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 cafe3310/public-agent-skills --skill tech-to-marketing-briefgit clone --depth 1 https://github.com/cafe3310/public-agent-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/cafe3310/public-agent-skills/tech-to-marketing-brief)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/tech-to-marketing-brief"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/tech-to-marketing-brief/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/cafe3310/public-agent-skills/tech-to-marketing-brief"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/tech-to-marketing-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01651 |
| Opus 5 | $0.00019 | $0.00826 |
| Sonnet 5 | $0.00008 | $0.00330 |
| Haiku 4.5 | $0.00004 | $0.00165 |
Grade A, and why
tech-to-marketing-brief 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 13d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech-to-Marketing-Brief (产研侧宣发物料生成器)
当产研人员(技术/算法)需要向运营团队交付新功能、或者需要为冷冰冰的技术指标包装具有“人味”和“网感”的宣发方案时,务必触发此技能。
技能背景
产研人员(技术、算法)往往擅长描述“怎么实现”和“技术指标”,但运营团队需要的是“解决什么痛点”和“如何引发传播”。 本技能的作用是充当翻译官与策划大师,将零碎的技术描述,通过发散思维、痛点关联和风格重塑,转化为可直接交付给运营和开发侧的三大核心产物。
工作流 (Workflow)
当用户输入技术特性的零星描述时,请严格按照以下步骤执行:
Step 0: 专家资源检索 (Expert Retrieval - 推荐)
在正式开始前,为了获取更专业的行业视角与标准模版,建议通过 /skill::plugin-search-and-use 检索以下领域的专家插件(位于 knowledge-work-plugins 目录下):
- 市场营销领域:检索
campaign-plan(活动策划)、content-creation(内容创建)、brand-review(品牌语气检查) 等插件,以辅助 Step 2 和 Step 3。 - 产品管理领域:检索
write-spec(需求撰写) 插件,以提升 Step 4 中 Jira Ticket 的编写专业度。 - 上下文获取:如果需要对标竞品,可检索
competitive-brief(竞品简报) 插件。
Step 1: 发散与关联 (Divergent Thinking & Research)
- 提取核心技术点:识别用户输入中的技术亮点(如长文本处理、复杂逻辑推理、跨模态理解能力)。
- 痛点翻译:将技术指标翻译为实际生产环境中的特定限制或效率瓶颈。例如:将“超长上下文”映射为“打破多文档关联分析时的信息割裂”;将“CoT 推理”映射为“解决决策链路中容易忽略的边缘案例”。
- (可选) 联网搜索:使用 WebSearch 工具搜索目标用户群(如开发者、文案人员、财务人员)近期的共性抱怨或热议的垂直领域话题,寻找可以结合的真实痛点。
Step 2: 撰写运营 Brief 文档 (The Operations Brief)
生成一份标准的、可直接交付给运营或外部博主的 Brief 文档。 必须包含以下模块:
- 差异化认知(核心心智):明确该技术带来的核心改变(如:从“AI 作为工具”到“AI 作为深度业务参与者”的认知跨越)。
- 高保真测试场景(核心):严禁无目的、低强度的泛化测试(如简单的润色/总结)。应设计 1-2 个真实世界中面临的信息密度极高、逻辑极复杂的垂直测试场景(如:多源碎片信息的长链条对齐、特定职业中的非标流程自动化)。
- 转化与操作路径:说明产品的接入入口、特定模型版本及功能切换方式。
- 审核红线:禁止单纯的“称赞式”测评。必须要求展示模型解决问题的“真实探索过程”或“从混乱到秩序的演化路径”。
Step 3: 产出社媒宣发案例库 (Social Media Cases)
根据上述场景,为不同受众群体提供案例原型:
- 视觉/感官驱动型 (如小红书):
- 风格:问题前置、强烈的逻辑反差、强调“确定性”。
- 内容:重点通过 Before & After 的对比,展示原本极其耗时的繁琐工作如何变得轻量化、透明化。
- 深度洞察型 (如微信公众号):
- 风格:专业主义、去大词、去黑话。
- 内容:从底层逻辑分析技术突破如何重塑业务流程,展示对垂直行业的非共识见解。
- 极简事实型 (如 X / 朋友圈):
- 风格:Hook + 硬核证据。
- 内容:一句极具冲击力的事实陈述 + 配合能够体现逻辑深度的产出截图。
Step 4: 拆解配套的开发任务 (Jira Tickets)
为了支撑上述的营销活动,产品需要具备对应的落地承接能力。请输出 1-3 个具体的 Jira 任务(Epic/Task):
- 标题:格式如
[Feature] 配合XX宣发:增加XXX功能 - User Story (用户故事):As a... I want to... So that...
- 验收标准 (AC):如:网关层需识别外部请求并自动注入调优好的系统指令集;或者在产品后台上线专用的业务场景模板。
风格规范 (Tone & Guidelines)
- 拒绝套路表达:输出必须符合资深业务专家的视角。严禁使用“随着 AI 时代的到来”、“本质上”、“致力于”等废话。
- 制造差异化张力:通过挖掘“反直觉的事实”或“业务链条中的隐性矛盾”来建立张力。
- 细节决定颗粒度:所有的案例、场景必须源自真实、具体的业务切片(如特定职业的特定操作流、极端压力下的应急任务),严禁使用过度虚化的通用描述。
What ships with it
3 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.
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.
- 13d ago First seen · 73 lines · 39 tokens per session scan A 29208fc1e115
tech-to-marketing-brief is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,651 once invoked, about $0.0002 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
firstsun-project-init
Bootstraps a firstsun-dev project end-to-end: selects relevant skills, scaffolds the agent harness, creates or reconciles the GitHub repository, applies repository metadata and README standards, and classifies the project under Firstsun Dev governance. New projects default to Workshop and are not automatically…
firstsun-pm
Expert project management for the Firstsun-Dev organization. This skill standardizes issue creation across multiple repositories, ensures all tasks are correctly linked to the central Project Board (#6), and enforces naming conventions. Trigger this whenever the user says "add a task", "create a ticket", "new job"…
monorepo-management
Master monorepo management. Use this to set up or optimize multi-package repositories using Turborepo, pnpm workspaces, or Nx.
gh-cli
GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
spec-kitty-mission-system
Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are resolved through the 6-tier chain, and how doctrine artifacts (procedures, tactics, directives) compose mission behavior.…