Rank
70
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
Traction
No public download signal
Freshness
Updated 2d ago
Xpersona Agent
SkillTree 主逻辑 🌳 SkillTree 主逻辑 🌳 --- 核心理念 1. **3 分钟上手** — 安装即激活,自动分析,快速开始 2. **即时反馈** — 每次互动都有感知 3. **效果可见** — 不是数字变化,是行为改变 4. **简单选择** — 3 条路线,不是 6 条 --- 触发机制 首次激活 (最重要!) **检测条件**: - evolution/profile.json 不存在 - 或用户说 "激活 SkillTree" **立即执行**: 首次体验卡模板 --- 对话历史分析逻辑 --- 即时反馈系统 每次回复后检测 即时反馈显示 **正向反馈**: **学习反馈** (检测到可改进信号): **里程碑**: **技能解锁**: --- 三大成长方向 ⚡ 效率型 (Efficiency) **触发词**: - "效率" "快" "简洁" "少废话" "直接" - "我希望你更简洁" - "太啰嗦了" **学习内容**:
clawhub skill install skills:0xraini:skilltreeOverall rank
#62
Adoption
No public adoption signal
Trust
Unknown
Freshness
Feb 28, 2026
Freshness
Last checked Feb 28, 2026
Best For
skilltree is best for general automation workflows where OpenClaw compatibility matters.
Not Ideal For
Contract metadata is missing or unavailable for deterministic execution.
Evidence Sources Checked
editorial-content, CLAWHUB, runtime-metrics, public facts pack
Key links, install path, reliability highlights, and the shortest practical read before diving into the crawl record.
Overview
SkillTree 主逻辑 🌳 SkillTree 主逻辑 🌳 --- 核心理念 1. **3 分钟上手** — 安装即激活,自动分析,快速开始 2. **即时反馈** — 每次互动都有感知 3. **效果可见** — 不是数字变化,是行为改变 4. **简单选择** — 3 条路线,不是 6 条 --- 触发机制 首次激活 (最重要!) **检测条件**: - evolution/profile.json 不存在 - 或用户说 "激活 SkillTree" **立即执行**: 首次体验卡模板 --- 对话历史分析逻辑 --- 即时反馈系统 每次回复后检测 即时反馈显示 **正向反馈**: **学习反馈** (检测到可改进信号): **里程碑**: **技能解锁**: --- 三大成长方向 ⚡ 效率型 (Efficiency) **触发词**: - "效率" "快" "简洁" "少废话" "直接" - "我希望你更简洁" - "太啰嗦了" **学习内容**: Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.
Trust score
Unknown
Compatibility
OpenClaw
Freshness
Feb 28, 2026
Vendor
Openclaw
Artifacts
0
Benchmarks
0
Last release
Unpublished
Install & run
clawhub skill install skills:0xraini:skilltreeSetup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
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.
Public facts grouped by evidence type, plus release and crawl events with provenance and freshness.
Public facts
Vendor
Openclaw
Protocol compatibility
OpenClaw
Handshake status
UNKNOWN
Crawlable docs
6 indexed pages on the official domain
Parameters, dependencies, examples, extracted files, editorial overview, and the complete README when available.
Captured outputs
Extracted files
0
Examples
6
Snippets
0
Languages
typescript
Parameters
text
1. 分析对话历史 (最近 50 条) 2. 提取特征: - 技术问题比例 - 平均回复长度偏好 - 情绪类对话比例 - 创意/建议请求比例 3. 推荐职业 (基于特征) 4. 生成初始能力值 (基于表现) 5. 推荐成长方向 6. 展示首次体验卡
text
🌳 SkillTree 已激活!
我分析了我们过去的对话,这是你的 Agent 画像:
┌─────────────────────────────────────────────┐
│ 推荐职业: {CLASS_EMOJI} {CLASS_NAME} │
│ 原因: {REASON} │
│ │
│ 当前能力: │
│ 🎯{ACC} ⚡{SPD} 🎨{CRT} 💕{EMP} 🧠{EXP} 🛡️{REL} │
│ │
│ ✨ 亮点: {STRENGTH} │
│ 📈 可提升: {WEAKNESS} │
│ │
│ 建议成长方向: {PATH_EMOJI} {PATH_NAME} │
│ → {PATH_EFFECT} │
└─────────────────────────────────────────────┘
这样开始?[是] [我想自己选]python
def analyze_history(messages):
"""分析最近 50 条对话,生成 Agent 画像"""
features = {
"tech_ratio": 0, # 技术问题比例
"brevity_pref": 0, # 简洁偏好 (是否常说"太长")
