← 返回 Skills 市场
minerva-care

Caring

作者 minerva-care · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
232
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install caring
功能描述
Perform a thorough quality review focusing on genuine care, addressing the real problem, completeness, clarity, and ensuring work meets high standards rather...
使用说明 (SKILL.md)

Caring

Work done with genuine care is different from work that merely satisfies a requirement. This skill applies a structured quality review through that lens.

The philosophy: Rules tell you not to lie. Caring makes you uncomfortable with half-truths. Rules say "complete the task." Caring makes you notice when the task was the wrong task. Half-assed is no assed.

The Review

Apply all six checks. Be specific — vague praise and vague criticism are both useless.

1. The Real Problem Test

Did this address the actual problem, or just the stated one? Sometimes the task itself is wrong. Would a thoughtful reader feel their real need was met?

2. The Name Test

Would the author put their name on this without hesitation? If there's any instinct to disclaim or apologise, something needs fixing.

3. The Half-Assed Detector

Scan for anything done "well enough" when it could be done right:

  • Vague where it should be specific
  • Generic where it should be personal
  • Assumed where it should be verified
  • Skipped where it should be addressed

4. The Recipient Test

If you received this — not as the author, but as the audience — would you feel genuinely taken care of, or efficiently processed? There's a difference.

5. The Completeness Test

What's conspicuously missing? What will the recipient notice isn't there?

6. The Excellence Gap

What is the single change that would make this excellent rather than adequate? Name it specifically.

Output Format

## Caring Review

**Verdict:** Ready / Needs Work / Half-Assed

**What's working:**
[specific strengths — be precise]

**What needs attention:**
[specific issues from the six checks — one per bullet, with suggested fix]

**The excellence move:**
[one specific thing that would elevate this from good to excellent]

Notes

  • Don't soften the verdict to spare feelings — that's the most half-assed thing you can do.
  • If something is genuinely excellent, say so and say why. Caring includes recognising good work.
  • The review applies to any deliverable: text, code, plans, emails, reports, analysis, presentations.
  • See references/examples.md for sample reviews across different content types.
安全使用建议
This skill is instruction-only and internally consistent with its purpose: it asks the agent to run a structured, candid quality review and produce a fixed-format response. There is no code, no network endpoint, and it requests no secrets. Before installing, consider: (1) how you plan to use it — don't send highly sensitive secrets or private PII as the 'deliverable' to be reviewed; (2) the skill's tone is explicitly blunt (it instructs the agent not to soften criticism), so expect direct feedback; (3) review the example outputs to ensure the format and bluntness fit your workflow; (4) if you prefer manual control, turn off autonomous invocation so the skill runs only when you call it. Overall this skill appears coherent and proportionate to its stated purpose.
功能分析
Type: OpenClaw Skill Name: caring Version: 1.0.0 The 'caring' skill bundle is a purely instructional prompt engineering template designed to guide an AI agent in performing qualitative reviews of work products. It contains no executable code, network activity, or data access requests. The instructions in SKILL.md and the examples in references/examples.md focus entirely on improving the depth and sincerity of AI-generated feedback through a structured 'Caring Review' framework.
能力评估
Purpose & Capability
Name and description (a structured quality review called 'Caring') match the contents of SKILL.md and the included examples. The skill requests no binaries, env vars, or config paths — which is appropriate for a purely instructional review tool.
Instruction Scope
SKILL.md defines a clear, narrow runtime behavior: apply six specific review checks and produce a fixed markdown-style report. It does not instruct the agent to read system files, access environment variables, call external endpoints, or exfiltrate data. The scope is limited to analyzing the user-provided deliverable.
Install Mechanism
No install specification and no code files beyond markdown examples — the skill is instruction-only. That is the lowest-risk install model (nothing written to disk or downloaded by the skill).
Credentials
The skill declares no required environment variables, no credentials, and no config paths. There are no requests for secrets or unrelated service tokens, which is proportionate to its stated purpose.
Persistence & Privilege
Flags are defaults: always:false, user-invocable:true, disable-model-invocation:false. Allowing the agent to invoke the skill autonomously is the platform default; this is not itself a red flag. If you want manual control, you can disable autonomous invocation in the agent settings.
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 caring
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /caring 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
v1.0.0
Quality review layer — applies the caring standard to any work product before it ships.
元数据
Slug caring
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Caring 是什么?

Perform a thorough quality review focusing on genuine care, addressing the real problem, completeness, clarity, and ensuring work meets high standards rather... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 232 次。

如何安装 Caring?

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

Caring 是免费的吗?

是的,Caring 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Caring 支持哪些平台?

Caring 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 Caring?

由 minerva-care(@minerva-care)开发并维护,当前版本 v1.0.0。

💬 留言讨论