anthropic-cybersecurity-skills
Provides 754 structured skills for AI-driven security operations. Maps them to MITRE ATT&CK, NIST CSF, ATLAS, D3FEND, and NIST AI RMF.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Provides 754 structured skills for AI-driven security operations. Maps them to MITRE ATT&CK, NIST CSF, ATLAS, D3FEND, and NIST AI RMF.
Designs serverless AWS architectures and infrastructure-as-code templates, including CloudFormation. Covers CI/CD setup, AWS migration, and cost optimization across Lambda, API Gateway, DynamoDB, ECS, and Aurora.
Structures experiment plans into initial implementation, baseline tuning, creative research, and ablation stages. Specifies datasets, comparison baselines, hyperparameter sweeps, and evaluation metrics.
Supports right-censored and competing-risk survival workflows. Covers leakage-safe preprocessing, model selection, probability prediction, and censoring-aware evaluation metrics.
Runs model evaluations on local hardware using inspect-ai and lighteval. Guides local GPU evaluation and backend selection among vLLM, Transformers, and accelerate; excludes cloud job orchestration and evaluation publication.
Moves learned patterns from MEMORY.md into CLAUDE.md or .claude/rules/. Makes proven agent behaviors subject to permanent enforcement.
Configures ElevenLabs agents, tools, and knowledge bases and integrates web, mobile, and server SDKs. Supports voice systems and troubleshooting package deprecations, webhooks, CSP, allowlists, and tool parsing.
Ingests documents, web pages, video, and audio into research notebooks. Supports AI notes, summaries, document chat, full-text and vector search, custom transformations, and multi-speaker podcasts across multiple AI providers.
Supports URL extraction, entity discovery, structured enrichment, and recurring web monitoring. Suits current-evidence research, academic-source discovery, repeated lookups, and exhaustive reports.
Supports hierarchical Bayesian models, MCMC with NUTS, and variational inference. Includes LOO and WAIC model comparison and posterior checks.
Handles stable Paseo releases as a new patch or minor version. Also supports promoting an existing beta release to stable.
Sets up or updates foundational profile information for social media work. Creates a shared context document covering voice, audience, content pillars, and platform preferences for other social media skills to reference.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name