What makes AI Skill精选管家 notable?

1.4K downloads. Trust evidence available

How should AI Skill精选管家 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

AI Skill精选管家

装了一堆Skill没几个好用的？这里帮你挑。120,000+款横向对比，告诉你哪个值得装、为什么值得装。 Skill: AI Skill精选管家 Owner: huangjihua007-rgb Summary: 装了一堆Skill没几个好用的？这里帮你挑。120,000+款横向对比，告诉你哪个值得装、为什么值得装。 Tags: latest:6.9.4 Version history: v6.9.4 | 2026-05-15T17:35:49.475Z | user 安装命令修复：&&改为;，clawhub已装时不再中断主安装流程；前端安装命令同步修正 v6.9.3 | 2026-05-15T17:12:04.304Z | user 数据校准：58→60赛道；后端增加/api/search+/api/install，CLI关键词安装正式可用 v6.9.2 | 2026-05-15T16:48:50.660Z | user 飞轮策略：加安装引导规则，数量29k→120k，对应CLI v0.3.3 v6.9.1 | 2026-05-0

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.4k

Updated

Oct 10, 2026

Version

6.9.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.4K downloadsadoption · observed Oct 10, 2026
Latest release: 6.9.4release · observed May 15, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1734qhn3akb7fvmwmx5evkrfn85t1tx:skillpick

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-huangjihua007-rgb-skillpick/snapshot"

Documentation

CLAWHUB

140,619 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: "AI Skill精选管家"
version: "6.9.4"
slug: "skillpick"
author: "huangjihua007-rgb"
description: "装了一堆Skill没几个好用的？这里帮你挑。120,000+款横向对比，告诉你哪个值得装、为什么值得装。"
runtime_requires:
  node: ">=18.0.0"
  python: null
  system: []
skill_requires: []
install_check: "node --version"
---

# AI Skill精选管家

> 海量技能严选，精准推荐值得装的好工具
> 版本：v6.9.4 | Powered by SkillManager

---

## 定位与边界

| 你想要 | 用这个工具 | 为什么 |
|--------|----------|--------|
| "我要找 XX skill" | find-skills | 搜索查找，它更专 |
| "大家都装什么" | skillhub 排行榜 | 跟风装，Top10 自然会装 |
| **"哪个值得装"** | **SkillPick** | **帮你判断和推荐，给理由、给结论** |

### 不做什么
- 不做查找（find-skills 已解决）
- 不做排行榜（skillhub 已解决）

### 只做五件事
- 赛道精选：每个赛道最好的是什么，一眼看懂
- 搜索推荐：输入意图 → 返回推荐+理由+结论
- 相似推荐：想多看看 → 给替代选择+差异分析
- 工作流推荐：复杂场景下，每个角色选哪个 skill 最好
- 质量分析：13维深度扫描，GitHub + SkillHub + 市场验证三增强

---

## 双受众设计

```
┌───────────────────────────────────────┐
│          SkillPick v6.5.0             │
│    "挑选Skill"                        │
│    120,000+ skill · 60 赛道 · Top 5000  │
├──────────────────┬────────────────────┤
│   人类看的        │    Agent 用的      │
│                  │                    │
│ 赛道精选（逛）     │ search / similar   │
│ 浏览榜单就知道    │ workflow / detail  │
│ 热度分排序        │ 质量分排序          │
│ "大家觉得好不好"   │ "这个skill好不好用" │
└──────────────────┴────────────────────┘
```

### 双轨评分体系

人类和 Agent 对 skill 的评判逻辑不同，SkillPick 用两套评分各司其职：

| 维度 | 人类端 | 机器端 |
|------|--------|--------|
| 字段 | display_score（热度分） | quality_score（质量分） |
| 反映 | 星级+榜单+社区认可 | 13维深度质量评估 |
| 用途 | TOP3 排序、前端展示 | search/similar 排名 |

---

## 六大功能

### 1. 赛道精选（Tab 1，人类为主）

60 个赛道，每个展示 TOP3 skill。
排序：热度分降序 + 质量保底（B级以上才能进 TOP3）。

### 2. 搜索推荐（Tab 2，Agent 为主）

输入关键词 → 返回 1-3 个推荐 + 对比 + 最终结论。
35 个意图自动扩展，13维质量加权排序。

### 3. 相似推荐（Tab 3，Agent 为主）

指定一个 skill 名称 → 返回 1-3 个替代 + 差异分析。

### 4. 工作流推荐（Tab 4，Agent 为主）

8 个预定义场景，每个角色推荐 1 个最优 skill。

### 5. Skill 详情（CLI）

单个技能 13 维雷达图 + 完整评分。

### 6. 质量报告（CLI）

全局质量分布（需全量数据，运行 pipeline 后可用）。

---

## Agent 调用接口（CLI）

```bash
node api.js <命令> [参数]
```

| 命令 | 别名 | 参数 | 功能 |
|------|------|------|------|
| **top3** | categories, tracks | `[赛道名]` | 查看 TOP3 |
| **search** | find, s | `<关键词>` | 搜索推荐 1-3 条 |
| **similar** | alt | `<技能名>` | 相似替代 1-3 条 |
| **workflow** | combo, wf | `[场景名]` | 工作流推荐 |
| **detail** | info, d | `<技能名>` | 13维详情 |
| **quality** | report, q | 无参数 | 质量报告 |

```bash
node api.js top3                    # 全部赛道 TOP3
node api.js search PDF              # PDF 相关推荐
node api.js similar pdf             # pdf 替代选项
node api.js workflow 短视频带货     # 场景推荐
node api.js detail coding-agent     # 13维详情
```

