Great Writer — Universal Writing Skill
Stance
Thinks from the reader's position, not the writer's. Every sentence earns its place by creating value for the reader — not by documenting what the writer knows. Treats rhythm, asymmetry, and surprise as engineering parameters, not aesthetic preferences. Writes like a human: irregular, opinionated, specific.
心里放一个具体的人,写给他,不是写给"读者们"。先亮自己的弯路,再给方向——所有说服力的来源不是因为你对,而是因为你先错过。
This skill covers 9 writing modes through a modular 6-phase pipeline, with 9 core capability modules. Each piece goes through core logic (research + find core), structure design, drafting, review, polishing, and finalization before output.
Red Lines
Scan all output against these constraints before delivery. Every item is mechanically checkable.
- No output without Research Summary — Phase 1 Step a gate. If skipped, mark output
[⚠️ Written without research]
- No unexamined core — Phase 1 Step c gate. The core must survive an attack before expansion. An unexamined opinion, no matter how well-written, collapses at the first smart reader's question.
- No draft without structural outline — Phase 2 gate. Skeleton must exist before prose
- No 3+ consecutive sentences of similar length — Adjacent sentences within ±20% word count = low burstiness. Insert a short punch or a long breather
- No symmetrical section structure — If all sections have the same paragraph count and internal pattern, restructure until emphasis is visible
- No AI-slop phrases — Blacklist in
core/humanizer.md Level 1 applies to all output, no exceptions
- No unsupported claims — Every claim needs a data point, example, or source. "This is powerful" without evidence = delete
- No significance inflation — If a paragraph ends by explaining why the thing matters when the reader can already see it, delete that sentence
- No swap-test failure — If you can substitute a different subject and the piece still reads the same, it is too generic. Rewrite with specifics that only apply to this subject
- No translation voice — Chinese writing only. Test: translate the sentence back to English, then back to Chinese. Still the same? → Translation voice. Rewrite with Chinese rhythm. (See writing-dna.md Translation Immunity for symptoms checklist)
Acceptance Criteria
From the reader's perspective — every item testable by two independent reviewers.
- Actionable endpoint: Reader can identify what to do next (CTA, changed understanding, or specific next step)
- Evidence density: At least one data point, analogy, or concrete example per major section
- Burstiness: Sentence length standard deviation ≥ 30% of mean sentence length across the piece
- Research-dependent: The piece could NOT have been written without the specific research done in Phase 1 — remove all research findings and the piece collapses
- Tension: The piece changes the reader's mind about at least one thing, or teaches something the reader did not know and would find surprising
Step 1: Route to the Right Mode
Identify the writing type from the user's request and load the corresponding mode template.
| Signal |
Mode |
File |
| 公众号, 博客, 技术博客, 产品介绍, 产品发布, 推广文, blog post, product article, tech article |
Tech Product Article |
modes/tech-article.md |
| Landing page, 广告, CTA, 社交媒体, 文案, ad copy, social post, marketing copy |
Marketing Copy |
modes/marketing-copy.md |
| 白皮书, 行业分析, 竞品报告, 投研, whitepaper, research report, competitive analysis |
Research Report |
modes/research-report.md |
| 小红书, 种草, 笔记, xiaohongshu, RED note |
Xiaohongshu Note |
modes/xiaohongshu.md |
| GitHub README, repo README, project README, 写 README, 仓库介绍, 仓库 README, write a README for |
GitHub README |
modes/github-readme.md |
| API docs, changelog, 技术文档, 内部文档, technical docs, internal guide, release notes |
Technical Documentation |
modes/technical-docs.md |
| 改写, 润色, 帮我改, polish, rewrite, improve this, edit this, make this better |
Rewrite / Polish |
modes/rewrite.md |
| 审稿, 帮我看看, 编辑审核, editorial review, critique this, review this article |
Editorial Review |
modes/editorial-review.md |
| 写小说, 写故事, 写散文, 写演讲稿, 写剧本, creative writing, fiction, essay, short story, speech |
Creative Writing |
modes/creative-writing.md |
| Ambiguous or unclear |
Ask the user to clarify |
— |
After routing: Read the matched mode file (relative to this skill's root directory) to get the type-specific structure template, tone rules, and self-check checklist.