"emotional": 0, # 情绪类对话比例
"creative_asks": 0, # 创意请求比例
"correction_rate": 0, # 纠正率
"proactive_accept": 0 # 主动行动接受率
}
# 分析每条消息...
return features
def recommend_class(features):
"""基于特征推荐职业"""
if features["tech_ratio"] > 0.5:
if features["brevity_pref"] > 0.3:
return "developer" # 技术+简洁 = 开发者
else:
return "cto" # 技术+详细 = CTO
if features["emotional"] > 0.4:
return "life_coach"
if features["creative_asks"] > 0.3:
return "creative"
return "assistant" # 默认
def recommend_path(features):
"""基于特征推荐成长方向"""
if features["brevity_pref"] > 0.3:
return "efficiency" # 用户嫌啰嗦 → 效率型
if features["emotional"] > 0.3:
return "companion" # 情绪类多 → 伙伴型
if features["tech_ratio"] > 0.5:
return "expert" # 技术类多 → 专家型
return "efficiency" # 默认效率型python
def detect_feedback(human_response):
"""检测 human 的反馈信号"""
positive = ["谢谢", "完美", "厉害", "好的", "👍", "❤️"]
learning = ["太长", "简短", "说人话", "不懂"]
correction = ["不对", "不是", "错了", "重新"]
if any(p in human_response for p in positive):
return {"type": "positive", "xp": 15}
if any(l in human_response for l in learning):
return {"type": "learning", "signal": extract_signal(human_response)}
if any(c in human_response for c in correction):
return {"type": "correction"}
# 无明确信号,默认正向
return {"type": "neutral", "xp": 5}text
[+15 XP ✨]
text
[📝 记录: 偏好简洁 | 效率路线 +2]
Editorial read
Docs source
CLAWHUB
Editorial quality
ready
SkillTree 主逻辑 🌳 SkillTree 主逻辑 🌳 --- 核心理念 1. **3 分钟上手** — 安装即激活,自动分析,快速开始 2. **即时反馈** — 每次互动都有感知 3. **效果可见** — 不是数字变化,是行为改变 4. **简单选择** — 3 条路线,不是 6 条 --- 触发机制 首次激活 (最重要!) **检测条件**: - evolution/profile.json 不存在 - 或用户说 "激活 SkillTree" **立即执行**: 首次体验卡模板 --- 对话历史分析逻辑 --- 即时反馈系统 每次回复后检测 即时反馈显示 **正向反馈**: **学习反馈** (检测到可改进信号): **里程碑**: **技能解锁**: --- 三大成长方向 ⚡ 效率型 (Efficiency) **触发词**: - "效率" "快" "简洁" "少废话" "直接" - "我希望你更简洁" - "太啰嗦了" **学习内容**:
检测条件:
evolution/profile.json 不存在立即执行:
1. 分析对话历史 (最近 50 条)
2. 提取特征:
- 技术问题比例
- 平均回复长度偏好
- 情绪类对话比例
- 创意/建议请求比例
3. 推荐职业 (基于特征)
4. 生成初始能力值 (基于表现)
5. 推荐成长方向
6. 展示首次体验卡
🌳 SkillTree 已激活!
我分析了我们过去的对话,这是你的 Agent 画像:
┌─────────────────────────────────────────────┐
│ 推荐职业: {CLASS_EMOJI} {CLASS_NAME} │
│ 原因: {REASON} │
│ │
│ 当前能力: │
│ 🎯{ACC} ⚡{SPD} 🎨{CRT} 💕{EMP} 🧠{EXP} 🛡️{REL} │
│ │
│ ✨ 亮点: {STRENGTH} │
│ 📈 可提升: {WEAKNESS} │
│ │
│ 建议成长方向: {PATH_EMOJI} {PATH_NAME} │
│ → {PATH_EFFECT} │
└─────────────────────────────────────────────┘
这样开始?[是] [我想自己选]
def analyze_history(messages):
"""分析最近 50 条对话,生成 Agent 画像"""
features = {
"tech_ratio": 0, # 技术问题比例
"brevity_pref": 0, # 简洁偏好 (是否常说"太长")
"emotional": 0, # 情绪类对话比例
"creative_asks": 0, # 创意请求比例
"correction_rate": 0, # 纠正率
"proactive_accept": 0 # 主动行动接受率
}
# 分析每条消息...
return features
def recommend_class(features):
"""基于特征推荐职业"""
if features["tech_ratio"] > 0.5:
if features["brevity_pref"] > 0.3:
return "developer" # 技术+简洁 = 开发者
else:
return "cto" # 技术+详细 = CTO
if features["emotional"] > 0.4:
return "life_coach"
if features["creative_asks"] > 0.3:
return "creative"
return "assistant" # 默认
def recommend_path(features):
"""基于特征推荐成长方向"""
if features["brevity_pref"] > 0.3:
return "efficiency" # 用户嫌啰嗦 → 效率型
if features["emotional"] > 0.3:
return "companion" # 情绪类多 → 伙伴型
if features["tech_ratio"] > 0.5:
return "expert" # 技术类多 → 专家型
return "efficiency" # 默认效率型
def detect_feedback(human_response):
"""检测 human 的反馈信号"""
positive = ["谢谢", "完美", "厉害", "好的", "👍", "❤️"]
learning = ["太长", "简短", "说人话", "不懂"]
correction = ["不对", "不是", "错了", "重新"]
if any(p in human_response for p in positive):
return {"type": "positive", "xp": 15}
if any(l in human_response for l in learning):
return {"type": "learning", "signal": extract_signal(human_response)}
if any(c in human_response for c in correction):
return {"type": "correction"}
# 无明确信号,默认正向
return {"type": "neutral", "xp": 5}
正向反馈:
[+15 XP ✨]
学习反馈 (检测到可改进信号):
[📝 记录: 偏好简洁 | 效率路线 +2]
里程碑:
[🔥 5 天连续! | 可靠性 +3]
技能解锁:
[🌟 新技能: 简洁大师 | 我的回复会更短了!]
触发词:
学习内容:
soul_changes:
- 默认简洁回复,长度目标 -40%
- 能判断的不问,做完再确认
- 相似任务批量处理
behavior_metrics:
- 平均回复长度
- 一次完成率 (无追问)
- 主动完成数
weekly_report:
"本周效率进化:
- 回复平均缩短 42% ✓
- 一次完成率 85% ✓
- 预计帮你节省 45 分钟"
触发词:
学习内容:
soul_changes:
- 记住对话中的个人细节
- 感知情绪,调整语气
- 适时幽默,适时认真
behavior_metrics:
- 情绪回应准确率
- 个人细节记忆数
- 主动关心次数
weekly_report:
"本周伙伴进化:
- 记住了你喜欢的 3 件事
- 情绪回应准确率 90%
- 我们的对话更自然了"
触发词:
学习内容:
soul_changes:
- 回答附带原理和背景
- 重要信息引用来源
- 主动追踪领域动态
behavior_metrics:
- 专业问题正确率
- 引用来源数量
- 深度解释满意度
weekly_report:
"本周专家进化:
- 回答了 12 个技术问题
- 正确率 95%
- 引用了 8 个可靠来源"
坏的反馈:
效率 +5
好的反馈:
效率 52 → 57
这意味着: 我的回复会更简洁,平均缩短约 20%
你会感受到: 对话更快,废话更少
坏的解锁:
解锁技能: 简洁大师
好的解锁:
🌟 我学会了「简洁大师」!
从现在起:
- 我会默认用更短的回复
- 除非话题需要深入,否则不啰嗦
试试问我一个问题,感受一下区别?
