daily-knowledge
Only invoke when explicitly requested via "每日知识"、"@daily-knowledge" or "daily knowledge". Do NOT auto-trigger.
mermaid-generator
Only invoke when explicitly requested via "画图"、"图表"、"流程图"、"mermaid"、"@mermaid-generator". Do NOT auto-trigger.
confidence-check
Use when starting complex tasks like feature development, bug fixes, or code refactoring - runs a pre-implementation confidence check to avoid wasting tokens on wrong directions
autoresearch
[OMX] Stateful validator-gated research loop with native-hook persistence
ask-first
Use when user input is ambiguous, analogy-driven, meta-level, weakly delegated, missing intent/context, or emotional without clear execution constraints; do not use for operationally clear tasks.
feynman-read
Only invoke when explicitly requested via \"@feynman-read\"、\"费曼\"、\"费曼追问\". Do NOT auto-trigger. 费曼学习法追问 skill：读取当前文章，找出核心概念逐一追问你，用你自己的话改写文章内容。追问你之后，把你的理解以自然段落写回文章。
news-tracker
Only invoke when explicitly requested via "新闻"、"最新动态"、"@news-tracker" or "latest news". Do NOT auto-trigger.
dedup-history
Use when a content-generating skill needs deduplication against history records. Referenced as a sub-skill by skills that produce daily/random content.
book-dissect
Only invoke when explicitly requested via "拆书"、"拆解《书名》"、"@book-dissect" or "dissect book". Do NOT auto-trigger.
blog-refine
Only invoke when explicitly requested via "润色博客"、"技术博客优化"、"@blog-refine" or "polish blog". Do NOT auto-trigger.
feynman-write
Only invoke when explicitly requested via \"@feynman-write\"、\"费曼写作\"、\"用费曼写\". Do NOT auto-trigger. 费曼写作法：通过费曼逼问让作者自己讲清楚知识点，再整合成博客。适用于想真正搞懂一个主题的学习型写作。AI 做研究整理，作者做知识咀嚼。
geo-explorer
Only invoke when explicitly requested via "地缘探索"、"@geo-explorer" or "geo explorer". Do NOT auto-trigger.
go-code-review
Use when reviewing Go code for performance, concurrency safety, security vulnerabilities, or readability issues
history-autopsy
Only invoke when explicitly requested via "历史速览"、"@history-autopsy" or "history autopsy". Do NOT auto-trigger.
insight-miner
Only invoke when explicitly requested via "洞见"、"@insight-miner" or "insight". Do NOT auto-trigger.
learn-topic
Only invoke when explicitly requested via "学习"、"讲解"、"teach me"、"@learn-topic". Do NOT auto-trigger.
notes-to-blog
Only invoke when explicitly requested via "@notes-to-blog"、"博客知识提取"、"笔记整理成博客". Do NOT auto-trigger. Manual-only skill for turning notes, debugging records, design summaries, code snippets, or rough drafts into a Chinese technical blog.
project-hunter
Only invoke when explicitly requested via "做什么项目"、"创业方向"、"副业"、"@project-hunter" or "project ideas". Do NOT auto-trigger.
strategic-product-advisor
Only invoke when explicitly requested via "产品方向"、"怎么赚钱"、"竞品分析"、"@strategic-product-advisor". Do NOT auto-trigger.
ui-ux-auditor
Only invoke when explicitly requested via "UI审查"、"设计审计"、"@ui-ux-auditor" or "design audit". Do NOT auto-trigger.
value-judge
Only invoke when explicitly requested via "值不值得看"、"评估打分"、"@value-judge" or "evaluate value". Do NOT auto-trigger.
wisdom-decoder
Only invoke when explicitly requested via "智慧解码"、"@wisdom-decoder" or "wisdom decoder". Do NOT auto-trigger.
using-forgetful-memory
Guidance for using Forgetful semantic memory effectively. Applies Zettelkasten atomic memory principles. Use when deciding whether to query or create memories, structuring memory content, or understanding memory importance scoring.
exploring-knowledge-graph
Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.
curating-memories
Guidance for maintaining memory quality through curation. Covers updating outdated memories, marking obsolete content, and linking related knowledge. Use when memories need modification, when new information supersedes old, or when building knowledge graph connections.
rag-exploitation
Attack techniques for Retrieval-Augmented Generation systems including knowledge base poisoning
infrastructure-security
Securing AI/ML infrastructure including model storage, API endpoints, and compute resources
automated-testing
CI/CD integration and automation frameworks for continuous AI security testing
model-extraction
Techniques to extract model weights, architecture, and training data through API queries
red-team-reporting
Professional security report generation, executive summaries, finding documentation, and remediation tracking
red-team-frameworks
Tools and frameworks for AI red teaming including PyRIT, garak, Counterfit, and custom attack automation
model-inversion
Privacy attacks to extract training data and sensitive information from AI models
prompt-hacking
Advanced prompt manipulation including direct attacks, indirect injection, and multi-turn exploitation
prompt-injection-testing
Master prompt injection attacks, jailbreak techniques, input manipulation, and payload crafting for LLM security testing
vulnerability-discovery
Systematic vulnerability finding, threat modeling, and attack surface analysis for AI/LLM security assessments
testing-methodologies
Structured approaches for AI security testing including threat modeling, penetration testing, and red team operations
security-testing
Comprehensive security testing automation for AI/ML systems with CI/CD integration
secure-deployment
Security best practices for deploying AI/ML models to production environments
safety-filter-bypass
Techniques to test and bypass AI safety filters, content moderation systems, and guardrails for security assessment
responsible-disclosure
Ethical vulnerability reporting, coordinated disclosure, and bug bounty participation for AI systems
benchmark-datasets
Standard datasets and benchmarks for evaluating AI security, robustness, and safety
code-injection
Test AI systems for code injection vulnerabilities including prompt-to-code attacks and agent exploitation
continuous-monitoring
Real-time monitoring and detection of adversarial attacks and model drift in production
defense-implementation
Implement mitigations, create input filters, design output guards, and build defensive prompting for LLM security
input-output-guardrails
Implementing safety filters, content moderation, and guardrails for AI system inputs and outputs
llm-jailbreaking
Advanced LLM jailbreaking techniques, safety mechanism bypass strategies, and constraint circumvention methods
adversarial-training
Defensive techniques using adversarial examples to improve model robustness and security
adversarial-examples
Generate adversarial inputs, edge cases, and boundary test payloads for stress-testing LLM robustness
data-poisoning
Test AI training pipelines for data poisoning vulnerabilities and backdoor injection
certifications-training
Professional certifications, CTF competitions, and training resources for AI security practitioners
Page 1299 of 1708 · 85384 results
