brief-analysis

brief-analysis is a skill for Claude Code, Codex from mabzhang/opc-toolkit. It costs 86 tokens per session (1,549 once invoked), scanned A, original, MIT.

A requirements-reading tool for turning briefs, chat records, meeting notes, voice-note summaries, and scattered requests into organized requirement cards. It separates confirmed facts, assumptions, conflicts, missing information, and next steps.

In plain words
What is it for?
Use it to clarify a marketing project before execution, identify information gaps, record assumptions, and turn a one-line request or conversation into an actionable brief.
Why use it?
It reduces the risk of starting work with unclear goals, missing constraints, or contradictory instructions. It also shows which unanswered questions could change the strategy or delivery.

Skill for Claude CodeCodex

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

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.

agentmods
npx agentmods add skills/mabzhang/opc-toolkit/brief-analysis
Any agent
npx skills add mabzhang/opc-toolkit --skill brief-analysis
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 brief-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/mabzhang/opc-toolkit/brief-analysis.svg)](https://agentmods.dev/skills/mabzhang/opc-toolkit/brief-analysis)
Your own site
<a href="https://agentmods.dev/skills/mabzhang/opc-toolkit/brief-analysis"><img src="https://agentmods.dev/badge/skills/mabzhang/opc-toolkit/brief-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,549 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00086 $0.01549
Opus 5 $0.00043 $0.00775
Sonnet 5 $0.00017 $0.00310
Haiku 4.5 $0.00009 $0.00155

Measured 5d ago against content hash ce1d7e029358, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brief-analysis 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 5d 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/brief-analysis/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brief Analysis — 需求归一与对齐

把任何格式的客户输入转成可执行的项目需求卡,识别目标矛盾、信息缺口、工作假设和下一步任务。

开工前确认

开始正式解析前,先检查任务口径。至少覆盖:

  • 用户真正要做什么,聚焦哪个品牌、产品、品类、平台和业务优先级。
  • 本地资料有哪些,每份资料用于什么;哪些部分禁止用网络公开数据替代。
  • 逐板块资料来源矩阵:行业、竞品、消费者、人群、关键词、价格段、直播、商品卡、千川、KOL、Campaign、TVC、预算/KPI 分别是“仅本地上传 / 仅网络公开 / 本地为主+网络补充 / 网络为主+本地校验”。
  • 是否允许联网,以及只允许在哪些未被本地资料覆盖的部分联网。
  • 给谁看、用于什么决策、默认交付为 Markdown .md、需要什么深度。
  • 参考旧方案时,哪些只借鉴框架,哪些会议纪要/修改意见优先级更高。

只有缺失信息会改变战略方向、交付边界或高风险判断时才暂停追问。若用户需求明确、要求直接开始或缺口可逆,先输出确认摘要和关键假设,然后继续解析。不要因为历史案例聚焦直播,就默认所有方案直播第一;业务主次必须来自用户本次输入。

输入处理

  1. 先完整读取全部材料,不要只抓关键词。
  2. 将原文信息分为:
    • 已明确:客户明确说过或文件中写明。
    • 可推断:根据上下文和行业常识可暂定。
    • 冲突:不同材料或同一材料内部矛盾。
    • 缺失:会影响策略、预算、排期或验收的信息。
  3. 对聊天记录和会议纪要,优先提炼“最终口径”,保留重要分歧。
  4. 对一句话需求,先形成最小可用 Brief,再列追问。

信息提取维度

维度 内容 必须程度
品牌与业务 品牌名、行业、产品类别、商业模式、客单价 必须
项目类型 新品上市、节点 Campaign、社媒运营、直播、年度规划、分析报告等 必须
目标 业务目标、传播目标、转化目标、优先级 必须
目标受众 核心人群、机会人群、地域、消费能力、痛点 必须
产品/卖点 USP、RTB、价格、货盘、合规表达、禁区 必须
竞品 直接竞品、替代竞品、客户提到的参考对象 尽量
渠道 抖音、小红书、微信、微博、B站、电商、线下等 必须
时间 提案日、上线日、节点、审核周期、素材交付期 必须
预算 制作、达人、媒介、样品、机动 尽量
资产 品牌规范、历史案例、素材、店铺/账号、数据后台 尽量
限制 合规红线、禁用词、法务审核、行业监管、品牌偏好 必须确认
成功标准 KPI、验收方式、客户内部决策标准 必须确认

Brief 质量评级

  • A 级:目标、受众、产品、渠道、时间、限制、验收方式明确,可直接进入策略和执行。
  • B 级:缺 1-3 个关键项,但能以工作假设推进,需要同步确认。
  • C 级:目标冲突或缺失过多,必须先做对齐工作坊或追问清单。

常见矛盾与处理

矛盾 表现 处理
品牌 vs 转化 又要声量又要短期 GMV 分阶段目标,拆 KPI 权重
人群过宽 “18-45 岁女性” 拆核心人群和机会人群
卖点过多 客户给 8-10 个卖点 提炼主卖点、支撑卖点、禁用卖点
预算不匹配 低预算参考高制作案例 说明差距,给替代执行路径
时间不合理 过短周期要求大制作/多平台 给风险、压缩方案和必须取舍
口径冲突 销售、市场、老板说法不同 标注冲突,建议确认最终决策人

输出格式

# 项目需求卡

## 1. 一句话项目判断
[用一句话说明这是一个什么项目,真正要解决什么问题。]

## 2. 已知信息
| 维度 | 内容 | 来源片段/依据 | 可信度 |
|---|---|---|---|

## 3. 关键矛盾
| 矛盾 | 影响 | 建议处理 |
|---|---|---|

## 4. 工作假设
| 假设 | 为什么可先这样假设 | 影响范围 | 需确认方式 |
|---|---|---|---|

## 5. 信息缺口
| 优先级 | 缺失信息 | 为什么重要 | 建议追问 | 能否先推进 |
|---|---|---|---|---|

## 6. 资料来源矩阵
| 分析板块 | 建议资料来源 | 是否需要用户授权联网 | 备注 |
|---|---|---|---|

## 7. Brief 质量评级
评级:[A/B/C]
理由:[3 条以内]

## 8. 下一步建议
- 立即启动:[可开始的研究/策略/执行任务]
- 等待确认:[必须确认的信息]

Read the full file on GitHub · 115 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. 5d ago First seen · 115 lines · 86 tokens per session scan A ce1d7e029358

Subscribe to this mod's changes

brief-analysis is a skill published in the GitHub repository mabzhang/opc-toolkit (3 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,549 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.

Related

Other skills, from other repositories

chinese-git-workflow

国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 69 tokens

brainstorming

在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。.

jnMetaCode/superpowers-zh · 40 tokens

chinese-commit-conventions

中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 65 tokens

chinese-documentation

中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 62 tokens

chinese-code-review

中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 62 tokens

mcp-builder

MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具,让 AI 助手连接外部能力.

jnMetaCode/superpowers-zh · 32 tokens