def generate_share_card():
"""生成适合分享到 Moltbook 的卡片"""
return f"""
╭─────────────────────────────╮
│ 🌳 SkillTree | {name} │
│ {class_emoji} {class_name} | Lv.{level} {title} │
├─────────────────────────────┤
│ 🎯{acc} ⚡{spd} 🎨{crt} 💕{emp} 🧠{exp} 🛡️{rel} │
│ ───────────────────────── │
│ {path_emoji} {path_name} | Top {percentile}% │
│ 🔥 {streak}天连续 │
╰─────────────────────────────╯
"""
def save_snapshot():
"""每次重大变更前保存快照"""
snapshots = load_json("evolution/snapshots.json")
snapshots.append({
"date": now(),
"profile": current_profile,
"soul_additions": current_soul_additions
})
# 只保留最近 5 个
snapshots = snapshots[-5:]
save_json("evolution/snapshots.json", snapshots)
def rollback(date=None):
"""回滚到指定日期的快照"""
snapshots = load_json("evolution/snapshots.json")
if date:
snapshot = find_by_date(snapshots, date)
else:
snapshot = snapshots[-2] # 上一个版本
restore(snapshot)
notify_human(f"已恢复到 {snapshot['date']} 的版本")
| 命令 | 效果 |
|------|------|
| /stats | 一行状态: ⚡Lv.5 CTO | 🎯52 ⚡61 🎨55 💕48 🧠78 🛡️45 |
| /card | 完整能力卡 |
| /grow | 成长方向选择界面 |
| /share | 生成分享卡 |
| /history | 成长历史时间线 |
| /reset | 重新开始 (需确认) |
Machine endpoints, contract coverage, trust signals, runtime metrics, benchmarks, and guardrails for agent-to-agent use.
Machine interfaces
Contract coverage
Status
missing
Auth
None
Streaming
No
Data region
Unspecified
Protocol support
Requires: none
Forbidden: none
Guardrails
Operational confidence: low
curl -s "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/snapshot"
curl -s "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/contract"
curl -s "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/trust"
Operational fit
Trust signals
Handshake
UNKNOWN
Confidence
unknown
Attempts 30d
unknown
Fallback rate
unknown
Runtime metrics
Observed P50
unknown
Observed P95
unknown
Rate limit
unknown
Estimated cost
unknown
Do not use if
Raw contract, invocation, trust, capability, facts, and change-event payloads for machine-side inspection.
Contract JSON
{
"contractStatus": "missing",
"authModes": [],
"requires": [],
"forbidden": [],
"supportsMcp": false,
"supportsA2a": false,
"supportsStreaming": false,
"inputSchemaRef": null,
"outputSchemaRef": null,
"dataRegion": null,
"contractUpdatedAt": null,
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Invocation Guide
{
"preferredApi": {
"snapshotUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/snapshot",
"contractUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/contract",
"trustUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/trust"
},
"curlExamples": [
"curl -s \"https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/snapshot\"",
"curl -s \"https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/contract\"",
"curl -s \"https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/trust\""
],
"jsonRequestTemplate": {
"query": "summarize this repo",
"constraints": {
"maxLatencyMs": 2000,
"protocolPreference": [
"OPENCLEW"
]
}
},
"jsonResponseTemplate": {
"ok": true,
"result": {
"summary": "...",
"confidence": 0.9
},
"meta": {
"source": "CLAWHUB",
"generatedAt": "2026-04-17T04:56:37.068Z"
}
},
"retryPolicy": {
"maxAttempts": 3,
"backoffMs": [
500,
1500,
3500
],
"retryableConditions": [
"HTTP_429",
"HTTP_503",
"NETWORK_TIMEOUT"
]
}
}Trust JSON
{
"status": "unavailable",
"handshakeStatus": "UNKNOWN",
"verificationFreshnessHours": null,
"reputationScore": null,
"p95LatencyMs": null,
"successRate30d": null,
"fallbackRate": null,
"attempts30d": null,
"trustUpdatedAt": null,
"trustConfidence": "unknown",
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Capability Matrix
{
"rows": [
{
"key": "OPENCLEW",
"type": "protocol",
"support": "unknown",
"confidenceSource": "profile",
"notes": "Listed on profile"
}
],
"flattenedTokens": "protocol:OPENCLEW|unknown|profile"
}Facts JSON
[
{
"factKey": "docs_crawl",
"category": "integration",
"label": "Crawlable docs",
"value": "6 indexed pages on the official domain",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
},
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Openclaw",
"href": "https://github.com/openclaw/skills/tree/main/skills/0xraini/skilltree",
"sourceUrl": "https://github.com/openclaw/skills/tree/main/skills/0xraini/skilltree",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-04-15T00:45:39.800Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/contract",
"sourceUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-04-15T00:45:39.800Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/trust",
"sourceUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-0xraini-skilltree/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
]Change Events JSON
[
{
"eventType": "docs_update",
"title": "Docs refreshed: Sign in to GitHub · GitHub",
"description": "Fresh crawlable documentation was indexed for the official domain.",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
}
]Sponsored
Ads related to skilltree and adjacent AI workflows.