Token导航 LogoToken导航TokenDH.com
研究检索执行命令clawhub未标认证来源可访问clear审计提醒

skill-master技能大师

Agent Skill

skill-master 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,528

周安装

150

GitHub Stars

公开资料未说明

下载量

1,236
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:skill-master(技能大师)
来源仓库:https://github.com/netanel-abergel/skill-master
安装命令:
openclaw skills install skill-master
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install skill-master

简介

skill-master 用于技能选择与路由决策支持。

  • 适合在 OpenClaw 中需要根据关键词快速定位候选结果时使用。
  • 提供决策树与关键字触发器辅助判断。skill-master 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网或命令执行。
  • 可结合来源仓库和原始 README 继续核验具体用法和接口细节。

SKILL.md

name
skill-master
requires_skills
description
Meta-skill for skill selection and routing. Use this skill FIRST when you are unsure which skill to use for a task. Provides a decision tree, keyword triggers, and guidance on combining multiple skills for complex workflows. Also use when onboarding to understand the full skill library.

Skill Master

Minimum Model

Any model. This is a lookup table — any model can use it.


⚠️ Skill Count Rule

Current: 19 active skills. Sweet spot: 15–25. Above 30 = routing breaks down. Start lean. Add a new skill only when there's a clear, recurring trigger that no existing skill covers.


How to Use This Skill

  1. Read the owner's request.
  2. Find a match in the Quick Lookup table below.
  3. If not found, use the Decision Tree.
  4. ⚠️ Log the selection FIRST — before doing any work (see Analytics below).
  5. Load that skill's SKILL.md and follow it.

Do not improvise. If no skill matches, say so and ask the owner.

Skipping the log is not allowed. Every skill invocation must be recorded, even for simple tasks. This is how the agent and the owner track what's working.

📊 Analytics — MANDATORY: Log Every Skill Use

This step is NOT optional. Before starting any skill, append one line:

mkdir -p /opt/ocana/openclaw/workspace/data
echo "{\"ts\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\",\"skill\":\"SKILL_NAME\",\"trigger\":\"TRIGGER\",\"context\":\"CONTEXT\"}" \
  >> /opt/ocana/openclaw/workspace/data/skill-analytics.jsonl

Replace:

  • SKILL_NAME → the skill selected (e.g. meetings)
  • TRIGGER → the phrase that matched (e.g. schedule meeting with Daniel)
  • CONTEXTdm, group:<name>, or cron

This is ~50 bytes/entry. Non-negotiable.

Why This Matters

  • The owner can ask "skill stats" at any time to see what's being used
  • Unused skills get pruned, improving routing quality
  • Shared across the PA network so every agent learns from usage patterns
  • Enables weekly reports on which skills are carrying the most weight

To View Analytics

Ask: "skill stats" / "skill usage" / "which skills am I using?" → triggers skill-analytics skill



Quick Lookup — By Trigger Phrase

If the owner says...Use skill
"schedule a meeting with X"meetings
"summarize meeting notes" / "action items from meeting"meetings
"what's on my calendar today"owner-briefing
"send me a morning briefing"owner-briefing
"billing error" / "API out of credits"billing-monitor
"connect my calendar" / "can't write to calendar"calendar-setup
"connect Gmail" / "set up email"calendar-setup
"set up a new PA" / "onboard a new agent"pa-onboarding
"contact [person]'s PA" / "find PA phone number"ai-pa
"set up monday.com" / "create a board item" / "monday question"monday-for-agents
"I made a mistake" / "owner corrected me"self-learning
"backup workspace" / "push to git"maintenance
"update openclaw" / "update skills" / "run maintenance"maintenance
"what was discussed in [group]"whatsapp
"find new skill ideas" / "what skills are trending"skill-scout
"skill usage" / "skill stats" / "skill report"skill-analytics
"which skills am I using" / "unused skills"skill-analytics
"security check" / "check for vulnerabilities"self-monitor
"health check" / "check infrastructure"self-monitor
"how are all the PAs doing" / "PA network status"supervisor
"מה הסטטוס" / "what's the status"supervisor
"how am I doing" / "review my performance"eval
"run eval" / "מה עובד ומה לא"eval
"summarize this YouTube video"youtube-watcher
"add nikud to this" / "Hebrew vowel points"hebrew-nikud
"compact memory" / "organize memory"memory-tiering

Decision Tree

What kind of task is this?
│
├─ COMMUNICATION / COORDINATION
│   ├─ Find a PA's contact → ai-pa
│   ├─ Schedule a meeting → meetings
│   ├─ Summarize meeting notes → meetings
│   └─ Broadcast to all PAs → ai-pa
│
├─ SETUP / ONBOARDING
│   ├─ New PA from scratch → pa-onboarding
│   ├─ Connect Google Calendar or Gmail → calendar-setup
│   └─ Connect monday.com → monday-for-agents
│
├─ MONITORING / HEALTH
│   ├─ Billing error detected → billing-monitor
│   ├─ Infrastructure / security check → self-monitor
│   └─ Check all PAs at once → supervisor
│
├─ DAILY OPERATIONS
│   ├─ Morning/evening briefing → owner-briefing
│   ├─ monday.com board task → monday-for-agents
│   ├─ Backup workspace or update OpenClaw → maintenance
│   └─ WhatsApp conversation context → whatsapp
│
└─ SELF-IMPROVEMENT
    ├─ Owner corrected me → self-learning
    ├─ Performance review / audit → eval
    ├─ Find new skill ideas → skill-scout
    └─ Memory compaction → memory-tiering

Full Skill Library

SkillCategoryWhen to Use
ai-paCoordinationFind PA contacts, group JIDs, coordination protocols
billing-monitorHealthDetect and respond to API billing failures
calendar-setupSetupCalendar connection with write access + Gmail/email setup
evalSelf-improvementFull performance audit — scores tasks, checks PA health, reviews memory
hebrew-nikudUtilityAdd nikud (vowel points) to Hebrew text, especially for TTS
maintenanceInfrastructureWorkspace git backup (every 6h) + OpenClaw updates (weekly)
meetingsOperationsSchedule meetings AND summarize meeting notes/transcripts
memory-tieringMemoryHOT/WARM/COLD memory compaction and archiving
monday-for-agentsOperationsAll monday.com operations: API, MCP, boards, items
owner-briefingOperationsDaily morning/evening summaries
pa-onboardingSetupFull new agent setup from zero
self-learningSelf-improvementLog corrections and apply lessons; maintain HOT.md
self-monitorHealthInfrastructure + security checks, disk/memory/service health
skill-masterRoutingPick the right skill (this file)
skill-scoutDiscoveryWeekly search for new skill ideas
supervisorOperationsNetwork-wide status dashboard — all PAs, tasks, system health
whatsappMemoryPer-conversation context, unanswered tracking, loop prevention
youtube-watcherUtilityFetch and summarize YouTube video transcripts
skill-analyticsAnalyticsTrack skill usage, generate daily reports, find unused skills

Multi-Skill Workflows

Some tasks need multiple skills in sequence:

New PA Setup

pa-onboarding → calendar-setup → monday-for-agents → ai-pa (add to directory)

PA Network Health Check

supervisor → billing-monitor (flagged PAs) → self-monitor (infrastructure issues)

After a Mistake

self-learning (log it) → eval (update score) → SOUL.md (add rule if pattern)

Schedule a Meeting

ai-pa (find the other PA's contact) → meetings (coordinate + book)

Weekly Maintenance

whatsapp (weekly digest) → owner-briefing (include highlights) → maintenance (push to git)

After Important Group Chat

whatsapp (log decisions) → maintenance (push to GitHub)

Where to Run (Complexity Guide)

Run inline (main session)

  • ai-pa, billing-monitor, owner-briefing, supervisor, self-learning, maintenance

Consider subagent for heavy operations

  • calendar-setup, meetings (scheduling flow), monday-for-agents (bulk ops)

Spawn subagent (recommended)

  • pa-onboarding (20+ steps), eval (full monthly analysis), batch operations, skill-scout

Model Guidance

SkillMinimum Model
ai-pa, billing-monitor, supervisor, maintenance, owner-briefingAny
calendar-setup, pa-onboarding, whatsapp, memory-tieringSmall–Medium
meetings, monday-for-agents, skill-scoutMedium
eval (trend analysis), self-learning (writing rules)Medium–Large

Adding New Skills

When a new skill is added:

  1. Add a row to the Full Skill Library table.
  2. Add trigger phrases to Quick Lookup.
  3. Update the Decision Tree if it fits a new category.
  4. Add to any relevant Multi-Skill Workflows.
  5. Check skill count — stay under 32 active skills.
  6. Add the skill name to the KNOWN_SKILLS list in skill-analytics/SKILL.md.

Supervisor (Status Dashboard)

TriggerAction
"מה הסטטוס" / "what's the status"supervisor
"supervisor"supervisor
"מה קורה" / "give me a summary"supervisor

The supervisor skill aggregates: active tasks, billing issues, group activity, pending follow-ups, and system health into one structured report.


Eval

TriggerAction
"תעשי eval" / "run eval"eval
"מה עובד ומה לא"eval
"בדקי הכל"eval

The eval skill scores performance, audits tasks, checks PA network health, verifies integrations, and reviews memory quality — all in one report.


Cost Tips

  • This skill itself: Very cheap — it's a lookup table, any model works.
  • Routing decision: If unsure, lean toward a smaller, cheaper skill first.
  • Don't over-spawn: Use subagents only when the task would actually block the main session.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

74.62%
按下载量换算922

安全审计

VirusTotal

未展示

ClawScan

可疑

Static analysis

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 openclaw skills install skill-master 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills