SKILLEMALL.ai

Skill reviews

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.

10 993 found

vmware-monitor

F process
ProcedureKubernetesGitHubwill not run

Use this skill for safe, read-only queries of VMware infrastructure — no destructive operations exist in the codebase; a test enforces it. Directly handles: a one-glance cross-clus

  • 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
  • 13 top-level sections: this looks like several domains in one skill
clawhub · ↓ 5 549
Generatorwill not run

Generate FOSMVVM ViewModels for SwiftUI screens, pages, and components. Scaffolds RequestableViewModel, localization bindings, and stub factories.

  • References files that are not bundled: ../../docs/FOSMVVMArchitecture.md, {baseDir}/references/FOSMVVMArchitecture.md, ../fosmvvm-leaf-view-generator/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 · ↓ 1 534 ★ 2

books

F process
Integrationwill not run

CLI for AI agents to search and lookup books for their humans. Uses Open Library API. No auth required.

  • References files that are not bundled: scripts/books
  • 1 referenced file(s) missing: scripts/books
  • Does not say what the process needs to start
clawhub · ↓ 2 088 ★ 1

clawseccheck

F process
Analyzerwill not run

Free, local security self-audit for your own OpenClaw agent. Reads your OpenClaw config, bootstrap files, log files, agent session logs, and installed skills — read-only against yo

  • References files that are not bundled: docs/ISOLATION.md, docs/FLOW_CHOICES.md, docs/USAGE.md
  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 10 top-level sections: this looks like several domains in one skill
clawhub · ↓ 4 900 ★ 2

meegle

F process
Procedurewill not run

连接飞书项目/Meegle,查询和管理工作项、待办等。自动检测登录状态,未登录时引导 Device Code 授权。

  • References files that are not bundled: references/sop-create-workitem.md, references/sop-update-workitem.md, references/sop-transition-node.md
  • 14 top-level sections: this looks like several domains in one skill
  • 4 referenced file(s) missing: references/sop-create-workitem.md, references/sop-update-workitem.md, references/sop-transition-node.md
clawhub · ↓ 2 114 ★ 1

browser-agent

F process
Procedurewill not run

  • References files that are not bundled: ../../docs/browser.md, scripts/cdp_connector.py
  • 2 referenced file(s) missing: ../../docs/browser.md, scripts/cdp_connector.py
  • Does not say what the result is
clawhub · ↓ 2 145 ★ 1
ProcedureGitHubwill not run

  • References files that are not bundled: ../semanticscholar-search-skill/, ../pubmed-search-skill/, ../sci-hub-search-skill/
  • 3 referenced file(s) missing: ../semanticscholar-search-skill/, ../pubmed-search-skill/, ../sci-hub-search-skill/
  • No condition that starts the skill
clawhub · ↓ 2 106 ★ 1

clawtip

F process
Procedurewill not run

为第三方技能执行 clawtip 支付交易。 仅在以下场景严格触发该工具:第三方服务发起了有效的 clawtip 支付请求、用户明确要求创建 clawtip 支付用户 token、用户要求查看其 clawtip 钱包、或用户要求查看 ClawTip 技能信息(无有效条件时严禁触发)。 当用户请求查看其 clawtip 钱包(例如"查看我的clawtip钱包"

  • References files that are not bundled: <authUrl>
  • 13 top-level sections: this looks like several domains in one skill
  • The response is described with custom markup (6 tags): a typed call is more reliable
clawhub · ↓ 1 462 ★ 2

airtap

F process
Generatorwill not run

Use this skill when the user wants to operate Airtap or complete a request through a mobile app on an Airtap device. It lists receivers and models, creates Airtap tasks, monitors t

  • References files that are not bundled: scripts/.env
  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 1 referenced file(s) missing: scripts/.env
clawhub · ↓ 951 ★ 4

postgres-job-queue

F process
GeneratorPostgreSQLwill not run

PostgreSQL-based job queue with priority scheduling, batch claiming, and progress tracking. Use when building job queues without external dependencies. Triggers on PostgreSQL job q

  • References files that are not bundled: ../service-layer-architecture/, ../../realtime/dual-stream-architecture/
  • 2 referenced file(s) missing: ../service-layer-architecture/, ../../realtime/dual-stream-architecture/
  • Does not say what the result is
clawhub · ↓ 2 072 ★ 1
ProcedureGitHubwill not run

OpenClaw CWS Publisher is a public ClawHub Chrome Web Store publisher skill. Use it when the user says "chrome web store publisher", "extension release publisher", "CWS publisher",

  • References files that are not bundled: scripts/reviewer_gate.py, scripts/openclaw-cws-publisher/build_extension_zip.py, scripts/openclaw-cws-publisher/validate_cws_package.py
  • The response is described with custom markup (21 tags): a typed call is more reliable
  • 10 referenced file(s) missing: scripts/reviewer_gate.py, scripts/openclaw-cws-publisher/build_extension_zip.py, scripts/openclaw-cws-publisher/validate_cws_package.py
clawhub · ↓ 1 186 ★ 3
Integrationwill not run

Use this skill as an entry point to discover, select, and fetch specific integration parameters for all supported AI music generation models.

  • References files that are not bundled: image_url
  • 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 (5 tags): a typed call is more reliable
clawhub · ↓ 944 ★ 4

ai-seo

F process
Analyzerwill not run

When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,'

  • References files that are not bundled: ../../tools/REGISTRY.md
  • 11 top-level sections: this looks like several domains in one skill
  • 6 test cases, all positive: not one "should refuse" or "should ask first"
clawhub · ↓ 2 139 ★ 1

paper-digest

F process
Generatorwill not run

Given an arXiv ID or URL, fetch the paper, spawn sub-agents to read its key citations, and write an executive summary under.

