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.
Procedure
- No condition that starts the skill
- Does not say what the process needs to start
clawhub · ↓ 1 534 ★ 4
Procedure
Automatically identifies wet clothing and abnormal excretion via visual AI. Instantly notifies caregivers to improve care for incontinent elderly, bedridden patients, and infants,
- 1 steps
- Does not say what the result is
clawhub · ↓ 1 915 ★ 5
IntegrationGitHub
Multi-stage multi-agent reasoning middleware that reduces LLM hallucination by 70%+. 9 specialized emergence engines for invention, creative, pharma, genomics, chemistry, ecology,
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 146 ★ 6
Integration
Load this skill whenever the user wants to control, automate, or interact with a phone or mobile device. This includes: tapping, swiping, typing, taking screenshots, reading the sc
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 12 top-level sections: this looks like several domains in one skill
- The skill tells the model to perform an irreversible action with no human approval
clawhub · ↓ 1 936 ★ 3
Integrationwill not run
AI短剧提示词工厂 - 端到端将小说/故事创意转化为结构化提示词包(角色立绘+场景+道具+分镜图片+视频+音频)的完整流水线。一个入口启动全流程,内部自动按阶段推进:策划→设计→剧本→诊断→提示词组装→API JSON输出。支持小说改编和原创短剧两条路径。触发词:AI短剧、短剧制作、小说转短剧、短剧提示词、提示词工厂、短剧全流程、小说改编短剧、生成短剧、AI
- References files that are not bundled: scripts/ep{NN}/script.json, scripts/ep{NN}/script.md
- 10 top-level sections: this looks like several domains in one skill
- 2 referenced file(s) missing: scripts/ep{NN}/script.json, scripts/ep{NN}/script.md
clawhub · ↓ 1 869 ★ 3
IntegrationGitHub
API gateway for personal data with human-in-the-loop write approval. Connects agents to GitHub, Bluesky, Google Calendar, Home Assistant, and more — all through a single API with s
- 10 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 · ↓ 2 420 ★ 2
IntegrationStripeNotionwill not run
Firecrawl API integration with managed authentication. Scrape, crawl, map, and search web content.
Use this skill when users want to extract content from websites, crawl entire sit
- References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 14 top-level sections: this looks like several domains in one skill
clawhub · ↓ 3 775 ★ 1
Integrationwill not run
Patterns for building resilient API clients and real-time connections with retry logic, circuit breakers, and graceful degradation. Use when building production systems that need t
- References files that are not bundled: ../../meta/realtime-dashboard/, ../realtime-react-hooks/, ../websocket-hub-patterns/
- 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 · ↓ 2 351 ★ 2
Analyzerwill not run
Production skill for orchestrating Claude Code's native agent teams feature. Use when: (1) Multi-lens reviews, (2) Competing hypotheses debugging, (3) Full-stack features, (4) Arch
- References files that are not bundled: references/cost-management.md, references/troubleshooting.md, references/best-practices.md
- 11 top-level sections: this looks like several domains in one skill
- 3 referenced file(s) missing: references/cost-management.md, references/troubleshooting.md, references/best-practices.md
clawhub · ↓ 2 420 ★ 2
Integrationwill not run
Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base. Covers th
- References files that are not bundled: opensea-api/SKILL.md, opensea-marketplace/SKILL.md, opensea-swaps/SKILL.md
- 5 referenced file(s) missing: opensea-api/SKILL.md, opensea-marketplace/SKILL.md, opensea-swaps/SKILL.md
- Does not say what the result is
clawhub · ↓ 3 690 ★ 2
Analyzer
Identifies abnormal behaviors such as limb tremors, convulsions, stiffness, and gait abnormalities through video recognition, assisting in home risk monitoring for patients with ch
- 1 steps
- Does not say what the result is
clawhub · ↓ 1 736 ★ 5
Generator
会自己设计PPT的智能报告技能,内置47套PPT模板(商务、科技、创意、学术、政府、金融等全场景覆盖),根据主题风格自由选配模板并自主设计,将任意输入拆解为5-15页精美HTML报告,每页严格1017×720px对齐PPT画布。当用户说"生成报告"、"分析内容做成页面"、"做成HTML"、"内容可视化"时立即使用,无需确认直接生成。
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 2 257 ★ 3
Procedurewill not run