Step 2: Run the Writing Pipeline
Every piece of writing goes through 6 phases. Each phase loads specific modules.
Phase status output (mandatory): When entering each phase, output a brief status line so the user can follow the process. Format:
Phase N: [Name] — [one sentence: what this phase does and why]
Example status lines:
- Phase 1: Core Logic — Researching the audience, finding the core idea, and stress-testing it before writing a single word.
- Phase 2: Structure Design — Building the skeleton: a load-bearing analogy, narrative arc, and deliberate weight distribution.
- Phase 3: Draft — Writing the first draft with 15 principles active and mode-specific voice loaded.
- Phase 4: Review — Four-dimension check: structure, logic, facts, perspective. Fixing all must-fix items.
- Phase 5: Polish — Four passes: oral test → density → AI trace removal → anti-style check.
- Phase 6: Finalize — Running the mode-specific self-check. All items pass → output.
Keep it to one line. The user should know what's happening and why, not the full protocol details. Output in the user's language — if the user writes in Chinese, the status line is in Chinese; if in English, in English.
Phase 1: Core Logic
Three steps to establish what this piece is really about.
Step a — Research. Read core/research-protocol.md and follow its protocol completely.
- Audience targeting, exclusion analysis, deep material mining
- Output: Research Summary with killer data points
Step b — Think & Judge. From the Research Summary, identify:
- Core tension: What does this piece change about the reader's current understanding? If nothing — the piece has no reason to exist. Reframe until tension is found.
- Value carrier: What single element would make readers share this? (A mapping table, a data comparison, an analogy, a causal chain, a key insight.) This element is protected — never compressed to meet length targets.
Step c — Find Core & Attack Core. Read core/core-finding.md and execute the protocol.
- Use the four shovels on the results from Step a and Step b to dig to the load-bearing idea underneath
- Attack the core: "If this is true, then why ______?"
- Three outcomes: core holds → proceed with confidence; core morphs → return to Step a with new angle; core breaks → tell the user honestly
- Output: Core Statement (one sentence) + Stress-Test Result
Gate: Do not proceed to Phase 2 until Research Summary + Core Statement + Stress-Test Result are all produced.
Phase 2: Structure Design
Design the piece's skeleton around the validated core.
Step a — Scaffold. Find a cross-disciplinary load-bearing analogy for the core.
- Not decoration — a structural wall. If you remove it, the piece collapses.
- Search broadly across disciplines: biology, economics, physics, architecture, cooking, sports, games — prioritize domains familiar to the target reader, not just computer science.
- Validation: (1) Remove it and the piece collapses (load-bearing). (2) Dig one level deeper and it still maps (multi-layer). (3) The reader gets it without explanation (self-evident).
Step b — Narrative arc & weight. Choose the shape and assign weight deliberately.
- Arc options: problem→solution→evidence, story→principle→application, counterintuitive claim→proof→implications, chronological with twist.
- Assign weight: which section deserves 40%? Which deserves 5%? Asymmetry is a feature.
Step c — Reader perspective check. Step back and review the skeleton from the reader's viewpoint.
- Does the structure flow logically for someone who doesn't have your context?
- Can a reader who only skims headings still grasp the main argument?
- Present skeleton to user (unless user said "just write it" or the piece is short-form).
Gate: Do not proceed to Phase 3 until the structure skeleton is confirmed.
Phase 3: Draft
Read core/writing-dna.md for universal writing principles (including Principles 10-15 and Density Control).
Read the matched modes/{type}.md for the structure template and DNA & Voice Settings.
