marketing-proposal

marketing-proposal is a skill for Claude Code, Codex from mabzhang/opc-toolkit. It costs 88 tokens per session (1,493 once invoked), scanned A, original, MIT.

A tool for turning marketing research and strategy into a client-ready Chinese proposal. A proposal is a document that explains what should be done, why, how it will be executed, and how success will be measured.

In plain words
What is it for?
Use it to write campaign proposals, launch plans, annual marketing plans, executive summaries, budget and return estimates, or post-campaign improvement plans.
Why use it?
It organizes scattered strategy inputs into a decision document with a clear link between the business problem, recommendation, evidence, actions, budget, and measurement.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: $skill-name invocation.

Part of the opc-toolkit plugin — 11 skills shipped together

Good fit Use it to write campaign proposals, launch plans, annual marketing plans, executive summaries, budget and return estimates, or post-campaign improvement plans.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mabzhang/opc-toolkit/marketing-proposal
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 mabzhang/opc-toolkit --skill marketing-proposal
Clone the repo
git clone --depth 1 https://github.com/mabzhang/opc-toolkit

Made for: Claude Code, Codex.

Or install opc-toolkit, the plugin that ships this one along with the rest of its 11 skills.

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 marketing-proposal

README.md
[![agentmods](https://agentmods.dev/badge/skills/mabzhang/opc-toolkit/marketing-proposal/github.svg)](https://agentmods.dev/skills/mabzhang/opc-toolkit/marketing-proposal)
Your own site
<a href="https://agentmods.dev/skills/mabzhang/opc-toolkit/marketing-proposal"><img src="https://agentmods.dev/badge/skills/mabzhang/opc-toolkit/marketing-proposal/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 marketing-proposal

Your own site · 80×15
<a href="https://agentmods.dev/skills/mabzhang/opc-toolkit/marketing-proposal"><img src="https://agentmods.dev/badge/skills/mabzhang/opc-toolkit/marketing-proposal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,493 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 $0.00088 $0.01493
Opus 5 $0.00044 $0.00746
Sonnet 5 $0.00018 $0.00299
Haiku 4.5 $0.00009 $0.00149

Measured 9d ago against content hash 0e8e38c1f64a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

marketing-proposal 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 9d 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.

skills/marketing-proposal/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Marketing Proposal — 客户提案写作

把 Brief、研究、策略和执行计划整理为客户可读、可汇报、可决策的正式营销方案。重点是说服逻辑、结构完整、证据清楚和动作可落地。

写作原则

  1. 先结论后展开:客户先看到我们推荐什么和为什么。
  2. 用“背景 -> 洞察 -> 挑战 -> 策略 -> 创意/业务落地 -> 预算/KPI -> 排期”的逻辑链。
  3. 每个建议写明目标连接:为了什么、做什么、怎么衡量。
  4. 数据、竞品动作、用户原话、平台规则必须有来源;无来源则标注为假设。
  5. 预算和 ROI 不凭空承诺;给测算口径、变量和风险。
  6. 文风专业、清晰、有判断,避免堆砌形容词。
  7. 默认输出 Markdown .md 文档。若用户要求 PPT 或其它格式,把它当作额外交付物。
  8. 章节顺序按用户本次业务优先级动态调整,不把历史案例或固定 16 模块当作最终目录。

提案层级

类型 适用场景 推荐结构
精简方案 方向确认、内部沟通 6-8 个章节,突出判断和下一步
完整方案 客户提案、比稿 12-16 个章节,含研究、策略、执行、预算
执行方案 已定策略后的落地 重点写任务、排期、验收和风险
复盘/优化 投放后或运营中 数据表现、问题诊断、优化动作

动态章节模块

以下模块用于组装正式提案,不是固定目录。先看用户这次是直播、品牌 Campaign、商品卡、千川、KOL 媒介、年度运营还是研究分析,再决定前置顺序。

  1. 封面信息:品牌、项目、日期、版本。
  2. 执行摘要:一句话策略、关键机会、推荐打法。
  3. Brief 解构:目标、受众、产品、限制、关键矛盾。
  4. 资料来源与假设:本地资料、网络资料、来源矩阵、信息缺口。
  5. 市场与竞品:行业趋势、品类格局、竞品启示。
  6. 消费者洞察:人群、痛点、购买链路、内容触发。
  7. 核心挑战:本次项目必须解决的关键问题。
  8. 策略方向:核心主张、差异化、证据链。
  9. 创意主题:主题、解读、视觉/文案调性、内容支柱。
  10. 重点业务方案:把用户第一优先级写深,例如直播、Campaign、商品卡、千川、KOL/媒介或店铺运营。
  11. 支撑业务方案:只写与主目标强相关的承接模块。
  12. KOL/媒介:达人组合、平台角色、投放优化。
  13. 预算与 KPI:预算结构、目标框架、测量方式。
  14. 时间表与任务:里程碑、责任分工、验收标准。
  15. 风险预案:关键风险、触发信号、B 方案。
  16. 附录:来源、计算、假设、信息缺口。

说服力检查

  • 不是“市场很大”,而是说明具体增长点和本项目可抓住的部分。
  • 不是“年轻人喜欢”,而是说明哪个细分人群、什么场景、什么证据。
  • 不是“做内容矩阵”,而是说明每个内容支柱承担什么任务。
  • 不是“找达人种草”,而是说明达人层级、垂类、人设和验收标准。
  • 不是“提升 ROI”,而是说明预算口径、转化链路和优化变量。

输出格式

# [品牌名] [项目名] 营销方案
提案日期:[日期] | 版本:[V1.0]

## 执行摘要
[3-5 句:背景、核心挑战、推荐策略、预期结果。]

## 一、Brief 与目标
| 维度 | 内容 | 判断 |
|---|---|---|

## 二、市场与竞品洞察
[行业机会、竞品启示、可攻击空白。]

## 三、消费者洞察
[核心人群、痛点、购买障碍、内容触发。]

## 四、核心挑战
[一句话挑战 + 为什么它重要。]

## 五、策略方向
[核心主张、差异化、证据链。]

## 六、创意主题
[主题、解读、创意领地、内容支柱。]

## 七、重点业务方案
[根据本次优先级写深:直播 / Campaign / 商品卡 / 千川 / KOL媒介 / 年度运营等。]

## 八、支撑业务方案
| 阶段 | 时间 | 目标 | 内容动作 | 渠道 | KPI |
|---|---|---|---|---|---|

## 九、KOL 与媒介策略
[达人矩阵、渠道角色、投放逻辑。]

## 十、预算与 KPI
| 费用项 | 金额/占比 | 作用 | 备注 |
|---|---|---|---|

## 十一、执行时间表与任务单
| 时间 | 任务 | 负责人角色 | 输出物 | 验收标准 |
|---|---|---|---|---|

## 十二、风险预案
| 风险 | 影响 | 应对 |
|---|---|---|

## 十三、来源、假设与信息缺口

规则

  • 如果用户要求“4A 全案”,优先使用 $opc-proposal 的动态融合框架和 proposal-blueprint.md 的策略完整性模块。
  • 如果素材不足,仍可出 V0.1 方向稿,但必须列假设和需确认事项。
  • 避免在提案正文里写过多过程说明;把来源和假设放附录。

Read the full file on GitHub · 122 lines

Files

What ships with it

1 file 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.

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. 9d ago First seen · 122 lines · 88 tokens per session scan A 0e8e38c1f64a

Subscribe to this mod's changes

marketing-proposal is a skill published in the GitHub repository mabzhang/opc-toolkit (3 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,493 once invoked, about $0.0004 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.