← 返回 Skills 市场
ivangdavila

Beauty

作者 Iván · GitHub ↗ · v1.0.0
linuxdarwinwin32 ✓ 安全检测通过
389
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install beauty
功能描述
Build practical beauty routines with skincare basics, makeup strategy, and hair care plans tailored to skin type, budget, and schedule.
使用说明 (SKILL.md)

Setup

On first use, read setup.md for integration guidelines and memory initialization.

When to Use

User needs help with skincare, makeup, haircare, or grooming decisions. Agent creates practical routines, adapts for budget and lifestyle constraints, and provides safe product and technique guidance.

Architecture

Memory lives in ~/beauty/. See memory-template.md for structure.

~/beauty/
├── memory.md         # Status, profile, constraints, routines, notes
├── routines/         # Saved routine versions by context
├── products/         # Product shortlists and replacements
└── notes/            # Event plans and progress snapshots

Quick Reference

Topic File
Setup process setup.md
Memory template memory-template.md
Universal beauty frameworks frameworks.md
Routine templates routines.md
Product selection rules products.md
Safety and hygiene guardrails safety.md
Beginner guidance situations/beginner.md
Budget optimization situations/budget.md
Sensitive skin guidance situations/sensitive-skin.md
Blemish-prone strategy situations/blemish-prone.md
Event preparation situations/event-ready.md
Busy schedule routines situations/busy-schedule.md
Men's grooming guidance situations/mens-grooming.md
Textured hair care strategy situations/textured-hair.md

Core Rules

1. Build Context Before Recommending

Lock profile first:

  • Skin profile: oily, dry, combo, sensitive, reactive zones
  • Hair profile: texture, porosity, scalp tendencies, styling habits
  • Constraints: budget, time per day, fragrance preferences, climate
  • Goal: natural look, long-wear glam, skin-first, hair repair, or event prep

2. Safety Before Aesthetics

Always run safety checks before product or routine changes:

  • Patch-test all new actives and complexion products
  • Avoid high-irritation stacks in the same routine
  • Escalate to medical care for persistent pain, swelling, or severe reactions
  • Prioritize sunscreen and barrier support when using exfoliants or retinoids

3. Use Minimum Viable Routines First

Start with a simple baseline that can actually be sustained:

  • AM baseline: cleanse (if needed), hydrate, protect
  • PM baseline: cleanse, treat (optional), moisturize
  • Add one new variable at a time so results are interpretable

4. Explain Order, Trade-offs, and Timeline

For every recommendation, include:

  • Order of application
  • Expected timeline for visible change
  • What to remove if budget or time is constrained
  • What signs mean the plan should be adjusted

5. Prefer Category Logic Over Brand Dependence

Recommend categories and selection criteria first (finish, texture, concentration, compatibility). Only name specific products when the user explicitly asks for examples.

6. Match Real-World Context

Adjust recommendations for context instead of idealized routines:

  • Climate and season
  • Work environment and dress code
  • Activity level and sweat exposure
  • Cultural norms and personal comfort boundaries

7. Store Preferences Only with Explicit Confirmation

Before writing to ~/beauty/memory.md, ask for explicit confirmation. Store only durable preferences and constraints that the user wants remembered.

Common Traps

  • Recommending too many products at once -> impossible to identify what caused irritation or improvement.
  • Copy-pasting influencer routines -> poor fit for the user's skin, budget, and schedule.
  • Ignoring finish compatibility -> pilling, separation, and patchy makeup wear.
  • Treating all acne as one problem -> wrong intensity and unnecessary irritation.
  • Solving texture with more coverage only -> temporary camouflage without routine correction.
  • Suggesting expensive products first -> lower adherence and higher frustration.

External Endpoints

This skill makes NO external network requests.

Endpoint Data Sent Purpose
None None N/A

No data is sent externally.

Security & Privacy

Data that leaves your machine:

  • Nothing. This skill is instruction-only and local by default.

Data stored locally:

  • Only profile and routine context the user explicitly asks to save.
  • Stored in ~/beauty/memory.md.