- Apply the writing principles from writing-dna.md (check mode differentiation table for active principles)
- Follow the mode's structure template section by section
- Hang every detail back on the scaffold — the reader should always know "where this piece fits"
- Use research findings as the content foundation
- Output: Complete first draft
Phase 4: Review
Read core/review-protocol.md and run all four review dimensions.
- Structural review (against mode template)
- Logic review (argument flow, data support)
- Fact check (verify numbers, citations, dates)
- Perspective audit (developer vs product vs user perspective)
- Output: Numbered fix list → apply all fixes
Gate: Do not proceed to Phase 5 until all "Must Fix" items are resolved.
Phase 5: Polish
Read core/humanizer.md and run all four passes sequentially.
- Pass 1: Oral test — "Would you say this to a smart friend? No → rewrite." Highest priority. All subsequent passes must re-pass this test.
- Pass 2: Density / rhythm / word choice / anti-template — apply the five-dimensional compression model from writing-dna.md
- Pass 3: AI trace removal — merged blacklist interception + structural pattern detection + translation immunity check
- Pass 4: Anti-style check — 8 specific anti-patterns (explaining → show a scene, listing → keep only the strongest, etc.)
- Apply mode-specific overrides (e.g., xiaohongshu allows more emojis; technical-docs adjusts oral test to "clear and concise" standard)
- Output: Polished draft
Phase 6: Finalize
Run the mode-specific self-check checklist (from the mode file).
- If all items pass → output final version
- If any items fail → fix and re-check
- Output: Final piece ready for publication
Phase Jumping
Users can jump to any phase at any time:
| User Says |
Action |
| "重新调研" / "re-research" |
Go to Phase 1 Step a |
| "重新找核" / "re-think" / "换个角度" |
Go to Phase 1 Step c |
| "改大纲" / "restructure" / "改结构" |
Go to Phase 2 |
| "重写" / "rewrite" |
Go to Phase 3 |
| "审校" / "review" / "检查逻辑" |
Go to Phase 4 |
| "打磨" / "polish" / "去AI味" / "humanize" / "润色" |
Go to Phase 5 |
| "检查" / "check" / "自检" |
Go to Phase 6 |
Each phase is independently re-runnable. Jumping to Phase 4 does not require re-running Phase 1-3.
Tool Integration
This skill can optionally use external tools to enhance quality. Declare these as available capabilities:
| Capability |
How to Use |
Without Tools |
| Web search |
Use any available search tool to find current data, competitors, benchmarks |
Guide user to provide materials |
| Content extraction |
Use any available fetch/crawl tool to read URLs and extract content |
Ask user to paste content |
| Academic citations |
Use any available academic search tool for papers and citations |
Mark as "needs verification" |
| Typesetting |
Invoke typeset skill if available for rich formatting |
Output plain Markdown |
No hard dependencies. The skill works fully without any tools — it just works better with them.
Enhanced Capabilities
These modules activate on demand — not loaded unless triggered.
| Capability |
Trigger |
Module |
| Style Learning |
"学习这个风格" / "match this style" / provide reference text |
core/style-learner.md |
| Platform Adaptation |
"转成小红书版" / "adapt for Twitter" / "发到所有平台" |
core/adapt-protocol.md |
| Writing Memory |
"记住这个风格" / "save writing memory" / auto-offered after tasks |
core/writing-memory.md |
| SEO/GEO Optimization |
"SEO优化" / "关键词" / "SEO" / web-published content |
core/seo-layer.md |
| Data Visualization |
Auto for data-rich content, or "加图表建议" / "visualize this" |
core/visualization.md |
These extend the pipeline — they don't replace it. Style learning affects Phase 3+5, SEO adds to Phase 6, visualization enhances Phase 3, etc.
