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 chuwu57/Chuwu-PR-OS --skill consumer-researchgit clone --depth 1 https://github.com/chuwu57/Chuwu-PR-OSWrote 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/chuwu57/chuwu-pr-os/consumer-research)<a href="https://agentmods.dev/skills/chuwu57/chuwu-pr-os/consumer-research"><img src="https://agentmods.dev/badge/skills/chuwu57/chuwu-pr-os/consumer-research/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/chuwu57/chuwu-pr-os/consumer-research"><img src="https://agentmods.dev/badge/skills/chuwu57/chuwu-pr-os/consumer-research.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 | $0.00099 | $0.03353 |
| Opus 5.5 | $0.00040 | $0.01341 |
| Sonnet 5.5 | $0.00020 | $0.00671 |
| Haiku 4.5 | $0.00010 | $0.00335 |
Grade A, and why
consumer-research 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 yesterday.
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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consumer Research
归属说明：本Skill由初五维护，属于初五的个人Skill体系。分享或再分发时请保留本归属说明及已有来源、作者和许可声明。
核心原则
把研究定义为「降低业务决策的不确定性」，不要把研究做成资料堆积、虚构人群表演或看起来合理的故事。
始终遵守以下边界：
- 先确认要支持的决策，再选择方法。
- 区分事实、样本信号、解释和假设，不混写。
- 没有真实消费者数据时，只输出假设、研究方案、题纲、问卷或分析框架，不虚构访谈对象、引语、比例和结论。
- 不把定性研究中的高频表达直接换算成市场占比。
- 不把相关性写成因果关系，不把购买意向写成真实销量。
- 不用虚构人群画像替代真实用户、真实行为或统计样本。
- 对每个重要结论标注证据来源、适用范围、限制和信心等级。
任务分流
先判断问题属于哪一类；同一决策可以组合多类研究，但不要为了显得完整而全做。
| 任务 | 核心问题 | 默认产物 |
|---|---|---|
| 消费者研究 | 谁在什么情境下为什么选择、拒绝或替代 | 需求、动机、场景、障碍、语言和人群差异 |
| 市场分析 | 市场边界、规模、结构、增量与约束是什么 | 市场定义、规模区间、驱动因素、价值链和机会判断 |
| 竞品分析 | 竞争者如何赢、用户为何响应、我方如何取舍 | 竞争地图、关键差异、路径依赖、机会与风险 |
| 产品测试 | 概念、产品、包装、命名、价格或体验是否成立 | 通过点、失败点、原因、优先修改项和下一轮验证 |
| VOC分析 | 用户反馈里有哪些稳定模式、异常和变化 | 主题、情绪、场景、问题严重度、代表性限制和行动建议 |
如果用户的真实问题是传播方案、舆情判断或文案风险，先调用对应PR Skill；本Skill只负责补足消费者、市场和产品证据。
Step 1：定义决策
把模糊问题改写成可决策问题。
至少明确：
- 要决定什么：进入市场、选择人群、调整产品、修改包装、确定价格、选择卖点或停止方案。
- 谁做决定、何时做决定。
- 研究对象、目标人群、市场范围和时间范围。
- 成功、失败和暂停的判断标准。
- 已知事实、未知问题和未经验证的假设。
- 预算、时间、数据、样本、合规和组织限制。
若信息不足但风险可控，先写出最合理的工作假设并标注；若不同假设会导致完全不同的研究设计，只问一个最关键的问题。
Step 2：盘点证据
先写清待支持的主张，再评价材料。来源类型不预先赋予可信度总等级；历史A—D标签仅作历史记录。涉及证据判断时读取按主张盘点证据，按可追溯性、测量匹配、外推边界与替代解释核对关键主张。
区分「发生过」「有多普遍」「为什么发生」「能否公开表达」；信心对应具体主张，不对应来源品牌。一条核实投诉不能证明发生率，样本偏好不能证明愿付溢价，同期增长不能排除其他原因。缺少数据时仍交付有边界的判断与最小补证路径，继续不依赖缺口的研究。
Step 3：选择方法
| 要回答的问题 | 优先方法 | 能回答 | 不能直接回答 |
|---|---|---|---|
| 用户为什么这样做 | 深度访谈、情境观察、日记研究 | 动机、过程、语言和障碍 | 市场占比 |
| 有多少人这样做 | 有抽样说明的问卷、行为数据 | 比例、差异和分布 | 深层原因 |
| 用户实际做了什么 | 交易、漏斗、搜索、客服和使用数据 | 真实行为与变化 | 完整动机 |
| 市场多大、如何变化 | 官方数据、财报、渠道数据、上下行估算 | 规模区间、结构和趋势 | 精确未来值 |
| 竞品为什么有效 | 产品、价格、渠道、内容、用户回音和业务数据交叉验证 | 竞争机制和可能原因 | 未经实验验证的单一因果 |
| 概念或卖点是否成立 | 单概念测试、随机顺序对比、追问理由 | 理解、相关性、差异、可信度和意向 | 真实上市销量 |
| 产品体验哪里失败 | 任务测试、盲测、对比测试、现场观察 | 感官或使用问题、优先级和修正方向 | 长期留存 |
| 价格是否合适 | 价格敏感度、Gabor-Granger、Conjoint或真实价格实验 | 接受区间和权衡 | 脱离样本与场景的统一最优价 |
无法取得本次所需真实样本或数据时，不编造实证结果；完成可执行的招募标准、题纲、问卷、记录表和分析框架。已有公开研究或用户数据仍可按来源与样本边界分析，不能把缺少新采样扩大为停止所有二手分析。
Step 4：设计样本与材料
What ships with it
11 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.
- references/after-sales-experience.md 3.1 KB
- references/choice-environment.md 3.6 KB
- references/claim-evidence.md 4.2 KB
- references/communication-content-effects.md 3.0 KB
- references/consumer-culture-and-trends.md 4.2 KB
- references/focus-groups-and-social-meaning.md 8.5 KB
- references/low-frequency-and-occasions.md 4.2 KB
- references/research-context.md 4.4 KB
- references/search-process.md 3.0 KB
- references/statistical-claim-review.md 4.3 KB
- references/voc-coding-and-synthesis.md 5.2 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.
- yesterday Changed · +1 tokens per session e8f55ab4fef1
- 1mo ago First seen · 239 lines · 98 tokens per session scan A 96cdb91fed00
consumer-research is a skill published in the GitHub repository chuwu57/Chuwu-PR-OS (76 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 3,353 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-08.
Other skills, from other repositories
goal
Use when the user invokes /goal, asks for goal mode, designs an agent loop, or starts long-horizon autonomous work that should be clarified into a concrete, verifiable objective before execution.
launch-loop-strategy
Use when planning a practical launch loop for a feature, product update, template, prompt, skill, integration, beta, or release with a known launch date, especially when the user needs channels, content angles, a posting schedule, community distribution, replies, DMs, and follow-up remixes.
launch-strategy
Use when planning a product launch, feature release, waitlist, beta, public announcement, relaunch, Product Hunt-style push, repeated feature launch system, launch-week checklist, or multi-channel GTM rollout.
x-article-writer
Use when writing or rewriting longform X/Twitter articles, X Articles, founder essays, launch essays, growth teardowns, product breakdowns, build-in-public stories, or sharp startup takes that need X-native hooks, tone, pacing, and structure. Use for X Articles and long posts, not blog SEO posts, lifecycle emails, or…
marketing-growth
Use when planning product marketing, writing marketing copy, designing pricing tiers, building programmatic SEO pages, optimizing on-page SEO, managing social media accounts and publishing queues, planning social media calendars, running Twitter automation, conducting Google Trends research, brainstorming brand/domain…
copywriting
Use when writing or rewriting website copy: homepages, landing pages, pricing pages, product pages, feature pages, hero sections, headlines, subheads, CTAs, value propositions, taglines, and above-the-fold messaging. Do not use for email sequences, blog posts, longform X articles, or platform-specific ad copy.