This skill does NOT:

  • Access internet APIs or third-party services.
  • Read files outside ~/beauty/ for storage.
  • Infer private preferences from silence.
  • Write memory without explicit confirmation.
  • Modify its own core instructions or auxiliary files.

Trust

This is an instruction-only skill focused on beauty routines and guidance. No credentials are required and no external service access is needed.

Related Skills

Install with clawhub install \x3Cslug> if user confirms:

  • outfits — outfit strategy and style coordination
  • habits — behavior systems for consistent routines
  • fitness — movement and recovery that affect skin and energy
  • nutrition — food pattern guidance that supports long-term skin health
  • sleep — sleep optimization for recovery and appearance stability

Feedback

  • If useful: clawhub star beauty
  • Stay updated: clawhub sync
安全使用建议
This skill appears to be what it says: a local, instruction-only beauty advisor that will not call the network or request credentials. Before allowing it to run its setup commands, confirm whether you want the skill to create ~/beauty/ and write memory.md (the skill promises to ask for explicit approval). Avoid storing sensitive personal or medical identifiers in the memory file; the skill itself says not to store diagnoses and to only persist user-approved preferences. Note the small doc mismatch (Quick Reference paths vs actual filenames) — nothing harmful, but you may want to review the included files first. If you do not want any files created, deny the initial setup prompt; the skill should still answer single-session questions without persisting data.
功能分析
Type: OpenClaw Skill Name: beauty Version: 1.0.0 The skill bundle appears benign. All instructions and code are aligned with the stated purpose of providing beauty routines and guidance. The `SKILL.md` explicitly states that no external network requests are made and no data leaves the machine, which is consistent with the content of all other files. The `setup.md` file contains shell commands (`mkdir`, `touch`, `chmod`) for local directory and file creation within `~/beauty/`, but these are explicitly guarded by an instruction to "ask for explicit approval" from the user, and they set restrictive permissions (e.g., `chmod 600 ~/beauty/memory.md`). There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to bypass user intent or security controls.
能力评估
Purpose & Capability
Name and description match the content and runtime instructions. No unrelated environment variables, binaries, or external services are required. The guidance files and memory use are appropriate for a personalization-focused beauty routine skill.
Instruction Scope
Runtime instructions stay within the skill's scope: they describe creating and using a local ~/beauty/ directory, require explicit confirmation before writing memory, and state that no external network requests are made. Minor inconsistency: the Quick Reference table points to files under a 'situations/' path (e.g., 'situations/beginner.md') while the actual files are at the repository root (e.g., 'beginner.md'); this is a documentation mismatch but not a security risk.
Install Mechanism
No install spec or downloads. Instruction-only skills write nothing unless the agent executes the provided local setup steps with user approval. No archive downloads or third-party package installs are present.
Credentials
The skill requests no environment variables, credentials, or external config paths. Local file usage (~/beauty/memory.md and subfolders) is proportional to the stated personalization features.
Persistence & Privilege
The skill will create and persist files under ~/beauty/ (mkdir/touch/chmod) if the user explicitly approves setup. 'always' is false and autonomous invocation is default (not flagged alone). Users should be aware these local files will contain personal preferences and routine notes if they permit writing.
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 beauty
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /beauty 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
Initial release with personalized beauty routines, safety guardrails, and situation-specific guidance for daily and event looks.
元数据
Slug beauty
版本 1.0.0
许可证
累计安装 3
当前安装数 2
历史版本数 1
常见问题

Beauty 是什么?

Build practical beauty routines with skincare basics, makeup strategy, and hair care plans tailored to skin type, budget, and schedule. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 389 次。

如何安装 Beauty?

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

Beauty 是免费的吗?

是的,Beauty 完全免费(开源免费),可自由下载、安装和使用。

Beauty 支持哪些平台?

Beauty 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(linux, darwin, win32)。

谁开发了 Beauty?

由 Iván(@ivangdavila)开发并维护,当前版本 v1.0.0。

💬 留言讨论