GitHub
override-mechanisms
Implementing human override capabilities for AI decisions with proper tracking, auditing, and feedback loops.
☆ 0查看技能
tools llm ai AI 技能
发现 tools llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
分类目录: tools llm ai
tools llm ai 清除筛选
全部技能
GitHub
human-in-the-loop-workflows
Implementing human approval and review workflows for AI systems to ensure quality, safety, and compliance.
☆ 0查看技能
GitHub
llm-judge-patterns
Comprehensive guide to using LLMs as judges for automated evaluation including prompt patterns, calibration, bias reduction, and multi-judge ensembles
☆ 0查看技能
GitHub
ai-risk-assessment
Identifying, assessing, and mitigating risks in AI systems including bias, safety, privacy, security, and ethical concerns.
☆ 0查看技能
GitHub
prompt-library-minimal
คลัง prompts แบบ minimal ที่ใช้ token น้อยที่สุดแต่ได้ผลลัพธ์ดี พร้อม templates และ best practices
☆ 0查看技能
GitHub
ai-model-registry
Centralized management of machine learning models throughout their lifecycle, including versioning, metadata, and production deployment.
☆ 0查看技能
GitHub
llm-token-optimization
See the main LLM Cost Optimization skill for comprehensive coverage of token economics and optimization strategies.
☆ 0查看技能
GitHub
communication-templates
Pre-written message templates for incident communication across different channels and severity levels.
☆ 0查看技能
GitHub
llm-security-red-teaming
Comprehensive guide to securing LLM applications including prompt injection prevention, jailbreak detection, guardrails, and red teaming methodologies
☆ 0查看技能
GitHub
tool-permission-model
Comprehensive guide to implementing permission systems for AI agent tools including RBAC, approval workflows, and security policies
☆ 0查看技能
GitHub
llm-function-calling
Implementing function calling (tool use) with LLMs for structured outputs and external integrations.
☆ 0查看技能
GitHub
model-serving-inference
Comprehensive guide to deploying and serving LLM models including optimization, batching, caching, and production infrastructure
☆ 0查看技能
GitHub
prompting-patterns
Comprehensive guide to effective prompt engineering patterns including few-shot, chain-of-thought, ReAct, and advanced prompting techniques
☆ 0查看技能
GitHub
retrieval-playbook-for-ai
กลยุทธ์การ retrieve context ให้ AI อย่างมีประสิทธิภาพ - เลือกอะไร ไม่เลือกอะไร และจัดลำดับอย่างไร
☆ 0查看技能
GitHub
skill-architect
The master skill for analyzing, designing, and standardizing the creation of new AI skills (Skill 72).
☆ 0查看技能
GitHub
ai-data-privacy
Protecting personal and sensitive data throughout the machine learning lifecycle, from training to inference.
☆ 0查看技能
GitHub
ai-agent-patterns
Design patterns for building autonomous AI agents that can reason, plan, and execute tasks.
☆ 0查看技能
GitHub
anti-bloat-checklist
Checklist สำหรับตรวจสอบและกำจัด bloat ใน context, prompt, และ response เพื่อลด token cost และเพิ่ม signal-to-noise ratio
☆ 0查看技能
GitHub
rag-evaluation
Comprehensive guide to evaluating Retrieval-Augmented Generation systems including retrieval metrics, generation quality, faithfulness, and end-to-end evaluation frameworks
☆ 0查看技能
GitHub
sandboxing
Comprehensive guide to sandboxing AI agents including code execution isolation, resource limits, security boundaries, and safe tool execution
☆ 0查看技能
GitHub
enhance-bmad-skills
Interactive skill for adapting BMAD path references and enhancing skill content. Reviews skills for {project-root} references and prompts for handling choices.
☆ 0查看技能
GitHub
bootstrap-bmad-skills
Bootstrap and install BMAD-METHOD skills for Claude Code, Cursor, Antigravity, and other tools.
☆ 0查看技能
GitHub
codeagent
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, Gemini, and Opencode backends with file references (@syntax) and structured output.
☆ 0查看技能
GitHub
glean-knowledge
Searches Canva's Glean knowledge base for internal documentation, policies, how-tos, Slack threads, and company information. Use when asked about Canva processes, internal docs, Slack conversations, or company...
☆ 0查看技能
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。