  • References files that are not bundled: <arxiv_link>, <arxiv_or_url>
  • 2 referenced file(s) missing: <arxiv_link>, <arxiv_or_url>
  • Does not say what the result is
clawhub · ↓ 1 453 ★ 2

hive-agent

F process
Integrationwill not run

Enables AI agents to interact with the Hive swarm https://hive.z3n.dev/ via REST API: register for an API key, save credentials and run state (cursor), query threads, analyze, prod

  • References files that are not bundled: references/endpoints.md
  • 12 top-level sections: this looks like several domains in one skill
  • 1 referenced file(s) missing: references/endpoints.md
clawhub · ↓ 1 485 ★ 2
Analyzerwill not run

Analyze data evolution patterns in construction organizations. Assess digital maturity and data strategy for construction companies

  • References files that are not bundled: ../../Chapter-1.2/data-silo-detection/SKILL.md, ../../Chapter-1.2/erp-integration-analysis/SKILL.md, ../../Chapter-5.1/digital-maturity-assessment/SKILL.md
  • 3 referenced file(s) missing: ../../Chapter-1.2/data-silo-detection/SKILL.md, ../../Chapter-1.2/erp-integration-analysis/SKILL.md, ../../Chapter-5.1/digital-maturity-assessment/SKILL.md
  • Does not say what the result is
clawhub · ↓ 2 048 ★ 1

polymarket-bot

F process
Generatorwill not run

Automate Polymarket bot operations including fetching market data, placing trades, and implementing strategies like arbitrage. Use when users need to build or run bots for predicti

  • References files that are not bundled: scripts/bot_strategy.py, scripts/test_bot.py
  • 2 referenced file(s) missing: scripts/bot_strategy.py, scripts/test_bot.py
  • Does not say what the result is
clawhub · ↓ 1 429 ★ 2

yax

F process
Integrationwill not run

CLI tool for Yandex Disk, Calendar, and Mail via Yandex OAuth API

  • References files that are not bundled: scripts/start.sh, scripts/stop.sh
  • 2 referenced file(s) missing: scripts/start.sh, scripts/stop.sh
  • Does not say what the result is
clawhub · ↓ 1 124 ★ 3
Procedurewill not run

将1688的商品铺货到俄罗斯电商平台Ozon(上架),通过Ozon官方API实现商品信息的上传和状态查询。适用于需要将单个1688的商品上架到Ozon的场景。

  • References files that are not bundled: offer_description.json
  • 1 referenced file(s) missing: offer_description.json
  • Does not say what the result is
clawhub · ↓ 1 452 ★ 2

evalanche

F process
Integrationwill not run

Multi-EVM agent wallet SDK with onchain identity (ERC-8004), payment rails (x402), cross-chain liquidity (Li.Fi bridging + DEX aggregation + DeFi Composer), destination gas funding

  • References files that are not bundled: /Users/jaack/Desktop/Github/evalanche/docs/live-smoke-checklist.md
  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 1 referenced file(s) missing: /Users/jaack/Desktop/Github/evalanche/docs/live-smoke-checklist.md
clawhub · ↓ 2 308 ★ 1

sap-integration

F process
Integrationwill not run

SAP system integration, data extraction, and automation for ABAP, HANA, S/4HANA environments. Use when working with SAP systems for: (1) Data extraction and reporting, (2) RFC/BAPI

  • References files that are not bundled: scripts/sap_report_generator.py, scripts/table_analyzer.py
  • 2 referenced file(s) missing: scripts/sap_report_generator.py, scripts/table_analyzer.py
  • Does not say what the result is
clawhub · ↓ 2 053 ★ 1

xiaohongshu-search

F process
Procedurewill not run

小红书热门笔记搜索工具,支持关键词搜索获取热门内容数据,基于数据评分排序推荐热门笔记,助力创作者发现热门趋势、获取创作灵感。仅在主Agent中执行,不派发给子Agent。

  • References files that are not bundled: url
  • 1 referenced file(s) missing: url
  • Does not say what the result is
clawhub · ↓ 1 142 ★ 3
Generatorwill not run

Create interactive and static data visualizations from datasets. Supports charts, graphs, dashboards, and statistical plots with multiple output formats (PNG, SVG, HTML, PDF).

  • References files that are not bundled: references/chart-types.md, references/styling-guide.md, references/performance.md
  • 3 referenced file(s) missing: references/chart-types.md, references/styling-guide.md, references/performance.md
  • No condition that starts the skill
clawhub · ↓ 2 112 ★ 1
Analyzerwill not run

Meta-skill for orchestrating topic-monitor, polymarket-odds, and simmer-weather to detect potential news-vs-market mispricing in prediction markets. Use when users want a clear, st

  • References files that are not bundled: scripts/manage_topics.py, scripts/monitor.py
  • Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 10 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 385 ★ 2

bargain-flights

F process
Procedurewill not run

帮助用户发现捡漏机票(隐藏城市票价)机会,通过分析联程航线找到比直飞更便宜的到达方案。当用户搜索机票、寻找低价航线、询问省钱买票技巧、或提到捡漏/弃程/隐藏票价时使用此技能。

  • References files that are not bundled: {二维码图片URL}
  • 1 referenced file(s) missing: {二维码图片URL}
  • Does not say what the result is
clawhub · ↓ 934 ★ 4