Claude Skills by yanacuti1121

Implement a structured threat intelligence lifecycle encompassing planning,

'Implements threat modeling using the MITRE ATT&CK framework to map adversary

'Implements an integrated incident ticketing system connecting SIEM alerts

'Implements USB device control policies to restrict unauthorized removable

Deploy and configure Velociraptor for scalable endpoint forensic artifact

Deploy and operate Greenbone/OpenVAS vulnerability management using the

Vulnerability remediation SLAs define mandatory timeframes for patching

Build automated alerting for vulnerability remediation SLA breaches with

'Configure ModSecurity WAF with OWASP Core Rule Set (CRS) for web application

Zero-Knowledge Proofs (ZKPs) allow a prover to demonstrate knowledge

Deploy CyberArk Secure Cloud Access to eliminate standing privileges

Implement NextDNS as a zero trust DNS filtering layer with encrypted

'Implementing zero trust access controls for SaaS applications using

'This skill guides organizations through implementing zero trust architecture

Implement Zero Trust Network Access using Zscaler Private Access (ZPA)

'Implementing Zero Trust Network Access (ZTNA) in cloud environments

Deploy Google BeyondCorp Enterprise zero trust access controls using

Implement HashiCorp Boundary for identity-aware zero trust infrastructure

In-memory vector index with JSON persistence for small-scale agent RAG. Upsert/query/delete embeddings, cosine similarity search, JSON snapshot save/load, and memory-budget enforcement. Sources: wseagar/vector-storage.

Run and document production incidents — severity classification, incident commander role, communication cadence, triage steps, post-incident review (PIR/postmortem) generation, and action item tracking. Use when asked about "incident response", "how to run an incident", "postmortem template", "PIR", "on-call runbook", "severity levels", or when a production issue is actively happening. Do NOT use for: SLO target design — use `slo-design`.

Semantic codebase ingestion — given a topic or repo URL, agent maps the dependency graph, identifies key entry points, filters noise files, and synthesizes a structured spec. BloopAI-inspired semantic search over code at macro scale. Triggered by /ingest-repo.

INI configuration file parsing for legacy and system configs. Flat and sectioned INI, special character handling, environment variable substitution, and safe stringify. Sources: isaacs/ini.

Học hành vi từ session thực tế — tạo atomic instincts với confidence scoring, tự động activate khi gặp pattern tương tự. Bản đơn giản hơn continuous-learning-v2.

Use when extracting structured data (JSON, typed objects) from LLM responses with validation and retries. Triggers on: 'instructor', 'structured output', 'extract JSON from LLM', 'pydantic llm', 'LLM return JSON', 'trích xuất dữ liệu từ LLM', 'LLM trả về JSON', 'parse LLM output', 'validated LLM output', 'schema extraction'.

'This skill covers integrating OWASP ZAP (Zed Attack Proxy) for Dynamic

'This skill covers integrating Static Application Security Testing (SAST)

'Intercepts and analyzes HTTP/HTTPS traffic from mobile applications

Make interfaces feel responsive and alive — micro-interactions, spring physics, press states, optimistic updates, skeleton loaders, cursor feedback, sound design hints, and delight moments. Use when asked to "make this feel better", "interface feels unresponsive", "add micro-interactions", "the UI feels dead", "springy animations", "delight", "optimistic UI", "skeleton screen", "cursor feedback", "feel more like a native app", "haptic feedback patterns", or "interface lacks personality". Do N...

'Investigates insider threat indicators including data exfiltration attempts,

'Investigates phishing email incidents from initial user report through

Identify, collect, and analyze ransomware attack artifacts to determine

4-agent parallel investment research team modeled after legendary investors. business-analyst (Duan Yongping lens), financial-analyst (Buffett lens), industry-researcher (Munger lens), risk-assessor (Li Lu lens). team-lead synthesizes into a single verdict. Inspired by ai-berkshire (MIT).

Istio service mesh traffic management for agent clusters. VirtualService routing, DestinationRule load balancing, circuit breaking, canary deployments, mTLS policies, and fault injection. Sources: istio/istio (Apache-2.0).

