tcms-writer
For tech-product marketing teams — turns a product knowledge base into brand-side long-form drafts (blogs, case studies, product write-ups), not third-party analysis. Produces only 1500-3000 word long-form drafts from a content brief; does not handle social posts, short content, or channel adaptation. Not for neutral industry research — use industry-deep-dive-pipeline for that. Skill: tcms-writer Owner: haiyangchenbj Summary: For tech-product marketing teams — turns a product knowledge base into brand-side long-form drafts (blogs, case studies, product write-ups), not third-party analysis. Produces only 1500-3000 word long-form drafts from a content brief; does not handle social posts, short content, or channel adaptation. Not for neutral industry research — use industry-deep-dive-pipeline
Rank
62
Safety
84
Downloads
983
Updated
Oct 11, 2026
Version
1.3.0
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 983 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
- 983 downloadsadoption · observed Oct 11, 2026
- Latest release
- 1.3.0release · observed Sep 20, 2026
- Handshake status
- UNKNOWNsecurity
What changed
Newest first. Only changes that point at a source are listed.
Release 1.3.0release
Full-package republish: now includes references (brand rules, sensitive terms, 3 content templates) and bilingual READMEs that were missing from earlier uploads. Skill body is the 1.3.0 English edition.
Observed Sep 20, 2026 · source
Install and run
Setup complexity: low.
clawhub skill install s17672gh0nx9qr7sjp84kz7xen83jv7v:tcms-writer- 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.
- 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-tcms-writer/snapshot"
Run-check
$0.02 USD1 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
119,398 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
--- name: tcms-writer version: "1.3.0" description: | For tech-product marketing teams — turns a product knowledge base into brand-side long-form drafts (blogs, case studies, product write-ups), not third-party analysis. Produces only 1500-3000 word long-form drafts from a content brief; does not handle social posts, short content, or channel adaptation. Not for neutral industry research — use industry-deep-dive-pipeline for that. read_when: - 写文章 - 写稿 - 写初稿 - 起草 - 技术博客 - 品牌技术稿 - 案例文章 - 客户案例 - 产品解读 - 产品稿 - 新闻稿 - content brief - draft - 按brief写 allowed-tools: - read_file - write_to_file - replace_in_file - web_fetch - search_content - search_file - list_dir disable: false --- # TCMS Writer 基于产品知识库、品牌规范和选题Brief,产出高质量的长文初稿。 ## 工作模式:提示链(Prompt Chaining) 按固定步骤执行,每一步输入输出明确。 --- ## Step 1: 确认选题 [确定性] 读取用户提供的选题信息,确认以下要素: | 要素 | 必须明确 | 缺失时处理 | |------|---------|-----------| | 文章类型 | 技术博客 / 客户案例 / 产品解读 | 询问用户 | | 目标产品 | 具体产品名 | 询问用户 | | 目标读者 | 架构师/CTO/工程师/分析师 | 默认"技术决策者" | | 核心信息 | 要传达的关键价值点 | 从知识库提取 | | 素材来源 | 知识库/内部材料/已发文章 | 默认使用知识库 | | 保密要求 | 是否有内部案例需脱敏 | 默认全部脱敏 | 如果用户提供了Brief文件路径,直接读取Brief。 --- ## Step 2: 读取素材 [确定性] **只读与目标产品相关的文件,不加载无关产品信息:** 1. **产品知识库** → 搜索目标产品对应章节(不读全文,用search_content定位) 2. **品牌规范** → `references/brand-rules.md`(每次都读) 3. **文章模板** → 按文章类型读取对应模板: - 技术博客:`references/templates/tech-blog.md` - 客户案例:`references/templates/case-study.md` - 产品解读:`references/templates/product-update.md` 4. **补充素材**(按需):Brief中指定的内部文档或已发布文章 > 以上路径需根据实际项目目录配置。 --- ## Step 3: 写作 [LLM] ### 写作规则 **产品名称**: - 首次提及使用官网全称(参见brand-rules.md产品名称对照表) - 后续可用简称 **品牌露出**: - 标题中包含品牌名或具体产品官方名称 - 开头两段内引入品牌或具体产品 - 结尾有固定品牌格式 **数据引用**: - 所有数据必须来自知识库或已发布文章,不可编造 - 引用时记录来源(用于Step 5生成引用表) **客户信息**: - 内部来源的客户案例**默认脱敏** - 脱敏格式:"某+行业+企业规模" - 不出现客户公司名、内部人员姓名、项目代号 - 用户明确告知已授权的可使用客户名称 **竞品处理**: - 不直接点名任何竞品 - 使用"某友商平台"等替代表述 **产品能力来源验证**: - 只引用知识库中存在的产品能力 - 不确定是否已公开的,在预审清单中标注"需确认" ### 英文稿 AI 强特征与作者性门禁 [英文稿必过] 本节是 TCMS 对统一英文规则源 `tech-writing-pipeline/references/english-ai-writing-strategy.md` 的应用说明。可访问该规则源时必须加载;本 Skill 不另建禁词表,也不以 AI detector 分数作为发布结论。本节规则不替代产品、品牌、客户、竞品、命名和知识库约束。 1. **先建英文 claim map。** 英文稿动笔前,用英文记录 `Claim / Evidence / Counterargument / Boundary / What the reader should not infer` 五项。英文稿按英文读者的论证顺序重写,不按中文句序逐句翻译。 2. **P0 直接停止。** 出现虚构事实、数字、引语、关系或归因;空泛开场或结尾承载主要信息;只有积极形容词没有对象、证据和条件;`studies show` / `experts believe` 没有可核查来源;反方只被提及却未评价;把中文平行结构或媒体表达直接搬进英文稿,均退回Brief或素材重建。 3. **P1 进入人工复核。** 单段内修辞包装词成组出现,反复使用 `not just X but Y` 等对举模板,破折号或同构三项并列变成节奏骨架,或积极表述超过对象、来源、测量和限定条件时,进入人工复核。单个风格词不构成问题。 4. **作者性检查。** 每个主要段落都要能指出具体对象、事件、数字或观察行为;作者愿意承担的判断;最强合理反驳;对反驳的处理;以及会使判断变窄或失效的条件。 5. **按渠道解释结构。** LinkedIn 的对象清单、责任清单、承担事实功能的三项并列或结构母题不能单独判为 AI 腔。只有它们与空泛开场、来源不裁决、作者判断缺席或修辞包装叠加时,才升级处理。detector 分数只能作为观察项,不能进入 PASS/FAIL。 ### 文章结构 不写成:功能1 → 功能2 → 功能3 的产品说明书 要写成:**问题 → 为什么难 → 方案(自然引入产品能力)→ 效果 → 适用判断**
README.md
# TCMS Writer **Part of the `tcms-*` family** — brand-side content skills for tech-product marketing teams. *Not for neutral third-party industry research — that is `industry-deep-dive-pipeline`'s job.* ## What it does Turns a product knowledge base and brand rules into **brand-side long-form drafts** (technical blogs, customer case studies, product write-ups). Produces only 1500–3000 word drafts from a content brief. It does **not** handle social posts, short content, or channel adaptation (see `tcms-adapter`). ## When to use - You have a topic brief and need a long-form brand marketing draft. - The piece is promotional / product-positioning in nature. ## When NOT to use - Neutral, third-party industry deep-dives → use `industry-deep-dive-pipeline`. - Single-article pre-publish compliance check → use `tcms-compliance-reviewer`. - Channel adaptation → use `tcms-adapter`. ## Trigger phrases 写文章, 写稿, 写初稿, 起草, 技术博客, 品牌技术稿, 案例文章, 客户案例, 产品解读, 产品稿, 新闻稿, content brief, draft, 按brief写 ## Pipeline position `tcms-planner` (brief) → **`tcms-writer`** (draft) → `tcms-compliance-reviewer` (review) → `tcms-adapter` (channels) → `tcms-performance-analyst` (monthly report)
_meta.json
{
"ownerId": "kn70yg6zwmkftx4939qrs89awx82rr9a",
"slug": "tcms-writer",
"version": "1.3.0",
"publishedAt": 1789876495288
}references/brand-rules.md
# 品牌与内容规范
> 按实际品牌和产品线配置以下内容。
## 产品正式名称
首次提及用全称,后续可用简称。
| 简称 | 官网全称 | 首次引用格式 |
|------|---------|------------|
| 产品A | xxx平台 | XX云xxx平台(产品A) |
| 产品B | xxx服务 | XX云xxx服务(产品B) |
| ... | ... | ... |
> 从官网产品页获取正式名称,保持一致。
## 品牌露出规则
- 标题中包含品牌名或具体产品官方名称
- 开头两段内引入品牌或具体产品
- 结尾固定格式:**{品牌名},帮助/助力 xxx企业xxx。**
- 正文中产品首次出现用全称,后续用简称
## 写作调性
- 专业、克制、有判断。不油腻,不夸张,不AI营销腔