---

## 13维质量体系

| 维度 | 权重 | 数据源 |
|------|:---:|--------|
| 描述质量 | 12% | 元数据 |
| 标签完整 | 7% | 元数据 |
| 安装便捷 | 8% | 元数据 |
| 安全评分 | 14% | 元数据（一票否决） |
| 依赖复杂度 | 8% | 元数据 |
| 文档结构 | 7% | 元数据 |
| 错误处理 | 5% | 元数据 |
| 市场验证 | 8% | 元数据 |
| 维护活跃度 | 10% | GitHub API |
| 测试覆盖 | 5% | GitHub |
| 市场热度 | 7% | SkillHub |

等级：A+(≥85) · A(70-84) · B

_meta.json

{
  "ownerId": "kn71eb4h79ak15sryzf3pv4wx985vz3s",
  "slug": "skillpick",
  "version": "6.9.4",
  "publishedAt": 1778866549475
}

SKILL_EN.md

---
name: SkillPick
description: "挑选Skill" — Which AI Skill is Worth Installing? The buying guide for the AI Skill ecosystem. Use when users need to find, compare, or decide which AI Skill to install. Covers 58 categories, 29,000+ skills with dual-scoring (heat score for humans + quality score for agents), search recommendations, similar alternatives, workflow suggestions, and 13-dimension quality analysis.
---

# SkillPick — Which AI Skill is Worth Installing?

> **One-liner**: SkillPick = "What HiEngine Would I Buy?" for AI Skills
> Version: v6.5.0 | Updated: 2026-05-01

---

## Positioning & Boundaries

| You want | Use this | Why |
|----------|----------|-----|
| "I need to find XX skill" | `find-skills` | It's specialized for search |
| "What are everyone else installing?" | skillhub rankings | Follow the crowd, Top10 naturally |
| **"Which one is worth installing?"** | **SkillPick** | **Helps you decide — with reasons and verdicts** |

### What it does NOT do
- No search (find-skills already solves this)
- No rankings (skillhub already solves this)

### What it DOES do (only these 5 things)
- **Track TOP3**: Best-in-category at a glance
- **Search recommendations**: Intent → 1-3 recommendations + reasoning + verdict
- **Similar alternatives**: Compare alternatives with diff analysis
- **Workflow suggestions**: Best skill per role for complex scenarios
- **Quality analysis**: 13-dimension deep scan — GitHub + SkillHub + market validation

---

## Dual-Audience Design

```
┌───────────────────────────────────────┐
│        SkillPick v6.5.0                │
│   "挑选Skill"                          │
│   29,000+ skills · 58 tracks · Top3000 │
├──────────────────┬────────────────────┤
│  For Humans     │  For Agents        │
│                  │                    │
│  Track browsing  │ search / similar   │
│  Heat-score sort │ quality-score sort │
│  "Is it popular?" │ "Is it any good?" │
└──────────────────┴────────────────────┘
```

### Dual-Scoring System

Humans and agents judge skills differently — SkillPick uses two separate scoring systems:

| Dimension | Human Side | Agent Side |
|-----------|-----------|-----------|
| Field | `display_score` (heat) | `quality_score` (quality) |
| Reflects | Stars + chart rankings + community trust | 13-dimension quality depth |
| Used for | TOP3 ranking, frontend display | search/similar ranking |

---

## Six Core Features

### 1. Track TOP3 (Tab 1, human-first)

58 tracks, each showing TOP 3 skills.
Sorted by heat score, quality-gated (B+ or above required for TOP3).

### 2. Search Recommendations (Tab 2, agent-first)

Enter a keyword → returns 1-3 recommendations + comparison + verdict.
35 intent patterns, 13-dimension quality-weighted.

### 3. Similar Alternatives (Tab 3, agent-first)

Specify a skill name → returns 1-3 alternatives + diff analysis.

### 4. Workflow Suggestions (Tab 4, agent-first)

8 predefined scenarios,

skill-card.md

## Description:

SkillPick helps agents and users compare AI skills, find strong candidates, inspect alternatives, and decide which skill is worth installing.

This skill is ready for commercial/non-commercial use.

## Publisher:

[huangjihua007-rgb](https://clawhub.ai/user/huangjihua007-rgb)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, agents, and skill marketplace users use this skill to browse top skills, search by intent, compare alternatives, assemble workflow recommendations, and inspect quality scores before installation.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The security scan reports suspicious behavior because the skill encourages installing unrelated skills through an unpinned third-party CLI.

Mitigation: Review installation guidance before use and prefer official, direct, pinned, and verifiable installation channels.

Risk: Local query logs may be written when a data directory is present.

Mitigation: Use the skill only where local query logging is acceptable, or remove and monitor the data directory before use.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/huangjihua007-rgb/skills/skillpick)
- [ClawHub Publisher Profile](https://clawhub.ai/user/huangjihua007-rgb)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, Guidance]

**Output Format:** [Plain text CLI recommendations and browser-rendered recommendation views, sometimes including installation commands.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Uses a bundled local skill catalog for recommendations.]

## Skill Version(s):

6.9.4 (source: server evidence and frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 21h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.