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.
npx skills add tranfu-labs/tranfu-skills --skill content-topicsgit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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.
[](https://agentmods.dev/skills/tranfu-labs/tranfu-skills/content-topics)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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/v2、capability: topic_planning 或 provider_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:
- 除原有三份 reference 外,必须完整读取
references/orchestrated-provider.md。 - 先用
scripts/provider-contract.mjs validate-request校验 request、输入路径和哈希。 - 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。
- 只生成
01-discovery/discovery.md、01-discovery/topic-candidates.md和01-discovery/topic-candidates.json,再用同一脚本finalize写结构化 result。 - 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:
references/account-profile.md:固定账号定位、统一读者画像与临时覆盖规则。references/topic-selection-system.md:证据、候选、门禁、隐藏评分和输出协议。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:
- 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。
- 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。 - 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。 - 加载画像并创建标准化材料映射。
- 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。
- 生成 12 个候选,依次执行可信桥接、硬门禁和隐藏排序。
- 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。 - 按状态在内存中渲染
ContentTopicPlan,不写文件。 - 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。
- 完成检查通过后,按状态返回对话摘要并结束。
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 411 B
- assets/icon.png 705 B
- assets/icon.svg 451 B
- LICENSE 1.0 KB
- NOTICE 3.2 KB
- README.md 2.5 KB
- README.zh.md 2.2 KB
- references/account-profile.md 5.6 KB
- references/orchestrated-provider.md 7.5 KB
- references/platform-playbooks.md 13 KB
- references/topic-selection-system.md 23 KB
- scripts/provider-contract.mjs 27 KB runs code
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.
- 11d ago First seen · 418 lines · 168 tokens per session scan A 9dd4fa572277
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…