GitHub
setup-ralph
Setup the Ralph autonomous AI coding loop - ships features while you sleep
Skills IA testing security llm ai
Découvrez les skills testing security llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: testing security llm ai
testing security llm ai Effacer les filtres
Explorer
GitHub
research-expert
Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.
GitHub
skill-creator
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
GitHub
prompt-engineering
Advanced prompt engineering techniques for optimal AI responses. Use this when crafting prompts, optimizing AI interactions, or designing system prompts for applications.
GitHub
evaluation
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
GitHub
help
Show Inference Confidenz help and documentation
GitHub
skill-creator
Meta-skill for creating high-quality Claude Code skills
GitHub
ai-collaborate-teaching
Design co-learning experiences using the Three Roles Framework (AI as Teacher/Student/Co-Worker). Use when teaching AI-driven development workflows, spec-first collaboration, or balancing AI assistance with fou...
GitHub
assemble-dialogue
Instructions for Stage 3 dialogue assembly, combining requests, traces, and captions into final JSON format
GitHub
observer-sys
Metacognitive Analyzer and Form Selector (Observer).
GitHub
skill-maintenance
Use when creating, updating, auditing, or validating Agent Skills. Provides validation scripts and guidance for keeping skills accurate and compliant with the Agent Skills specification.
GitHub
skill-converter
スキルを各AI Agent固有のフォーマットに変換する。「スキルを変換」「convert skill」などと言われたときに使用する
GitHub
skill-importer
Standardized procedure to import external skills (e.g. from anthropics/skills) into the workspace.
GitHub
llm-doc-writer
Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.
GitHub
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.
GitHub
agent-skills
Create, use, and manage Agent Skills for Claude. Use when working with Skills, creating custom capabilities, or understanding how Skills extend Claude's functionality. Covers Skill architecture, file structure,...
GitHub
growth-hacker
Generate growth strategies and ready-to-publish marketing content for product growth. Use when planning launches, assessing product-market fit, creating marketing content, designing experiments, optimizing acti...
GitHub
rlhf-feedback
Autonomous RLHF feedback capture - Claude self-captures mistakes and successes
GitHub
snowtower-maintainer
Maintains SnowTower project documentation, README, and Claude configuration. Use when updating documentation, auditing .claude folder contents, syncing README with actual project state, or reviewing agent/patte...
GitHub
video-script-generator
Generate short video scripts for oral broadcast from article content. Automatically analyzes content and outputs scripts in one of three template types. Outputs style analysis report, system instruction, and re...
GitHub
collaborative-design
実装方針・作業内容の吟味・修正を、ユーザーとAIの会話で行う。ユーザーからの指示があるまでは、勝手にコーディング作業に取りかからない
GitHub
create-game-assets
Generate game assets (sprites, UI icons, backgrounds, tilesets) using DALL-E 3 from a YAML specification file. Use when user asks to create game art, generate sprites, or make game graphics.
GitHub
qdrant-expert
A specialized guide for managing Qdrant Cloud collections, optimizing vector schemas for RAG, and executing precise semantic search queries in Python.
GitHub
research-agent-optimization
Optimize the research agent for rate limit handling, API call efficiency, web search integration fixes, and improved streaming UX with granular progress updates and source attribution.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.