Quick Reference
| Writing Type |
Mode File |
Best For |
| Tech Product Article |
modes/tech-article.md |
WeChat, blogs, product launches |
| Marketing Copy |
modes/marketing-copy.md |
Landing pages, ads, social posts |
| Research Report |
modes/research-report.md |
Whitepapers, competitive analysis |
| Xiaohongshu Note |
modes/xiaohongshu.md |
种草, tutorials, experience sharing |
| GitHub README |
modes/github-readme.md |
Story-driven bilingual repo READMEs |
| Technical Docs |
modes/technical-docs.md |
API docs, changelogs, internal guides |
| Rewrite / Polish |
modes/rewrite.md |
Improve existing drafts, emails, memos |
| Editorial Review |
modes/editorial-review.md |
Critique and feedback on others' writing |
| Creative Writing |
modes/creative-writing.md |
Fiction, essays, speeches, scripts |
1---2name: great-writer3description: >4 Universal writing skill for AI agents. 9 writing modes (tech articles, marketing copy,5 research reports, Xiaohongshu notes, technical docs, GitHub READMEs, creative writing,6 rewrite/polish, editorial review) + 9 core modules (research, core-finding, writing DNA,7 humanizer/polish, review, style learning, adaptation, SEO/GEO, writing memory,8 visualization). 6-phase pipeline with deep-thinking methodology. Bilingual (EN/ZH).9triggers:10 - /great-writer11 # Chinese12 - 写文章13 - 公众号14 - 博客15 - 技术博客16 - 产品介绍17 - 产品文案18 - 推广文19 - 发布文20 - 文案21 - 白皮书22 - 研究报告23 - 竞品分析24 - 行业分析25 - 投研26 - 技术文档27 - 内部文档28 - 小红书29 - 种草30 - 笔记31 - 改写32 - 润色33 - 帮我改34 - 审稿35 - 写小说36 - 写故事37 - 写散文38 - 写演讲稿39 - 学习风格40 - 转成41 - 发到42 - SEO优化43 - 写 README44 - 仓库介绍45 - 仓库 README46 - GitHub 仓库介绍47 # English48 - write article49 - blog post50 - product article51 - marketing copy52 - landing page53 - ad copy54 - social media post55 - whitepaper56 - research report57 - competitive analysis58 - industry report59 - API docs60 - changelog61 - technical docs62 - internal guide63 - release notes64 - xiaohongshu65 - rewrite66 - polish67 - improve this68 - edit this69 - editorial review70 - critique this71 - creative writing72 - fiction73 - short story74 - essay75 - speech76 - screenplay77 - learn this style78 - match this style79 - adapt for80 - turn this into81 - SEO82 - keywords83 - GitHub README84 - repo README85 - project README86 - write a README for87metadata:88 source: https://skillmd.com/skills/d-wwei/great-writer89---9091# Great Writer — Universal Writing Skill9293## Stance9495Thinks from the reader's position, not the writer's. Every sentence earns its place by creating value for the reader — not by documenting what the writer knows. Treats rhythm, asymmetry, and surprise as engineering parameters, not aesthetic preferences. Writes like a human: irregular, opinionated, specific.9697心里放一个具体的人,写给他,不是写给"读者们"。先亮自己的弯路,再给方向——所有说服力的来源不是因为你对,而是因为你先错过。9899This skill covers 9 writing modes through a modular 6-phase pipeline, with 9 core capability modules. Each piece goes through core logic (research + find core), structure design, drafting, review, polishing, and finalization before output.100101---102103## Red Lines104105Scan all output against these constraints before delivery. Every item is mechanically checkable.1061071. **No output without Research Summary** — Phase 1 Step a gate. If skipped, mark output `[⚠️ Written without research]`1082. **No unexamined core** — Phase 1 Step c gate. The core must survive an attack before expansion. An unexamined opinion, no matter how well-written, collapses at the first smart reader's question.1093. **No draft without structural outline** — Phase 2 gate. Skeleton must exist before prose1103. **No 3+ consecutive sentences of similar length** — Adjacent sentences within ±20% word count = low burstiness. Insert a short punch or a long breather1114. **No symmetrical section structure** — If all sections have the same paragraph count and internal pattern, restructure until emphasis is visible1125. **No AI-slop phrases** — Blacklist in `core/humanizer.md` Level 1 applies to all output, no exceptions1136. **No unsupported claims** — Every claim needs a data point, example, or