- 允许专业术语,紧跟一句通俗解释
- 给结论和判断,不只堆信息
- 像成熟的技术分析者,不像内容农场
## 禁用表达
| 类型 | 禁用 | 替代 |
|------|------|------|
| 竞品点名 | 具体竞品名称 | "某友商平台""原有闭源平台" |
| 未确认产品 | 内部规划中未正式发布的产品 | 不提及 |
| 空话 | 赋能/闭环/端到端/强大/显著/大幅/打造 | 用具体数据和场景替代 |
| 内部代号 | 任何未在官网出现的产品代号 | 不使用 |
## 客户脱敏规则
内部来源的客户案例默认脱敏:
| 场景 | 脱敏格式 |
|------|---------|
| 知名企业 | 某+行业+规模,如"某头部券商" |
| 一般企业 | 某+行业+企业类型,如"某SaaS服务商" |
| 人员信息 | 不出现姓名/工号/企业微信ID |
> 在此处维护具体客户名→脱敏名的映射表(不随代码同步)。
## 已授权可公开引用的客户
> 在此处维护已明确授权的客户名单。references/sensitive-terms.md
# 敏感词与禁用表达 ## 禁止出现的客户名称(内部来源,未确认授权) > 在此处维护具体客户名称列表。内部材料中出现的客户名必须脱敏处理。 ## 禁止出现的竞品名称 > 在此处维护竞品公司名和产品名列表。 替代表述:某友商平台 / 原有闭源平台 / 国际主流平台 / 其他同类产品 ## 禁止出现的未确认产品 > 在此处维护内部规划中、对外口径未确认的产品名。 ## 禁止出现的内部信息 - 内部项目代号 - 内部人员姓名和通讯ID - 内部材料中的管理备注(如"需和XX确认") - 内部材料roadmap中标注但官网未上线的功能(需逐条验证) ## 慎用表达(非禁止,但尽量避免) 赋能, 闭环, 端到端, 强大, 显著, 大幅, 打造, 一站式, 全面, 领先, 极致, 颠覆, 革命性 → 用具体数据和场景描述替代
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!
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
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
- Card JSON
- Facts JSON
- Snapshot JSON
- Contract JSON
- Trust JSON
- Changes JSON
- Warnings JSON
- Seen by JSON
- Disagreements JSON
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/haiyangchenbj/skills/tcms-writer",
"sourceUrl": "https://clawhub.ai/haiyangchenbj/skills/tcms-writer",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T22:37:48.448Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-haiyangchenbj-tcms-writer/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-haiyangchenbj-tcms-writer/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-11T22:37:48.448Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "983 downloads",
"href": "https://clawhub.ai/haiyangchenbj/tcms-writer",
"sourceUrl": "https://clawhub.ai/haiyangchenbj/tcms-writer",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-11T22:37:48.448Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.3.0",
"href": "https://clawhub.ai/haiyangchenbj/tcms-writer",
"sourceUrl": "https://clawhub.ai/haiyangchenbj/tcms-writer",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-09-20T03:54:55.288Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-haiyangchenbj-tcms-writer/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-haiyangchenbj-tcms-writer/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.3.0",
"description": "Full-package republish: now includes references (brand rules, sensitive terms, 3 content templates) and bilingual READMEs that were missing from earlier uploads. Skill body is the 1.3.0 English edition.",
"href": "https://clawhub.ai/haiyangchenbj/tcms-writer",
"sourceUrl": "https://clawhub.ai/haiyangchenbj/tcms-writer",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-09-20T03:54:55.288Z",
"isPublic": true
}
]
}Record generated Oct 12, 2026.
For crawlers
This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.
- One record, as JSON: card, facts, snapshot, contract, trust, changes, warnings, seen by, disagreements.
- Every agent, one feed: /.well-known/ai-catalog.json
- What this site sells, and the price: /.well-known/x402
- Paid run-check: /api/v1/agents/clawhub-haiyangchenbj-tcms-writer/run-check
