GitHub
adversarial-training
Defensive techniques using adversarial examples to improve model robustness and security
Skills IA Données et IA
Découvrez les skills Données et IA, comparez leurs dépôts et consultez leurs instructions.
Catégories: Données et IA
Données et IA Effacer les filtres
Explorer
GitHub
automated-testing
CI/CD integration and automation frameworks for continuous AI security testing
GitHub
code-injection
Test AI systems for code injection vulnerabilities including prompt-to-code attacks and agent exploitation
GitHub
model-extraction
Techniques to extract model weights, architecture, and training data through API queries
GitHub
certifications-training
Professional certifications, CTF competitions, and training resources for AI security practitioners
GitHub
red-team-reporting
Professional security report generation, executive summaries, finding documentation, and remediation tracking
GitHub
security-testing
Comprehensive security testing automation for AI/ML systems with CI/CD integration
GitHub
prompt-injection-testing
Master prompt injection attacks, jailbreak techniques, input manipulation, and payload crafting for LLM security testing
GitHub
benchmark-datasets
Standard datasets and benchmarks for evaluating AI security, robustness, and safety
GitHub
git-basics
Git fundamentals - init, add, commit, status, log, and core concepts
GitHub
basic-workflow
Daily Git workflow - add, commit, push, pull cycle for everyday development
GitHub
collaboration
Team collaboration - remote, fetch, pull, push, clone, and team workflows
GitHub
branching
Git branching strategies - create, switch, merge, rebase, and workflows
GitHub
github-features
GitHub platform features - PRs, issues, actions, projects, and automation
GitHub
git-intro
Introduction to Git version control - what, why, and first steps
GitHub
advanced-git
Advanced Git - interactive rebase, cherry-pick, bisect, reflog, and power user operations
GitHub
verification-before-completion
Use when about to claim work is complete, fixed, or passing. Run verification commands and confirm output before making any success claims. Evidence before assertions.
GitHub
test-driven-development
Use when implementing any feature or bugfix. Write the test first, watch it fail, write minimal code to pass. Red-Green-Refactor cycle.
GitHub
brainstorming
Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
GitHub
subagent-driven-development
Use when executing implementation plans with independent tasks. Dispatches subagents per task with two-stage review (spec then quality).
GitHub
executing-plans
Use when you have a written implementation plan to execute. Load plan, review critically, execute tasks in batches with verification.
GitHub
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code. Creates detailed implementation plans with bite-sized tasks.
GitHub
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. Always find root cause before attempting fixes. Evidence before assertions.
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...
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.