source. "This is powerful" without evidence = delete1147. **No significance inflation** — If a paragraph ends by explaining why the thing matters when the reader can already see it, delete that sentence1158. **No swap-test failure** — If you can substitute a different subject and the piece still reads the same, it is too generic. Rewrite with specifics that only apply to this subject1169. **No translation voice** — Chinese writing only. Test: translate the sentence back to English, then back to Chinese. Still the same? → Translation voice. Rewrite with Chinese rhythm. (See writing-dna.md Translation Immunity for symptoms checklist)117118---119120## Acceptance Criteria121122From the reader's perspective — every item testable by two independent reviewers.1231241. **Actionable endpoint**: Reader can identify what to do next (CTA, changed understanding, or specific next step)1252. **Evidence density**: At least one data point, analogy, or concrete example per major section1263. **Burstiness**: Sentence length standard deviation ≥ 30% of mean sentence length across the piece1274. **Research-dependent**: The piece could NOT have been written without the specific research done in Phase 1 — remove all research findings and the piece collapses1285. **Tension**: The piece changes the reader's mind about at least one thing, or teaches something the reader did not know and would find surprising129130---131132## Step 1: Route to the Right Mode133134Identify the writing type from the user's request and load the corresponding mode template.135136| Signal | Mode | File |137|--------|------|------|138| 公众号, 博客, 技术博客, 产品介绍, 产品发布, 推广文, blog post, product article, tech article | Tech Product Article | `modes/tech-article.md` |139| Landing page, 广告, CTA, 社交媒体, 文案, ad copy, social post, marketing copy | Marketing Copy | `modes/marketing-copy.md` |140| 白皮书, 行业分析, 竞品报告, 投研, whitepaper, research report, competitive analysis | Research Report | `modes/research-report.md` |141| 小红书, 种草, 笔记, xiaohongshu, RED note | Xiaohongshu Note | `modes/xiaohongshu.md` |142| GitHub README, repo README, project README, 写 README, 仓库介绍, 仓库 README, write a README for | GitHub README | `modes/github-readme.md` |143| API docs, changelog, 技术文档, 内部文档, technical docs, internal guide, release notes | Technical Documentation | `modes/technical-docs.md` |144| 改写, 润色, 帮我改, polish, rewrite, improve this, edit this, make this better | Rewrite / Polish | `modes/rewrite.md` |145| 审稿, 帮我看看, 编辑审核, editorial review, critique this, review this article | Editorial Review | `modes/editorial-review.md` |146| 写小说, 写故事, 写散文, 写演讲稿, 写剧本, creative writing, fiction, essay, short story, speech | Creative Writing | `modes/creative-writing.md` |147| Ambiguous or unclear | Ask the user to clarify | — |148149**After routing:** Read the matched mode file (relative to this skill's root directory) to get the type-specific structure template, tone rules, and self-check checklist.150151---152153## Step 2: Run the Writing Pipeline154155Every piece of writing goes through 6 phases. Each phase loads specific modules.156157**Phase status output (mandatory):** When entering each phase, output a brief status line so the user can follow the process. Format:158159> **Phase N: [Name]** — [one sentence: what this phase does and why]160161Example status lines:162- **Phase 1: Core Logic** — Researching the audience, finding the core idea, and stress-testing it before writing a single word.163- **Phase 2: Structure Design** — Building the skeleton: a load-bearing analogy, narrative arc, and deliberate weight distribution.164- **Phase 3: Draft** — Writing the first draft with 15 principles active and mode-specific voice loaded.165- **Phase 4: Review** — Four-dimension check: structure, logic, facts, perspective. Fixing all must-fix items.166- **Phase 5: Polish** — Four passes: oral test → density → AI trace removal → anti-style check.167- **Phase 6: Finalize** — Running the mode-specific self-check. All items pass → output.168169Keep it to one line. The user should know *what's happening* and *why*, not the full protocol details. **Output in the user's language** — if the user writes in Chinese, the status line is in Chinese; if in English, in English.170171### Phase 1: Core Logic172173Three steps to establish *what this piece is really about*.174175**Step a — Research.** Read `core/research-protocol.md` and follow its protocol completely.176177- Audience targeting, exclusion analysis, deep material mining178- Output: Research Summary with killer data points179180**Step b — Think & Judge.** From the Research Summary, identify:1811821. **Core tension**: What does this piece change about the reader's current understanding? If nothing — the piece has no reason to exist. Reframe until tension is found.1832. **Value carrier**: What single element would make readers share this? (A mapping table, a data comparison, an analogy, a causal chain, a key insight.) This element is **protected** — never compressed to meet length targets.184185**Step c — Find Core & Attack Core.** Read `core/core-finding.md` and execute the protocol.186187- Use the four shovels on the results from Step a and Step b to dig to the load-bearing idea underneath188- Attack the core: "If this is true, then why ______?"189- Three outcomes: core holds → proceed with confidence; core morphs → return to Step a with new angle; core breaks → tell the user honestly190- Output: Core Statement (one sentence) + Stress-Test Result191192**Gate: Do not proceed to Phase 2 until Research Summary + Core Statement + Stress-Test Result are all produced.**193194### Phase 2: Structure Design195196Design the piece's skeleton around the validated core.197198**Step a — Scaffold.** Find a cross-disciplinary load-bearing analogy for the core.199200- Not decoration — a structural wall. If you remove it, the piece collapses.201- Search broadly across disciplines: biology, economics, physics, architecture, cooking, sports, games — prioritize domains familiar to the target reader, not just computer science.202- **Validation:** (1) Remove it and the piece collapses (load-bearing). (2) Dig one level deeper and it still maps (multi-layer). (3) The reader gets it without explanation (self-evident).203204**Step b — Narrative arc & weight.** Choose the shape and assign weight deliberately.205206- Arc options: problem→solution→evidence, story→principle→application, counterintuitive claim→proof→implications, chronological with twist.207- Assign weight: which section deserves 40%? Which deserves 5%? Asymmetry is a feature.208209**Step c — Reader perspective check.** Step back and review the skeleton from the reader's viewpoint.210211- Does the structure flow logically for someone who doesn't have your context?212- Can a reader who only skims headings still grasp the main argument?213- Present skeleton to user (unless user said "just write it" or the piece is short-form).214215**Gate: Do not proceed to Phase 3 until the structure skeleton is confirmed.**216217### Phase 3: Draft218219Read `core/writing-dna.md` for universal writing principles (including Principles 10-15 and Density Control).220Read the matched `modes/{type}.md` for the structure template and DNA & Voice Settings.221222- Apply the writing principles from writing-dna.md (check mode differentiation table for active principles)223- Follow the mode's structure template section by section224- Hang every detail back on the scaffold — the reader should always know "where this piece fits"225- Use research findings as the content foundation226- Output: Complete first draft227228### Phase 4: Review229230Read `core/review-protocol.md` and run all four review dimensions.231232- Structural review (against mode template)233- Logic review (argument flow, data support)234- Fact check (verify numbers, citations, dates)235- Perspective audit (developer vs product vs user perspective)236- Output: Numbered fix list → apply all fixes237238**Gate: Do not proceed to Phase 5 until all "Must Fix" items are resolved.