Jaeger distributed trace collection and visualization. OTLP ingest, sampling strategies, trace analysis, latency bottleneck detection, and agent chain root-cause analysis. Sources: jaegertracing/jaeger (Apache-2.0).

Production-grade RAG system patterns — keyword search foundations + vector hybrid retrieval, FastAPI, OpenSearch, Airflow pipelines. Dùng khi build RAG cho production.

Jepsen-style distributed system fault injection patterns. Network partition simulation, clock skew injection, process kill scenarios, linearizability checkers, and fault-tolerance test design. Sources: jepsen-io/jepsen (EPL-1.0).

Automated Jest test case generation from AST and type signatures. Bazel rules_jest integration, property-based test scaffolding, snapshot generation, and coverage-driven test augmentation. Sources: aspect-build/rules_jest (Apache-2.0).

Coding Interview University — John Washam's CS study plan để land job tại FAANG. Data structures, algorithms, system design. Checklist-based, forked 400K+. CC BY-SA 4.0.

JWT/JWS/JWE token patterns for Swarm Bus agent identity. Sign JWTs with ES256/RS256, verify claims, encrypt payloads with JWE (A256GCM), short-lived token rotation, and agent-to-agent bearer auth. Sources: panva/jose.

JWT sign/verify with claim validation and privilege-decay enforcement. auth0/node-jsonwebtoken patterns, algorithm lockdown, expiry enforcement, scope-based authorization, and token blacklisting. Sources: auth0/node-jsonwebtoken.

Kubernetes JavaScript client for agent-driven cluster operations. Pod CRUD, Deployment scaling, namespace isolation, ConfigMap injection, log streaming, and exec into containers. Sources: kubernetes-client/javascript (Apache-2.0).

Kubernetes Custom Resource Definitions and controller reconciliation loop patterns. CRD schema design, controller-runtime reconciler, desired-state diffing, and agent lifecycle as a K8s-native resource. Sources: kubernetes/kubernetes (Apache-2.0).

SQLite task board for structured multi-agent parallelization. Workers claim tasks, send heartbeats, request approval gates, and spawn child tasks. Use when orchestrating 3+ parallel agents on a complex project with dependencies.

Keccak256 and ethers.js cryptographic utilities for hash-chain integrity. keccak256 of log entries, ABI encoding, hex data manipulation, event topic hashing, and Ethereum-compatible hash structures. Sources: ethers-io/ethers.js.

Khoj — open-source self-hostable AI second brain: chat với docs + web, semantic search, custom agents, image gen, TTS. Multi-LLM (Claude/GPT/Gemini/Ollama). Browser/Obsidian/Phone.

ktlint anti-bikeshedding Kotlin linter. Zero-config formatting, custom rule sets, auto-fix, Git pre-commit integration, and Gradle plugin setup. Sources: pinterest/ktlint (MIT).

Design and debug Kubernetes workloads — Deployment/StatefulSet patterns, resource requests/limits, liveness/readiness/startup probes, HPA/KEDA autoscaling, ConfigMap/Secret injection, PodDisruptionBudget, rolling update strategy, and debugging CrashLoopBackOff. Use when asked about "Kubernetes deployment", "k8s", "pod crashing", "CrashLoopBackOff", "OOMKilled", "resource limits", "liveness probe", "readiness probe", "HPA", "horizontal pod autoscaler", "rolling update", "kubectl debug", "pod n...

KV-cache optimization patterns for LLM inference. Prefix caching, sliding window attention, cache reuse across turns, static cache for fixed prompts, and TTFT reduction strategies. Sources: huggingface/transformers (Apache-2.0).

Review L2 session facts and promote valuable ones to L1 Atomic Memory. Use at end of session or when L2 accumulates facts worth keeping permanently. Runs add-fact.sh for each promoted fact.

Use when the user wants to generate or keep repository documentation up to date via OpenWiki (langchain-ai/openwiki) — an LLM-driven CLI that writes a wiki for a codebase (or a personal knowledge base from Notion/Gmail/Slack/X/web search) and keeps it fresh via a scheduled CI pull request. Examples: \"set up OpenWiki for this repo\", \"keep the docs updated automatically\", \"generate an agent wiki\".