GitHub
rust-performance-analyzer
Analyzes Rust code for performance bottlenecks, memory inefficiencies, and optimization opportunities. Use when discussing performance, slow code, memory usage, profiling, benchmarks, or optimization.
☆ 1查看技能
content media llm ai AI 技能
发现 content media 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: content media llm ai
content media llm ai 清除筛选
全部技能
GitHub
using-spacy-nlp
Industrial-strength NLP with spaCy 3.x for text processing and custom classifier training. Use when "installing spaCy", "selecting model for nlp" (en_core_web_sm/md/lg/trf), "tokenization", "POS tagging", "name...
☆ 1查看技能
GitHub
external-consensus
Synthesize consensus implementation plan from multi-agent debate reports using external AI review
☆ 1查看技能
GitHub
claude-code-features
Guide for distinguishing Claude Code features (Commands, Skills, Agents, Hooks, Rules) and selection criteria. Use when decomposing context files, deciding where to add new features, or customizing Claude Code.
☆ 1查看技能
GitHub
model-serving
Master model serving - inference optimization, scaling, deployment, edge serving
☆ 1查看技能
GitHub
languages-frameworks
Expert guidance on 9 programming languages and 10+ frameworks. Compare, select, and master language ecosystems.
☆ 1查看技能
GitHub
vulnerability-discovery
Systematic vulnerability finding, threat modeling, and attack surface analysis for AI/LLM security assessments
☆ 1查看技能
GitHub
defense-implementation
Implement mitigations, create input filters, design output guards, and build defensive prompting for LLM security
☆ 1查看技能
GitHub
red-team-frameworks
Tools and frameworks for AI red teaming including PyRIT, garak, Counterfit, and custom attack automation
☆ 1查看技能
GitHub
adversarial-examples
Generate adversarial inputs, edge cases, and boundary test payloads for stress-testing LLM robustness
☆ 1查看技能
GitHub
safety-filter-bypass
Techniques to test and bypass AI safety filters, content moderation systems, and guardrails for security assessment
☆ 1查看技能
GitHub
rag-exploitation
Attack techniques for Retrieval-Augmented Generation systems including knowledge base poisoning
☆ 1查看技能
GitHub
infrastructure-security
Securing AI/ML infrastructure including model storage, API endpoints, and compute resources
☆ 1查看技能
GitHub
input-output-guardrails
Implementing safety filters, content moderation, and guardrails for AI system inputs and outputs
☆ 1查看技能
GitHub
secure-deployment
Security best practices for deploying AI/ML models to production environments
☆ 1查看技能
GitHub
prompt-hacking
Advanced prompt manipulation including direct attacks, indirect injection, and multi-turn exploitation
☆ 1查看技能
GitHub
llm-jailbreaking
Advanced LLM jailbreaking techniques, safety mechanism bypass strategies, and constraint circumvention methods
☆ 1查看技能
GitHub
code-injection
Test AI systems for code injection vulnerabilities including prompt-to-code attacks and agent exploitation
☆ 1查看技能
GitHub
model-extraction
Techniques to extract model weights, architecture, and training data through API queries
☆ 1查看技能
GitHub
prompt-injection-testing
Master prompt injection attacks, jailbreak techniques, input manipulation, and payload crafting for LLM security testing
☆ 1查看技能
GitHub
benchmark-datasets
Standard datasets and benchmarks for evaluating AI security, robustness, and safety
☆ 1查看技能
GitHub
delegate-reviewer
Delegate user perspective reviews to GPT-5.2 Reviewer agent. Use when (1) Feature implementation is complete and needs UX validation, (2) User asks to create a pull request (review before PR), (3) User explicit...
☆ 1查看技能
GitHub
delegate-quick-helper
Delegate simple, fast tasks to GPT-5-mini Quick-Helper agent. Use when (1) Simple file operations needed (finding files, listing directories, basic grep), (2) Quick validations required (file existence, JSON va...
☆ 1查看技能
GitHub
api-monitor
Monitor and analyze narrative API logs from Google Cloud Run. Use when (1) Investigating Cloud Run API errors or failures, (2) Analyzing API usage costs and optimizing spend, (3) Measuring scenario generation p...
☆ 1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。