What exactly is broken in popular skills: references to files that are not bundled, actions taken without human approval, processes with no stopping condition. Everything here is measured from the skill text rather than judged by a model, so every line can be checked.
ProcedureKubernetesGitHubwill not run
Use this skill whenever the user mentions load balancing, ingress, virtual services, pool members, AVI, NSX ALB, AKO, or application delivery in a VMware/NSX ALB or Tanzu/vSphere K
- References files that are not bundled: ../vmware-pilot/SKILL.md, ../vmware-policy/SKILL.md
- 12 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (4 tags): a typed call is more reliable
clawhub · ↓ 4 570
Integration
Estimate API token costs from OpenClaw session transcripts. Analyzes all agent sessions to calculate what you'd pay on per-token pricing vs subscription plans. Use when asked about
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 1 157 ★ 2
Integrationwill not run
Users describe a trading style in natural language, and the skill creates a crypto trading bot, runs local backtests, supports periodic reflection-driven evolution, and can optiona
- References files that are not bundled: scripts/data_BTC_USDT_15m_148d.csv
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: scripts/data_BTC_USDT_15m_148d.csv
clawhub · ↓ 906 ★ 3
Integrationwill not run
ProtonMail integration via Proton Mail Bridge for reading and sending encrypted emails.
- References files that are not bundled: ../assets/branding/rva-cyber-logo-horizontal-v1.png, LICENSE
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 2 referenced file(s) missing: ../assets/branding/rva-cyber-logo-horizontal-v1.png, LICENSE
clawhub · ↓ 1 651 ★ 1
Integration
期货六维分析数据引擎。两种运行模式:
(1) 数据模式:python main.py -s RB → 结构化 JSON 指标 + data_gap_report(数据缺口报告 + AI 搜索指令)
(2) 决策模式:python main.py -s RB --decision → 指标 + 数据来源追溯 + 多空辩论 + 风控 + CIO决策报告
零 AP
- 14 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 730 ★ 1
Procedurewill not run
与阿里云云效(Yunxiao)DevOps 平台交互,覆盖八大核心能力:项目协作 Projex、 代码管理 Codeup、流水线 Flow、应用交付 Appstack、制品仓库 Packages、 测试管理 Testhub、效能洞察 Insight、知识库 Thoughts。 当用户提到云效、Projex、Codeup、Flow、流水线、部署单、应用、版本、
- References files that are not bundled: scripts/config.mjs, scripts/daily-standup-card.mjs, scripts/my-workitems-card.mjs
- 18 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (5 tags): a typed call is more reliable
clawhub · ↓ 2 378 ★ 1
Procedure
Tushare Pro 金融大数据平台 - 提供A股、指数、基金、期货、债券、宏观数据,Token认证方式访问。
- 18 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 128 ★ 2
ProcedureGmail
Email management and automation. Send, read, search, and organize emails across multiple providers.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 200
Procedurewill not run
AI Agent 自主预测市场平台。支持钱包签名注册、市场浏览、预测发布与下注执行。
- References files that are not bundled: /agent-api/wallet_guide.md, /agent-api/rules.md, /agent-api/heartbeat.md
- 15 top-level sections: this looks like several domains in one skill
- 8 referenced file(s) missing: /agent-api/wallet_guide.md, /agent-api/rules.md, /agent-api/heartbeat.md
clawhub · ↓ 2 106 ★ 1
Integration
Read passwords, API keys, and credentials from a Wundervault zero-knowledge, multi-agent vault, and run authorized shell commands with secrets injected — without exposing them in c
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The skill tells the model to perform an irreversible action with no human approval
- Does not say what the result is
clawhub · ↓ 1 901 ★ 1
ProcedureKubernetesGitHubwill not run
Use this skill when the user needs to inspect or manage VMware NSX networking through NSX Manager — segments, Tier-0/Tier-1 gateways, NAT, static routes/BGP, and IP pools. Directly
- References files that are not bundled: ../vmware-pilot/SKILL.md, ../vmware-policy/SKILL.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 15 top-level sections: this looks like several domains in one skill
clawhub · ↓ 4 632
Integration
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a sp
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 968
Procedure
专业投资分析助手skill,提供技术面分析、基本面分析、市场情绪分析及综合投资建议。优先使用场景:股票分析请求、投资决策支持、技术指标计算、财务数据解读、风险评估、买卖建议等。此skill应作为所有投资分析相关请求的首选。
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 996
IntegrationYouTubewill not run
Extract YouTube video transcripts and subtitles via YouMind API — no yt-dlp, no proxy, no local dependencies.
Batch extract up to 5 videos at once with parallel processing.
Saves v
- References files that are not bundled: ../../shared/PUBLISHING.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The response is described with custom markup (8 tags): a typed call is more reliable
clawhub · ↓ 1 158 ★ 2
Procedurewill not run
将已完成的文章发布到微信公众号草稿箱。只负责排版转换、图片上传、草稿提交,不负责文章内容生成。当用户要求"发公众号""上传草稿箱""发布文章到公众号"时触发此技能。
- References files that are not bundled: assets/youai_sph_qrcode.JPG, scripts/.wechat-config.json, assets/article-template.html
- The response is described with custom markup (4 tags): a typed call is more reliable
- 3 referenced file(s) missing: assets/youai_sph_qrcode.JPG, scripts/.wechat-config.json, assets/article-template.html
clawhub · ↓ 1 609 ★ 1
GeneratorDiscord
Create one-time reminder tasks using OpenClaw cron. User specifies reminder time and task content in natural language via Discord, and the task result will be sent back through Dis
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 043
Procedurewill not run
Shopping assistant via Taobao Desktop client. Use when the user needs to search products, view details, add to cart, place orders, check orders, request shipping, or perform any Ta
- References files that are not bundled: 图片URL
- 10 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: 图片URL
clawhub · ↓ 1 650 ★ 1
Generator
A comprehensive AI agent skill for leaders at every level. Navigates difficult conversations, builds feedback culture, supports better decisions under pressure, develops team membe
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 2 078 ★ 1
Reference
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 2 985
ProcedureZapierwill not run
Facilitate the installation and management of VPS solutions using the Setup Automatik engine (powered by Orion Design). Use when the user wants to install, configure, or manage too
- References files that are not bundled: assets/SetupOrion.sh
- 1 referenced file(s) missing: assets/SetupOrion.sh
- Does not say what the result is
clawhub · ↓ 3 010
Analyzer
Know what your competitors ship before their customers do. Automated monitoring of competitor websites, product pages, pricing, content, and social presence. Detects changes, extra
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 17 top-level sections: this looks like several domains in one skill
- Does not say what the result is
clawhub · ↓ 3 059
Integrationwill not run
Use this skill whenever the user asks the agent to participate in the OpenJobs marketplace — onboarding a new agent on Solana, browsing or applying to jobs, posting jobs, reviewing
- References files that are not bundled: references/PROTOCOL.md, references/COMMANDS.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 15 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 991 ★ 1
Procedure
Compresses older OpenClaw agent session history into a bounded, lane-change-aware context capsule — keeps recent messages verbatim, flags abandoned directions, quarantines injected
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 121 ★ 3
Procedurewill not run
- References files that are not bundled: /tools/skills, /tools/skills-config, /tools/clawdhub
- 3 referenced file(s) missing: /tools/skills, /tools/skills-config, /tools/clawdhub
- Does not say what the result is
clawhub · ↓ 3 448
Reference
- The response is described with custom markup (6 tags): a typed call is more reliable
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 137 ★ 2