GitHub
skill-creator
Use when creating a new skill, updating an existing skill, or learning skill best practices. Load for extending Claude's capabilities with specialized workflows, tool integrations, or domain expertise. Covers s...
☆ 6查看技能
testing security llm ai AI 技能
发现 testing security 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: testing security llm ai
testing security llm ai 清除筛选
全部技能
GitHub
browser-testing
Use when testing web applications, debugging browser console errors, automating form interactions, or verifying UI implementations. Load for localhost testing, authenticated app testing (Gmail, Notion), or reco...
☆ 6查看技能
GitHub
claude-md-creator
Use when creating CLAUDE.md files, updating existing CLAUDE.md, validating CLAUDE.md structure, or auto-fixing CLAUDE.md issues. Load for setting up project instructions, global guidelines, local overrides, or...
☆ 6查看技能
GitHub
initialization
Use when starting a new session without feature-list.json, setting up project structure, or breaking down requirements into atomic features. Load in INIT state. Detects project type (Python/Node/Django/FastAPI)...
☆ 6查看技能
GitHub
context-graph
Use when storing decision traces, querying past precedents, or implementing learning loops. Load in COMPLETE state or when needing to learn from history. Covers semantic search with Voyage AI embeddings, Chroma...
☆ 6查看技能
GitHub
determinism
Use when verifying outcomes with code instead of LLM judgment, versioning prompts with hashes, or ensuring reproducible agent behavior. Load for any critical verification. Scripts return boolean exit codes, not...
☆ 6查看技能
GitHub
token-efficient
Use when processing 50+ items, analyzing CSV/log files, executing code in sandbox, or searching for tools. Load for data processing tasks. Achieves 98%+ token savings via in-sandbox execution, progressive discl...
☆ 6查看技能
GitHub
two-agent-harness
This skill sets up a complete two-agent development system based on the "Effective Harnesses for Long-Running Agents" research. It creates initializer-agent (for project planning) and coding-agent (for incremen...
☆ 6查看技能
GitHub
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or...
☆ 6查看技能
GitHub
model-selection
Select appropriate Claude model (Opus 4.5, Sonnet, Haiku) for agents, commands, or Task tool invocations based on task complexity, reasoning depth, and cost/speed requirements.
☆ 6查看技能
GitHub
prompt-engineering
Apply prompting techniques when creating prompts, agents, commands, system instructions, or SKILL.md files. Use for XML tags, multishot examples, chain-of-thought, response prefilling, and Claude 4-specific pat...
☆ 6查看技能
GitHub
knowledge-synthesis
Synthesize knowledge from multiple sources into Zettelkasten notes for Logseq. Use when creating wiki pages, integrating academic research, or building interconnected knowledge with [[links]] and
☆ 6查看技能
GitHub
research-workflow
Apply systematic research methodology for multi-step research, fact-finding, web search, or verification tasks. Use when performing Brave Search, Puppeteer navigation, or synthesizing information from multiple...
☆ 6查看技能
GitHub
rpi-setup-humanlayer
use this skill when a user asks to set up RPI or a "research plan implement" workflow, or to do anything related to RPI skills. if the user says the acronym "RPI" or "rpi" or "humanlayer", you MUST use this ski...
☆ 6查看技能
GitHub
temporal-cli
Master Temporal CLI workflow management with smart query building, payload decoding, and history filtering using temporal, base64, and jq
☆ 6查看技能
GitHub
epistemic-cognitive-guardrails
Discipline epistemique stricte pour eliminer les derives cognitives de Claude. Activation SYSTEMATIQUE sur TOUTES les conversations. Impose: (1) Zero invention/supposition, (2) Honnetete absolue, (3) Vision hol...
☆ 6查看技能
GitHub
sequential-thinking
Dynamic problem-solving through structured sequential thoughts. Use when breaking down complex problems, planning multi-step solutions, analyzing ambiguous requirements, debugging intricate issues, exploring de...
☆ 6查看技能
GitHub
td-ngram-splitter
N-gram generation for text preprocessing
☆ 6查看技能
GitHub
brainstorming
Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and increm...
☆ 6查看技能
GitHub
paper-to-code
Implement AI/ML research papers from scratch when no official code exists. Use when the user wants to reproduce a paper, implement an algorithm from a PDF, build a model architecture from a research paper, or c...
☆ 6查看技能
GitHub
genaiscript
Comprehensive expertise for working with Microsoft's GenAIScript framework - a JavaScript/TypeScript-based system for building automatable LLM prompts and AI workflows. Use when creating, debugging, or optimizi...
☆ 6查看技能
GitHub
fine-tuning-data-generator
Generates comprehensive synthetic fine-tuning datasets in ChatML format (JSONL) for use with Unsloth, Axolotl, and similar training frameworks. Gathers requirements, creates datasets with diverse examples, vali...
☆ 6查看技能
GitHub
thought-patterns
Orchestrates comprehensive cognitive thinking patterns for complex problem-solving. Analyzes tasks to select optimal pattern(s) from foundational, reasoning, creative, metacognitive, specialized, and neurodiver...
☆ 6查看技能
GitHub
agent-patterns
Modular orchestration of agent patterns from Anthropic's engineering guide. Intelligently selects and implements prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer, and autonom...
☆ 6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。