Privora · AI Agent 投资工作流平台 — Bearer Token 即接入 /agent/skills/execute 通用 dispatcher,覆盖 A 股/港股/美股/黄金/基金/财报数据 + Python 回测(含 sandbox)+ 模拟交易 + 组合归因(α/β TWR)+ 云端告警 + 流程编排。Hermes / Claude
- References files that are not bundled: CHANGELOG.md, lg-data-demo.gif, ../mcp-server/README.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 · ↓ 3 629 ★ 2
Analyzer
Scan content and websites for SEO gaps, identify opportunities to outrank competitors. Use when: (1) Analyzing page SEO, (2) Checking meta tags and structured data, (3) Reviewing c
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 3 385 ★ 1
ReferenceWord
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 423 ★ 2
ProcedureSlackAWSwill not run
Sub-skill of microsoft-365-agents-toolkit. Routed expert system with 100+ micro-expert files for migrating Slack bots to Teams, cross-platform bridging, and dual-platform bot devel
- References files that are not bundled: ../SKILL.md, ../test-playground/test-playground.md, ../test-teams/test-teams.md
- 39 referenced file(s) missing: ../SKILL.md, ../test-playground/test-playground.md, ../test-teams/test-teams.md
- Does not say what the result is
microsoft/skills · ★ 3 025
ProcedureAzurewill not run
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged
- References files that are not bundled: ../../../quota/quota.md
- 1 referenced file(s) missing: ../../../quota/quota.md
- Does not say what the result is
microsoft/skills · ★ 3 025
ProcedureAzurewill not run
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capa
- References files that are not bundled: ../preset/SKILL.md, ../customize/SKILL.md, ../../../quota/quota.md
- 4 referenced file(s) missing: ../preset/SKILL.md, ../customize/SKILL.md, ../../../quota/quota.md
- Does not say what the result is
microsoft/skills · ★ 3 025
AnalyzerAzurewill not run
Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if
- References files that are not bundled: ../../../quota/quota.md
- 1 referenced file(s) missing: ../../../quota/quota.md
- Does not say what the result is
microsoft/skills · ★ 3 025
IntegrationAzure
Azure Web PubSub Service SDK for Python. Use for real-time messaging, WebSocket connections, and pub/sub patterns.
Triggers: "azure-messaging-webpubsubservice", "WebPubSubServiceCl
- The response is described with custom markup (3 tags): a typed call is more reliable
- Does not say what the result is
- No condition that starts the skill
microsoft/skills · ★ 3 025
IntegrationAzure
Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation
- The response is described with custom markup (3 tags): a typed call is more reliable
- Does not say what the result is
- No condition that starts the skill
microsoft/skills · ★ 3 025
AnalyzerAzurewill not run
Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy),
- References files that are not bundled: ../../foundry-agent/create/create-hosted.md, preset/SKILL.md, customize/SKILL.md
- 5 referenced file(s) missing: ../../foundry-agent/create/create-hosted.md, preset/SKILL.md, customize/SKILL.md
- Does not say what the result is
microsoft/skills · ★ 3 025
IntegrationAzure
Azure AI Content Understanding SDK for Python. Use for multimodal content extraction from documents, images, audio, and video.
Triggers: "azure-ai-contentunderstanding", "ContentUn
- 18 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (3 tags): a typed call is more reliable
- Does not say what the result is
microsoft/skills · ★ 3 025
IntegrationAzurePowerPoint
Azure AI Document Translation SDK for batch translation of documents with format preservation. Use for translating Word, PDF, Excel, PowerPoint, and other document formats at scale
- 17 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (3 tags): a typed call is more reliable
- Does not say what the result is
microsoft/skills · ★ 3 025
IntegrationAzurewill not run
Azure Resource Manager SDK for API Management in .NET. Use for MANAGEMENT PLANE operations: creating/managing APIM services, APIs, products, subscriptions, policies, users, groups,
- References files that are not bundled: references/policies.md
- 11 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: references/policies.md
microsoft/skills · ★ 3 025