content-topics

content-topics is a skill for Codex from tranfu-labs/tranfu-skills. It costs 168 tokens per session (5,908 once invoked), scanned A, original, MIT.

A Chinese-language content-topic planning skill for a fixed content account. It turns research materials or public information into evidence-based topic options for several Chinese publishing platforms.

In plain words
What is it for?
Creating a main topic, backup topics, a shared outline, and platform-specific starting guidance for WeChat, Xiaohongshu, Zhihu, Weibo, and Toutiao. It does not write complete articles.
Why use it?
It helps choose relevant topics and adapt them to different platforms instead of starting from an unstructured pile of research. It also checks whether evidence is current and credible.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Creating a main topic, backup topics, a shared outline, and platform-specific starting guidance for WeChat, Xiaohongshu, Zhihu, Weibo, and Toutiao. It does not write complete articles.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tranfu-labs/tranfu-skills/content-topics
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add tranfu-labs/tranfu-skills --skill content-topics
Clone the repo
git clone --depth 1 https://github.com/tranfu-labs/tranfu-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for content-topics

README.md
[![agentmods](https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/content-topics/github.svg)](https://agentmods.dev/skills/tranfu-labs/tranfu-skills/content-topics)
Your own site
<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/content-topics"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/content-topics/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for content-topics

Your own site · 80×15
<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/content-topics"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/content-topics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,908 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00168 $0.05908
Opus 5 $0.00084 $0.02954
Sonnet 5 $0.00034 $0.01182
Haiku 4.5 $0.00017 $0.00591

Measured 11d ago against content hash 9dd4fa572277, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

content-topics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/provider-contract.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

own-skills/content-production/skills/content-topics/SKILL.md · 418 lines

How it starts

The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Topics

在素材调研/事实库与正式创作大纲之间完成选题决策。服务一个固定账号,默认加载内置跨平台账号画像;只在本次请求明确提供新画像时临时覆盖,不修改内置画像,不记录历史选题或表现数据。

运行模式路由

独立模式

普通用户请求默认进入独立模式,完整执行本文后续流程,交付 ContentTopicPlan,并按避碰规则写入 02-选题方案.md。新增的总控接口不得改变这一行为。

总控模式

content-production-provider: topic-planning-v1

只要结构化 request 出现 contract: content-production-provider/v2capability: topic_planningprovider_contract: topic-planning-v1 任一总控标志,就进入总控校验;只有完全没有这些标志时才使用独立模式。进入执行还必须同时满足三项标志和 interaction_policy: return_to_orchestrator。显式总控 request 无效时写 canonical BLOCKED result 并结束,绝不回退独立模式或创建 02-选题方案.md

进入总控模式后:

  1. 除原有三份 reference 外,必须完整读取 references/orchestrated-provider.md
  2. 先用 scripts/provider-contract.mjs validate-request 校验 request、输入路径和哈希。
  3. 复用原有证据、候选、门禁和隐藏排序规则,但采用总控快照的画像优先级与 canonical 输出。
  4. 只生成 01-discovery/discovery.md01-discovery/topic-candidates.md01-discovery/topic-candidates.json,再用同一脚本 finalize 写结构化 result。
  5. 把 result 返回总控并结束;不要继续执行本文的独立模式写入与对话返回步骤。

总控模式的完整输入、权限、状态映射和产物 schema 以 references/orchestrated-provider.md 为准。以下未特别注明的流程均描述独立模式。

职责边界

负责:

  • 从用户指定材料、当前内容目录的标准文件或实时公开信息中提炼内容机会。
  • 判断热点证据是否新鲜、可信并与账号相关。
  • 默认生成微信公众号、小红书、知乎、微博和今日头条的适配版本。
  • 推荐 1 个主选题和 4 个备选,为主选题提供共享母纲与平台起草提示。
  • 在当前内容目录写入命名产物 ContentTopicPlan

不负责:

  • 单独生成或优化标题、建立标题池。
  • 写完整文章、把已有正文改写成平台版本。
  • 只做资料搜集、深度调研或事实库维护。
  • 制作内容日历、发布内容、追踪历史选题或分析表现数据。

若请求同时包含选题和完整写稿,先完成选题并停止在本 Skill 的交付边界;把后续写作明确留给下游创作流程。若用户已经给出确定主题并只要标题或正文,不调用本 Skill。

必读文件

独立模式执行前先校验以下三份 reference 是否存在且可读。若任一文件不存在或不可读,必须返回 BLOCKED 诊断,列出缺失路径和恢复条件;不要生成候选,不要声称已写入产物,并结束。三份文件均可读时,必须完整读取:

  1. references/account-profile.md:固定账号定位、统一读者画像与临时覆盖规则。
  2. references/topic-selection-system.md:证据、候选、门禁、隐藏评分和输出协议。
  3. references/platform-playbooks.md:五个平台的适配判断、标题原型和内容形式。

不得只凭本文件中的摘要替代 reference。用户明确指定平台子集时仍读取完整平台手册,但只渲染指定平台。

执行总流程

CREATE A TODO LIST FOR THE TASKS BELOW:1. 解析输入;2. 核验证据;3. 生成候选;4. 筛选主备选;5. 写入产物;6. 复核。不要把待办写进最终产物。

按以下父流程执行,详细判据见后续同名步骤:

  1. 校验请求边界。若请求只属于不触发场景,说明边界并结束,不创建产物。
  2. 校验并完整读取三份必读 reference。若缺失或不可读,按上述 BLOCKED 出口结束。
  3. 解析内容来源和当前内容目录。若满足任一 BLOCKED 条件 → 设置 BLOCKED,跳至步骤 8,明确跳过步骤 4–7;否则继续。
  4. 加载画像并创建标准化材料映射。
  5. 检查双证据与 72 小时时效;证据不足时补查,无法补查时保留证据缺口。
  6. 生成 12 个候选,依次执行可信桥接、硬门禁和隐藏排序。
  7. 穷尽决定非阻塞状态:有合格主选题 → PASS;否则 → NEEDS_EVIDENCE 并披露所有证据或门禁缺口。
  8. 按状态在内存中渲染 ContentTopicPlan,不写文件。
  9. 执行写前检查。失败 → 返回对应步骤修正且不创建文件;通过 → 选择不会覆盖现有文件的名称并只写入一次,再执行写后检查。若文件系统不可写,改为在对话中返回完整产物并说明原因。
  10. 完成检查通过后,按状态返回对话摘要并结束。

Read the full file on GitHub · 418 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 418 lines · 168 tokens per session scan A 9dd4fa572277

Subscribe to this mod's changes

content-topics is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed yesterday), licensed MIT. It adds 168 tokens to every session and 5,908 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens