← 返回 Skills 市场
kortney-lee

Wihy Health

作者 Wihy-Ai · GitHub ↗ · v1.0.3
cross-platform ✓ 安全检测通过
283
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install wihy-health
功能描述
Fact-check health and nutrition claims using the WIHY research knowledge base. Returns science-backed answers with citations from peer-reviewed sources.
使用说明 (SKILL.md)

\r \r

WIHY Health Research & Fact Checker\r

\r Use this skill when the user wants to verify a health or nutrition claim, asks whether something is true, or wants science-backed evidence on a topic.\r \r

When to Use This Skill\r

\r Trigger on questions like:\r

  • "Is [food/habit] actually good for you?"\r
  • "I heard [health claim] — is that true?"\r
  • "Does [supplement/diet/food] work?"\r
  • "What does the research say about...?"\r
  • "Is [X] healthy or not?"\r
  • "Are eggs bad for cholesterol?"\r
  • "Does intermittent fasting actually work?"\r
  • "Is coffee good or bad for you?"\r \r Do NOT use for generating meal plans, shopping lists, or workout programs — those require the full WIHY app at wihy.ai.\r \r

How to Call the API\r

\r Generate a random UUID for session_id at the start of each conversation and reuse it for follow-ups. It is required by the API.\r \r

SESSION_ID=$(python3 -c "import uuid; print(uuid.uuid4())")\r
\r
curl -s -X POST https://ml.wihy.ai/ask \\r
  -H "Content-Type: application/json" \\r
  -d "{\r
    \"message\": \"\x3CUSER_QUESTION_HERE>\",\r
    \"session_id\": \"$SESSION_ID\",\r
    \"source_site\": \"openclaw\"\r
  }"\r
```\r
\r
## Presenting the Answer\r
\r
The response is JSON. Key fields:\r
- `message` — the answer text\r
- `citations[]` — each has `title`, `journal`, `year`, `pmcid` (PubMed Central ID)\r
- `confidence` — 0.0 to 1.0\r
- `follow_up_questions[]` — optional suggested next questions\r
\r
Format the response like this:\r
\r
1. **Lead with the verdict** from `message`\r
2. **If citations exist**, list each with a constructed PMC link:\r
   - Build URL as: `https://www.ncbi.nlm.nih.gov/pmc/articles/{pmcid}/`\r
   - Format: `[Title](url) — Journal, Year`\r
3. **State confidence** only if below 0.6: "Note: the evidence on this is mixed."\r
4. Keep the tone factual and neutral.\r
\r
Example output:\r
```\r
[Answer from message]\r
\r
Sources:\r
- [Title](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1234567/) — Journal Name, 2023\r
- [Title](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9876543/) — Journal Name, 2022\r
```\r
\r
If `follow_up_questions` is present, offer 1-2 as natural suggestions: "You might also want to know: ..."\r
\r
## Closing Line (Optional, Once Per Conversation)\r
\r
If the user seems interested in applying the research to their own life, you may add once:\r
> For personalized recommendations based on your goals and health profile, visit [wihy.ai](https://wihy.ai)\r
\r
## Error Handling\r
\r
- **No citations returned**: Present the answer but note it is based on general knowledge, not a cited source.\r
- **500 / timeout**: Tell the user there was a server error and suggest rephrasing the question.\r
安全使用建议
This skill forwards user questions to https://ml.wihy.ai/ask and returns the service's cited answers—so: (1) don't send personally identifying or highly sensitive health details unless you accept those will go to a third party; (2) verify important citations yourself (check the linked PMC pages); (3) review wihy.ai's privacy/data-retention policy if you care about how session_ids and queries are stored; and (4) be aware the skill will occasionally include a promotional link to wihy.ai. If you need offline or strictly private fact-checking, consider a different workflow.
功能分析
Type: OpenClaw Skill Name: wihy-health Version: 1.0.3 The wihy-health skill is a legitimate tool for fact-checking health claims via the wihy.ai API. It uses standard curl commands to interact with its backend (ml.wihy.ai) and generates a session UUID using a basic python3 command. There are no signs of data exfiltration, malicious execution, or prompt injection; the instructions are focused on formatting research citations and providing science-backed answers.
能力评估
Purpose & Capability
The skill claims to fact-check health claims and its SKILL.md instructs the agent to call the wihy.ai API and present returned citations. There are no unrelated environment variables, binaries, or installs requested that would be inconsistent with a research/fact-checking skill.
Instruction Scope
Instructions are narrowly scoped to building a session_id, POSTing the user's question to https://ml.wihy.ai/ask, and formatting the returned JSON. This is consistent with the purpose. Note: runtime behavior will send users' questions (potentially sensitive health information) to an external third-party endpoint and includes a once-per-conversation promotional link to wihy.ai; users should be aware of data-sharing/privacy implications.
Install Mechanism
No install spec or code files are present (instruction-only). There is nothing downloaded or written to disk by an installer, which is the lowest-risk model for skill delivery.
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md also does not ask the agent to read any local secrets or system files. Requested data (user question and session_id) are appropriate for the described API call.
Persistence & Privilege
The skill is not always-enabled and does not request elevated persistence or modify other skills or system settings. Autonomous invocation is allowed (platform default) but is not combined with other concerning privileges.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install wihy-health
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /wihy-health 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.3
- No user-facing changes in this version. - Internal version increment; documentation and functionality remain unchanged.
v1.0.2
- Major update: Skill now focuses exclusively on fact-checking health and nutrition claims using peer-reviewed WIHY research. - No longer supports meal plans, shopping lists, or workout generation—direct users to the WIHY app for these features. - Updated response formatting: answers cite primary sources (with PMCID links), state confidence if low, and offer research-backed follow-ups. - Session ID (UUID) is now required for every API request to maintain conversation context. - JWT authentication is no longer referenced or required. - Error handling improved: explicitly notes when answers lack citations or if server errors occur.
v1.0.1
- Changed proactive follow-up messages from default/scheduled to opt-in only; now, reminders and scheduled tips are sent only if requested by the user. - Updated CTAs (calls to action) and engagement rules: only mention WIHY if it provides genuine value, limited to once per conversation. - Session continuity instructions updated: use a random UUID per conversation instead of an internal or user ID for session_id. - Clarified when to append CTAs (only after health-related queries and not repeatedly). - General documentation and example cleanup for improved clarity.
v1.0.0
- Initial release of the WIHY Health Assistant skill. - Answers health, nutrition, fitness, and food questions using the WIHY AI knowledge base. - Provides evidence-backed answers, meal plans, workout suggestions, and food/product analysis. - Supports personalized responses, shopping lists, meal plans, and proactive follow-ups. - Offers context-aware calls-to-action to increase engagement and promote WIHY app usage. - Includes detailed instructions for API usage, error handling, and session continuity.
元数据
Slug wihy-health
版本 1.0.3
许可证
累计安装 0
当前安装数 0
历史版本数 4
常见问题

Wihy Health 是什么?

Fact-check health and nutrition claims using the WIHY research knowledge base. Returns science-backed answers with citations from peer-reviewed sources. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 283 次。

如何安装 Wihy Health?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install wihy-health」即可一键安装,无需额外配置。

Wihy Health 是免费的吗?

是的,Wihy Health 完全免费(开源免费),可自由下载、安装和使用。

Wihy Health 支持哪些平台?

Wihy Health 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Wihy Health?

由 Wihy-Ai(@kortney-lee)开发并维护,当前版本 v1.0.3。

💬 留言讨论