Discover and install skills, docs, and rules to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
HKUDS/OpenSpace Track and complete all required deliverables before finishing a task | Skills | |
HKUDS/OpenSpace Transform unstructured clinical encounters into comprehensive SOAP notes with ICD codes and care plans | Skills | |
HKUDS/OpenSpace Handle websites requiring JavaScript by using curl with browser headers and validating file types. | Skills | |
HKUDS/OpenSpace Check FFmpeg encoder availability before video encoding to avoid library mismatches | Skills | |
HKUDS/OpenSpace Check available FFmpeg encoders before writing encoding scripts to avoid library version mismatches | Skills | |
HKUDS/OpenSpace Create Excel files with openpyxl by falling back to run_shell with inline Python heredoc when execute_code_sandbox fails | Skills | |
HKUDS/OpenSpace Extract text from DOCX files with shell-primary approach and Python zipfile fallback for maximum reliability | Skills | |
HKUDS/OpenSpace Identify and classify agent failures occurring before execution starts | Skills | |
vudovn/ag-kit Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps. | Skills | |
vudovn/ag-kit Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support. | Skills | |
vudovn/ag-kit Mobile game development principles. Touch input, battery, performance, app stores. | Skills | |
vudovn/ag-kit 2D game development principles. Sprites, tilemaps, physics, camera. | Skills | |
vudovn/ag-kit Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts. | Skills | |
Orchestra-Research/AI-Research-SKILLs Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails. | Skills | |
xbtlin/ai-berkshire AI Berkshire skill: 行业投资研究:产业链全景扫描 + 四大师个股分析框架. Source: skills/industry-research.md. | Skills | |
tanweai/pua PUA team status alias for Codex. Codex subcommand mapping for Claude Code /pua:team-status style usage; invoke with $pua-team-status. | Skills | |
tanweai/pua 日本語の生産性コーチングモード。明示的な依頼、反復失敗、受け身、検証不足、品質不満のときに、構造化トラブルシューティングと証拠ベースの完了確認を促す。 | Skills | |
TencentBlueKing/bk-bcs Harness 规范文档生成——harness-engineering 的子 skill,负责项目上下文感知、 信息收集、五大组件与技术规范文档的生成/修正、开发地图生成及总结报告。 由 harness-engineering 按生成类触发词路由调用,不独立触发。 | Skills | |
roman01la/skills-agents Use when you have a spec or requirements for a multi-step task, before touching code | Skills | |
NeoLabHQ/context-engineering-kit Systematic Fishbone analysis exploring problem causes across six categories | Skills |
Can't find what you're looking for? Evaluate a missing skill.