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 mabzhang/opc-toolkit --skill consumer-insightgit clone --depth 1 https://github.com/mabzhang/opc-toolkitWrote 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/mabzhang/opc-toolkit/consumer-insight)<a href="https://agentmods.dev/skills/mabzhang/opc-toolkit/consumer-insight"><img src="https://agentmods.dev/badge/skills/mabzhang/opc-toolkit/consumer-insight.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.01101 |
| Opus 5 | $0.00044 | $0.00550 |
| Sonnet 5 | $0.00017 | $0.00220 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
consumer-insight 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 7d 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.
What it actually says
Consumer Insight — 消费者洞察
将公开数据、社交聆听、评论语料和 Brief 信息转成创意团队可使用的人群洞察，而不是只给人口统计画像。
洞察原则
- 洞察必须解释“为什么会行动”，不只描述“他们是谁”。
- 真实用户原话必须来自公开来源；不能编造评论。
- 将核心人群和机会人群分开，避免“所有人都是目标用户”。
- 区分痛点、欲望、障碍、触发场景和信任证据。
- 输出要能直接指导内容标题、脚本、KOL 人设、渠道选择和转化钩子。
四层洞察模型
| 层级 | 要回答的问题 | 输出 |
|---|---|---|
| Who | 谁最可能买，谁最值得争取 | 人群分层、生活方式、消费能力 |
| What | 他们在意什么 | 功能需求、情绪需求、社交表达 |
| Why | 为什么买/不买 | 购买驱动、障碍、决策链路 |
| Where/When | 在哪被触发，什么时候下单 | 平台习惯、内容场景、购买时机 |
研究方法
- 社交聆听：小红书、抖音、微博、B站、知乎等公开内容。
- 交易评论：天猫、京东、抖音电商、品牌私域反馈，如可获得。
- 搜索/指数：百度指数、巨量算数、微信指数、平台热搜等。
- 行业报告：艾瑞、QuestMobile、平台白皮书、协会报告。
- Brief 证据：客户提供的一方人群、CRM、会员、销售反馈。
痛点分类
| 类型 | 用户表现 | 内容价值 |
|---|---|---|
| 功能痛点 | 产品不好用、效果不确定 | 功效证明、测评对比 |
| 信任痛点 | 不知道哪个可信 | 专业背书、真实案例、KOL 证言 |
| 决策痛点 | 选择太多、怕踩坑 | 选购指南、场景推荐 |
| 价格痛点 | 贵的不敢买，便宜的不放心 | 价值拆解、组合权益 |
| 情绪痛点 | 焦虑、尴尬、身份认同 | 情绪共鸣、生活方式内容 |
| 使用痛点 | 买后不会用、坚持不了 | 教程、挑战、陪伴型内容 |
洞察卡格式
每个关键洞察尽量写成：
因为 [真实场景/障碍]，
目标人群会 [行为/犹豫/搜索/比较]，
所以品牌应该用 [内容/证据/渠道]，
帮助他们 [降低风险/获得认同/完成决策]。
输出格式
# 消费者洞察报告
## 1. 核心判断
- 核心人群：
- 机会人群：
- 最强购买驱动：
- 最大转化障碍：
## 2. 人群分层
| 人群 | 画像 | 场景 | 痛点 | 内容触发 | 渠道 |
|---|---|---|---|---|---|
## 3. 真实用户语言
| 来源 | 用户原话/高频表达 | 反映的问题 | 可转化内容 |
|---|---|---|---|
## 4. 购买决策链路
认知 -> 兴趣 -> 搜索/比较 -> 信任建立 -> 下单 -> 复购/分享
为每一环写清：
- 用户问题：
- 需要的证据：
- 合适的内容：
- 合适的渠道：
## 5. 洞察卡
### 洞察 1：[一句话命名]
- 证据：
- 策略含义：
- 内容动作：
- KOL/渠道启示：
## 6. 创意与执行建议
- 说什么：
- 怎么说：
- 谁来说：
- 在哪说：
- 避免什么：
规则
- 画像要有具体场景，不只写年龄、性别、城市。
- 如果无法取得真实评论，明确写“缺少公开语料验证”，并把语料验证列入信息缺口。
- 不把单条评论当成普遍结论；至少说明它是案例、模式还是推断。
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.
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.
- 7d ago First seen · 110 lines · 87 tokens per session scan A de4bcd5bb0ec
consumer-insight is a skill published in the GitHub repository mabzhang/opc-toolkit (3 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,101 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.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
brainstorming
A brainstorming workflow for turning an idea into an agreed design before implementation. It requires exploring the project, asking clarifying questions, comparing options, documenting the design, and getting user approval.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
mcp-builder
A guide to building Model Context Protocol (MCP) servers, which let AI assistants use tools and read external data. It covers server structure, tool design, testing, and deployment in TypeScript and Python.