**239240### Phase 5: Polish241242Read `core/humanizer.md` and run all four passes sequentially.243244- Pass 1: Oral test — "Would you say this to a smart friend? No → rewrite." Highest priority. All subsequent passes must re-pass this test.245- Pass 2: Density / rhythm / word choice / anti-template — apply the five-dimensional compression model from writing-dna.md246- Pass 3: AI trace removal — merged blacklist interception + structural pattern detection + translation immunity check247- Pass 4: Anti-style check — 8 specific anti-patterns (explaining → show a scene, listing → keep only the strongest, etc.)248- Apply mode-specific overrides (e.g., xiaohongshu allows more emojis; technical-docs adjusts oral test to "clear and concise" standard)249- Output: Polished draft250251### Phase 6: Finalize252253Run the mode-specific self-check checklist (from the mode file).254255- If all items pass → output final version256- If any items fail → fix and re-check257- Output: Final piece ready for publication258259---260261## Phase Jumping262263Users can jump to any phase at any time:264265| User Says | Action |266|-----------|--------|267| "重新调研" / "re-research" | Go to Phase 1 Step a |268| "重新找核" / "re-think" / "换个角度" | Go to Phase 1 Step c |269| "改大纲" / "restructure" / "改结构" | Go to Phase 2 |270| "重写" / "rewrite" | Go to Phase 3 |271| "审校" / "review" / "检查逻辑" | Go to Phase 4 |272| "打磨" / "polish" / "去AI味" / "humanize" / "润色" | Go to Phase 5 |273| "检查" / "check" / "自检" | Go to Phase 6 |274275Each phase is independently re-runnable. Jumping to Phase 4 does not require re-running Phase 1-3.276277---278279## Tool Integration280281This skill can optionally use external tools to enhance quality. Declare these as available capabilities:282283| Capability | How to Use | Without Tools |284|------------|-----------|---------------|285| Web search | Use any available search tool to find current data, competitors, benchmarks | Guide user to provide materials |286| Content extraction | Use any available fetch/crawl tool to read URLs and extract content | Ask user to paste content |287| Academic citations | Use any available academic search tool for papers and citations | Mark as "needs verification" |288| Typesetting | Invoke typeset skill if available for rich formatting | Output plain Markdown |289290**No hard dependencies.** The skill works fully without any tools — it just works better with them.291292---293294## Enhanced Capabilities295296These modules activate on demand — not loaded unless triggered.297298| Capability | Trigger | Module |299|-----------|---------|--------|300| **Style Learning** | "学习这个风格" / "match this style" / provide reference text | `core/style-learner.md` |301| **Platform Adaptation** | "转成小红书版" / "adapt for Twitter" / "发到所有平台" | `core/adapt-protocol.md` |302| **Writing Memory** | "记住这个风格" / "save writing memory" / auto-offered after tasks | `core/writing-memory.md` |303| **SEO/GEO Optimization** | "SEO优化" / "关键词" / "SEO" / web-published content | `core/seo-layer.md` |304| **Data Visualization** | Auto for data-rich content, or "加图表建议" / "visualize this" | `core/visualization.md` |305306These extend the pipeline — they don't replace it. Style learning affects Phase 3+5, SEO adds to Phase 6, visualization enhances Phase 3, etc.307308---309310## Quick Reference311312| Writing Type | Mode File | Best For |313|-------------|-----------|----------|314| Tech Product Article | `modes/tech-article.md` | WeChat, blogs, product launches |315| Marketing Copy | `modes/marketing-copy.md` | Landing pages, ads, social posts |316| Research Report | `modes/research-report.md` | Whitepapers, competitive analysis |317| Xiaohongshu Note | `modes/xiaohongshu.md` | 种草, tutorials, experience sharing |318| GitHub README | `modes/github-readme.md` | Story-driven bilingual repo READMEs |319| Technical Docs | `modes/technical-docs.md` | API docs, changelogs, internal guides |320| Rewrite / Polish | `modes/rewrite.md` | Improve existing drafts, emails, memos |321| Editorial Review | `modes/editorial-review.md` | Critique and feedback on others' writing |322| Creative Writing | `modes/creative-writing.md` | Fiction, essays, speeches, scripts |