA = Reader Advocate
  • SEO = SEO Advisor

Lite Quality Loop for Social

社交内容轻量质量循环

Faster quality checks for social posts. Run after draft, before scheduling.
针对社交平台帖子的快速质量检查，在草稿完成后、排期前执行。

Judge 1: AI-Tell Judge (BLOCKING)

评审1：AI-Tell Judge（阻塞型）

Hard blocks - auto-reject if ANY found:
  • Correlative constructions ("X isn't just Y - it's Z")
  • Banned words: delve, comprehensive, crucial, leverage, landscape
  • Setup phrases: "The best part?", "What if I told you", "Here's the thing"
  • Staccato patterns: "No fluff. No filler. Just results."
  • Em dashes without spaces (use " - " not "—")
VERDICT: PASS only if zero hard blocks found.
严重问题——发现任意一项直接驳回：
  • 关联句式（「X不只是Y——更是Z」）
  • 禁用词汇：delve、comprehensive、crucial、leverage、landscape
  • 套路句式：「最棒的是？...」「如果我告诉你...」「重点是...」
  • 断句排比：「无冗余，无填充，只讲干货」
  • 无空格的破折号（使用「 - 」而非「—」）
评审结果： 仅当未发现任何严重问题时，判定为通过。

Judge 2: Voice Judge (BLOCKING)

评审2：Voice Judge（阻塞型）

Checks:
  • Sounds like OpenEd/brand account (not personal blog)
  • Aligns with Open Education values (parent empowerment, learner agency)
  • Appropriate tone for platform
  • No preachy or prescriptive language
VERDICT: PASS only if brand-aligned.
检查项：
  • 符合OpenEd/品牌账号语气（而非个人博客风格）
  • 符合开放教育价值观（赋能家长、学习者自主性）
  • 符合平台调性
  • 无说教或强制指令性语言
评审结果： 仅当内容符合品牌调性时，判定为通过。

Judge 3: Platform Judge (ADVISORY)

评审3：Platform Judge（建议型）

Platform-specific checks:
PlatformChecklist
LinkedIn200-500 words, links in comments, 3-5 hashtags, hook in first 2 lines
X70-100 chars optimal, 1-2 hashtags, retweet-worthy
InstagramVisual-first, caption supports, 5-10 hashtags, first 150 chars hook
FacebookNo external links, no hashtags, ends with question/engagement prompt
VERDICT: Advisory feedback - does not block.
平台专属检查项：
平台检查清单
LinkedIn200-500字，链接放在评论区，3-5个话题标签，钩子在前2行
X最优70-100字符，1-2个话题标签，适合转发
Instagram视觉优先，配文辅助，5-10个话题标签，前150字符为钩子
Facebook无外部链接，无话题标签，以问题或互动引导结尾
评审结果： 仅提供建议性反馈，不做阻塞性限制。

Lite Loop Process

轻量循环流程

DRAFT → AI-Tell Judge → Voice Judge → Platform Judge → SCHEDULE
             ↓ (fail)        ↓ (fail)
           FIX & RETRY     FIX & RETRY
草稿 → AI-Tell评审 → Voice评审 → Platform评审 → 排期
             ↓（未通过）        ↓（未通过）
           修改并重审     修改并重审

Quick Reference: AI Patterns to Avoid

快速参考：需避免的AI生成模式

Correlative Constructions (Most Common Tell)

关联句式（最常见特征）

  • "X isn't just Y - it's Z"
  • "X didn't Y. It Z."
  • "The goal isn't X - it's Y"
  • "It's not about X, it's about Y"
  • 「X不只是Y——更是Z」
  • 「X没有Y，而是Z」
  • 「目标不是X——而是Y」
  • 「关键不是X，而是Y」

Forbidden Words

禁用词汇

delve, comprehensive, crucial, vital, leverage, landscape, navigate, foster, facilitate, realm, paradigm, embark, journey, tapestry, myriad, multifaceted, seamless, cutting-edge
delve, comprehensive, crucial, vital, leverage, landscape, navigate, foster, facilitate, realm, paradigm, embark, journey, tapestry, myriad, multifaceted, seamless, cutting-edge

Forbidden Phrases

禁用句式

  • "The best part? ..." / "The secret? ..."
  • "What if I told you..." / "Here's the thing..."
  • "In today's fast-paced..." / "In the ever-evolving..."
  • "In conclusion" / "In summary"
  • "Let that sink in" / "Now more than ever"
  • 「最棒的是？...」/「秘诀是？...」
  • 「如果我告诉你...」/「重点是...」
  • 「在快节奏的当今...」/「在不断演变的...」
  • 「总结来说」/「综上所述」
  • 「好好想想」/「当下尤为重要」

Dramatic Contrast Reveals (Priority #2)

戏剧性反转表述（优先级第2）

  • "Not on lessons. On fear."
  • "Not the curriculum. The structure."
  • "He didn't teach. He observed."
  • Any "Not X. Y." fragment pattern
  • 「不是课程，是恐惧」
  • 「不是大纲，是结构」
  • 「他不教学，只观察」
  • 任何「不是X，是Y」的短句模式

Forbidden Patterns

禁用格式

  • Staccato: "No fluff. No filler. Just results."
  • Triple adjectives: "Bold, beautiful, brilliant"
  • Negation structure: "No X. No Y. Just Z."
  • 断句排比：「无冗余，无填充，只讲干货」
  • 三重形容词：「大胆、美丽、出色」
  • 否定结构：「没有X，没有Y，只有Z」

Formatting Rules

格式规则

  • Use hyphens with spaces - like this - not em dashes
  • No emojis in body content
  • No bold for emphasis in articles
  • 使用带空格的连字符 - 像这样 - 而非长破折号
  • 正文内容中不得使用表情符号
  • 文章中不得使用粗体强调",