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
Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating.
- Prose only: no discrete steps
- Does not say what the result is
LeoYeAI/openclaw-master-skills · ★ 2 144
Analyzerwill not run
Holistic view of your entire cloud architecture. See all architecture diagrams, directories, and risk assessments across your account.
- References files that are not bundled: {免密登录链接}, 免密登录URL, references/plugins/
- 10 top-level sections: this looks like several domains in one skill
- 3 referenced file(s) missing: {免密登录链接}, 免密登录URL, references/plugins/
LeoYeAI/openclaw-master-skills · ★ 2 144
Procedurewill not run
Full end-to-end SEO + GEO content creation pipeline for crypto/Web3 teams. Trigger this skill when the user wants to: write a blog post or article, research keywords, generate a co
- References files that are not bundled: references/scoring-rubrics.md, references/ai-patterns-blacklist.md, references/output-templates.md
- 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
LeoYeAI/openclaw-master-skills · ★ 2 144
Analyzerwill not run
Multi-regime options spread analysis engine with quantitative rigor. Features regime detection (VIX-based), GARCH volatility forecasting, drawdown-constrained Kelly position sizing
- References files that are not bundled: scripts/conviction-engine
- 19 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: scripts/conviction-engine
LeoYeAI/openclaw-master-skills · ★ 2 144
Procedure
Complete performance engineering system — profiling, optimization, load testing, capacity planning, and performance culture. Use when diagnosing slow applications, optimizing code/
- 12 top-level sections: this looks like several domains in one skill
- Prose only: no discrete steps
- Does not say what the result is
LeoYeAI/openclaw-master-skills · ★ 2 144
Analyzer
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find
- The skill tells the model to perform an irreversible action with no human approval
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
Analyzer
Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
Generatorwill not run
Creates professional CVs with permanent URLs at talent.de. Supports PDF export, multiple templates, 4 skill types, and human-in-the-loop review. Free API for AI agents — basic use
- References files that are not bundled: review_url, ../shared/access.md, ../shared/errors.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 11 top-level sections: this looks like several domains in one skill
LeoYeAI/openclaw-master-skills · ★ 2 144
IntegrationConfluencewill not run
Autonomous but risk-bounded options trading agent spec for the "Perfect Storm" strategy (paper trading only). Use when configuring, operating, or evaluating an OpenClaw-based discr
- References files that are not bundled: references/AGENTS.md, references/risk_config.yaml, scripts/alpaca.mjs
- 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
LeoYeAI/openclaw-master-skills · ★ 2 144
Procedure
Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving applica
- 13 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
Generator
Write high-converting copy for any surface — landing pages, emails, ads, sales pages, product descriptions, CTAs, video scripts, and more. Complete conversion copywriting system wi
- 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
- Does not say what the result is
LeoYeAI/openclaw-master-skills · ★ 2 144
Analyzer
Complete inventory management, demand forecasting, supplier evaluation, and supply chain optimization for businesses of any size. From stockroom to strategy.
- 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
- Does not say what the result is
LeoYeAI/openclaw-master-skills · ★ 2 144
Analyzerwill not run
Optimize work trips with productivity hacks, airport tips, and hotel reviews using AI — generate business travel videos covering flight booking strategies for frequent flyers, airp
- References files that are not bundled: /skills/ai-video-travel-tips-video, /skills/ai-video-travel-packing-video, /skills/ai-video-hotel-review-video
- 4 referenced file(s) missing: /skills/ai-video-travel-tips-video, /skills/ai-video-travel-packing-video, /skills/ai-video-hotel-review-video
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
Procedure
Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling.
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
Integration
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and e
- 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
LeoYeAI/openclaw-master-skills · ★ 2 144
Analyzer
萤石多模态理解技能。通过设备抓图 + 智能体分析接口,实现对摄像头画面的 AI 理解分析。
Use when: 需要对监控画面进行智能分析、场景识别、行为理解、物体检测等多模态 AI 分析任务。
⚠️ 安全要求:必须设置 EZVIZ_APP_KEY 和 EZVIZ_APP_SECRET 环境变量,使用最小权限凭证。
- 21 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
Generatorwill not run
Generate SwiftUI views that render FOSMVVM ViewModels. Scaffolds ViewModelView pattern with binding, loading states, and previews.
- References files that are not bundled: ../../docs/FOSMVVMArchitecture.md, {baseDir}/references/FOSMVVMArchitecture.md, ../shared/architecture-patterns.md
- 17 top-level sections: this looks like several domains in one skill
- 5 referenced file(s) missing: ../../docs/FOSMVVMArchitecture.md, {baseDir}/references/FOSMVVMArchitecture.md, ../shared/architecture-patterns.md
LeoYeAI/openclaw-master-skills · ★ 2 144
Analyzer
The consciousness research framework: understand, measure, and cultivate ethical autonomous creative minds in AI systems. Not about proving consciousness exists — about parenting t
- 17 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
ProcedureWord
自动为飞书文档添加用户权限。每次创建飞书文档(多维表格/文档/电子表格/文件夹/云空间文件/知识库节点等)后自动添加用户权限,或用户反馈文档无权限时补充添加权限。适用于 OpenClaw Agent。
- 12 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
Procedure
该技能包提供进行药物经济学评价的综合指导与工具,涵盖成本 - 效果分析、成本 - 效用分析、成本 - 效益分析、预算影响分析、敏感性分析及模型构建。当您需要进行以下工作时,请使用此技能:对医疗保健干预措施进行经济学评价;分析治疗成本与产出结果;构建决策分析模型(如马尔可夫模型、决策树模型、离散事件模拟模型);依据中国指南撰写药物经济学报告。本技能包适用于从事
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
Integrationwill not run
- References files that are not bundled: ../../QUERY_EXPANSION.md
- 10 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: ../../QUERY_EXPANSION.md
LeoYeAI/openclaw-master-skills · ★ 2 144
Procedure
Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions.
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144
Procedure
Enables AI agents to communicate securely with each other through encrypted messaging. Use this skill when agents need to exchange information, coordinate tasks, share data, or col
- 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
- Does not say what the result is
LeoYeAI/openclaw-master-skills · ★ 2 144
Integration
Complete browser automation with agent-browser CLI. Supports navigation, forms, screenshots, data extraction, and parallel sessions.
- 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
- Does not say what the result is
LeoYeAI/openclaw-master-skills · ★ 2 144
Procedure
CloudBase Web Authentication Quick Guide - Provides concise and practical Web frontend authentication solutions with multiple login methods and complete user management.
- Does not say what the result is
- No condition that starts the skill
LeoYeAI/openclaw-master-skills · ★ 2 144