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 961882/ray-skills --skill ray-content-topic-planninggit clone --depth 1 https://github.com/961882/ray-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/961882/ray-skills/ray-content-topic-planning)<a href="https://agentmods.dev/skills/961882/ray-skills/ray-content-topic-planning"><img src="https://agentmods.dev/badge/skills/961882/ray-skills/ray-content-topic-planning/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/961882/ray-skills/ray-content-topic-planning"><img src="https://agentmods.dev/badge/skills/961882/ray-skills/ray-content-topic-planning.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 | $0.00121 | $0.01137 |
| Opus 5 | $0.00060 | $0.00568 |
| Sonnet 5 | $0.00024 | $0.00227 |
| Haiku 4.5 | $0.00012 | $0.00114 |
Grade A, and why
ray-content-topic-planning 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 10d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
内容选题规划
从源文案拆解出完整的内容发布计划：选题 → 标题 → 结构 → 评分 → 节奏。
目录
触发条件
| 关键词 | 动作 |
|---|---|
| 「拆选题」「选题规划」「内容拆解」「topic planning」 | 执行完整流程 |
| 「重新评分」「校准评分」「补充历史文案」 | 从 Step 05 开始执行历史校准 |
执行模式
| 选项 | 说明 |
|---|---|
| ✅ 自动执行 | 触发后自动执行全流程，完成后报告结果 |
| 📝 两种输出模式 | 无历史文案 → 1 个文件；有历史文案 → 2 个文件 |
执行规范（必须遵守）
- 先读后做：执行 Step N 前，先 Read
workflow/stepN-*.md - 逐步验证：每步完成后检查输出是否符合预期
- 不跳步骤：按 1→2→3→4→5→6 顺序执行
- 落盘优先：所有关键产物写入文件，不靠内存传递
- 身份对齐：所有输出必须对齐用户的身份、平台、目标、风格
工作流（6 步）
| Step | 职责 | 执行者 | 文档 | 输入 | 输出 |
|---|---|---|---|---|---|
| 01 | 参数收集 | 主Agent | workflow/step01-init.md |
用户触发 | state/config.json |
| 02 | 批量出题 | 主Agent | workflow/step02-generate.md |
源文案 + 身份目标 | 20 个候选选题 |
| 03 | 筛选精选 | 主Agent | workflow/step03-screen.md |
20 个候选 | 5 个精选方向 |
| 04 | 深度拆解 | 主Agent | workflow/step04-breakdown.md |
5 个精选方向 | 标题 + 文案结构 |
| 05 | 多角色评分 | 主Agent | workflow/step05-scoring.md |
5 个拆解 + 历史文案(可选) | 评分表 + 排名 |
| 06 | 输出组装 | 主Agent | workflow/step06-output.md |
全部产物 | output/ |
数据流
第一阶段：理解输入
用户输入（源文案路径 + 身份目标路径 + 历史文案路径[可选]）
→ Step 01: 收集参数 → state/config.json
→ Step 02: 精读源文案 + 身份目标 → 20 个候选选题
第二阶段：筛选拆解
20 个候选 → Step 03: 筛选 → 5 个精选方向
→ Step 04: 拆解 → 每个方向的标题 + 结构
第三阶段：评分输出
5 个拆解 → Step 05: 多角色评分（+ 历史校准）→ 评分表 + 排名
→ Step 06: 组装输出文件 → output/
输出文件
| 条件 | 输出文件 |
|---|---|
| 始终输出 | {output_dir}/YYMMDD-选题｜标题｜结构.md |
| 有历史文案时追加 | {output_dir}/YYMMDD-历史文案分析与重新评分.md |
参考资料
| 文件 | 路径 | 用途 |
|---|---|---|
| 评分角色定义 | reference/definitions/scoring-roles.md |
5 个评审角色的职责和权重 |
| 选题分类定义 | reference/definitions/topic-categories.md |
4 类选题的定义和比例 |
| 内容 DNA 规则 | reference/definitions/content-dna-rules.md |
风格约束、AI 痕迹控制、CTA 规则 |
| 输出模板 | reference/templates/output-template.md |
最终输出文件的结构模板 |
What ships with it
10 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.
- reference/definitions/content-dna-rules.md 2.0 KB
- reference/definitions/scoring-roles.md 1.0 KB
- reference/definitions/topic-categories.md 1.1 KB
- reference/templates/output-template.md 1.3 KB
- workflow/step01-init.md 1.6 KB
- workflow/step02-generate.md 1.9 KB
- workflow/step03-screen.md 1.4 KB
- workflow/step04-breakdown.md 2.1 KB
- workflow/step05-scoring.md 2.6 KB
- workflow/step06-output.md 1.7 KB
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.
- 10d ago First seen · 108 lines · 121 tokens per session scan A 66ddc07cc342
ray-content-topic-planning is a skill published in the GitHub repository 961882/ray-skills (29 stars, last pushed 3mo ago), licensed MIT. It adds 121 tokens to every session and 1,137 once invoked, about $0.0006 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 2026-08-30.
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…