GitHub
my-llm-sdk
Use when working with my-llm-sdk
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
filter-duplicates
Fast pre-filter to remove articles already processed. Uses Redis for O(1) URL lookup to avoid wasting LLM calls on previously seen content.
GitHub
analyze-article
Use LLM to analyze a raw article. Generates summary, extracts entities, categorizes content, assigns importance score, and detects breaking news.
GitHub
compose-digest
Compose a formatted news digest from processed articles and trends. Uses LLM to generate cohesive narrative summary with embedded citations. Formats for Discord readability.
GitHub
context-compression
Compresses large text into minimal tokens while retaining key facts, entities, themes, and events. Used for reducing context window usage.
GitHub
customer-research
This skill should be used when the user asks to "understand customers", "customer research", "user personas", "customer needs analysis", "buyer journey mapping", "voice of customer", "customer segmentation", "u...
GitHub
r-development
Modern R development practices emphasizing tidyverse patterns (dplyr 1.1 and later, native pipe, join_by, .by grouping), rlang metaprogramming, performance optimization, and package development. Use when Claude...
GitHub
technology-assessment
This skill should be used when the user asks to "assess technology", "technology evaluation", "tech stack analysis", "technical feasibility", "technology trends", "build vs buy", "technology roadmap", "architec...
GitHub
agents-py
Build LiveKit Agent backends in Python. Use this skill when creating voice AI agents, voice assistants, or any realtime AI application using LiveKit's Python Agents SDK (livekit-agents). Covers AgentSession, Ag...
GitHub
trend-modeling
This skill should be used when the user asks to "model trends with limited data", "three-valued logic analysis", "scenario generation", "transitional graphs", "qualitative trend analysis", "uncertain data analy...
GitHub
mission-solo
HOUSTON executes feature tasks directly. No agents. Best for small features (1-3 tasks).
GitHub
agents-ts
Build LiveKit Agent backends in TypeScript or JavaScript. Use this skill when creating voice AI agents, voice assistants, or any realtime AI application using LiveKit's Node.js Agents SDK (@livekit/agents-js)....
GitHub
context-engineering-pack
Summit/IntelGraph context-engineering skill pack. Routes to the vendored Agent Skills for Context Engineering library via progressive disclosure, and applies repo-specific guardrails (atomic PRs, evidence, gove...
GitHub
smoke-test
Run smoke tests to verify the Everruns system works correctly.
GitHub
prompt-engineer
MUST use when editing CLAUDE.md, SKILL.md, or slash commands. Applies prompt engineering best practices regardless of task size.
GitHub
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
GitHub
smart-router
Multi-tier LLM routing for cost optimization in the BidDeed.AI ecosystem. Routes tasks to appropriate model tier based on complexity, achieving 90% FREE tier processing. Use when making API calls, selecting mod...
GitHub
skill-creator
Guide for creating effective skills that extend Claude's capabilities
GitHub
learning-documentation-skill
Document learning insights and activities to Supabase with proper categorization, formatting, and retrieval patterns
GitHub
adhd-task-management
ADHD-optimized task tracking and intervention system. Use when tracking tasks, detecting context switches, providing accountability interventions, or managing ADHD-specific productivity patterns for Ariel Shapi...
GitHub
adhd-productivity
ADHD-optimized productivity techniques and interventions. Invoke when user shows signs of task abandonment, context switching, or needs focus assistance.
GitHub
content-research-writer
Creates high-quality content (blog posts, tweets, newsletters, documentation) that matches the user's writing style and voice. Performs web research to find citations and supporting evidence. Use when user requ...
GitHub
agent-sdk-dev
Expert guide for claude-agent-sdk development questions - tools, subagents, permissions, hooks, sessions, MCP integration, and best practices.
GitHub
context-retriever
The "Recall Engine". Fetches history, decisions, and tasks related to a person or topic.
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.