Results for “network-pruning”

Use this skill for content decay analysis, pruning, merging, updating, redirecting, recovery prioritization. Trigger when the task involves seo work related to Content Decay Pruning, implementation, audits, debugging, strategy, or validation.

Create and apply Kubernetes NetworkPolicies to enforce pod-level network segmentation, restrict traffic between pods and namespaces, and block access to cloud metadata endpoints.

Inspect, plan, and invoke safe cleanup for runtime-manager-owned state without binding the workflow to a specific host orchestrator or agent provider.

EL2N: Deep Learning on a Data Diet

Critically audit agent skills and remove content that is outdated, disproven, model-specific, or based on poorly cited sources. Load when improve-skills runs its per-skill cycle, when the user asks to prune skills, remove outdated techniques, check if skills are still valid, verify citations in skills, audit skill sources, or update skills for a new model release. Also triggers on "are these skills still valid", "check for obsolete techniques", "verify skill citations", or "update skills for GPT-5/Claude 4/Gemini 2". Runs before split-skill and compress-skill — removing bad content first means the remaining content is worth preserving.

Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.

Routes NuRec/Neural Reconstruction requests to the correct upstream NVIDIA skill (datasets, conversion, training, rendering, object harvesting, frame cleanup).

Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.

Deletes local git branches whose upstream is gone, removing attached worktrees first.

NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs.

NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs.

Expert network engineer specializing in modern cloud networking, security architectures, and performance optimization. Masters multi-cloud connectivity, service mesh, zero-trust networking, SSL/TLS, global load balancing, and advanced troubleshooting. Handles CDN optimization, network automation, and compliance. Use PROACTIVELY for network design, connectivity issues, or performance optimization.

Reads invocation logs from eval_tracker and recommends which of the 50+ skills to prune or consolidate. Run monthly to keep the skill surface tight. Triggers: "audit skills", "prune skills", "which skills do I never use", "skill cleanup".

Create, manipulate, and analyze complex networks and graphs using the NetworkX Python package, including algorithms, generators, I/O, and visualization.

NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs.

NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs.

NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs.

Internal network assessment. VLAN hopping, ARP spoofing detection, broadcast protocol abuse (LLMNR/NBT-NS/mDNS), network segmentation verification, SNMP enumeration, NFS exposure, router/switch audit, and internal service mapping. Assumes attacker has network access. Uses nmap, arp-scan, nbtscan, snmpwalk, onesixtyone, smbmap, nfs-common, masscan, hping3, and netexec.

Analyze network packet captures (PCAP/PCAPNG) using Wireshark, tshark, tcpdump, and Python to reconstruct communications, extract files, and identify malicious traffic.

Create, manipulate, and analyze complex networks and graphs using the NetworkX Python package.

Configures and troubleshoots network infrastructure: DNS records, reverse proxies, SSL certificates, firewalls, CDNs, and load balancers.

Create, analyze, and visualize complex networks and graphs in Python with NetworkX, including graph algorithms, community detection, synthetic network generation, and multiple I/O formats.

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

Performs advanced network reconnaissance using Nmap's scripting engine, timing controls, evasion techniques, and output parsing to discover hosts, enumerate services, detect vulnerabilities, and fingerprint operating systems across authorized target networks.

Produces NetworkX code with explicit graph kind, node identity, edge multiplicity, direction, attribute schema, weight semantics, and algorithm preconditions, including testing.

CRUD patterns for state slices — consistent `domain/create|read|update|delete` action naming, request/success/failure triples per operation, and normalised `{ byId, allIds }` entity shapes for O(1) lookups. Use when designing a new entity slice, standardising action-type names, or refactoring array-shaped state.

Expert patterns for Neon serverless Postgres, branching, connection pooling, and Prisma/Drizzle integration Use when: neon database, serverless postgres, database branching, neon postgres, postgres serverless.

Build network traffic baselines from NetFlow/IPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly/daily traffic pattern profiling.

Conducts comprehensive network penetration tests against authorized target environments using host discovery, port scanning, service enumeration, vulnerability identification, and controlled exploitation following PTES methodology.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

Implements Kubernetes network policies for micro-segmentation, covering ingress/egress rules, Calico and Cilium, with a Python CLI for managing and validating policies.

嵌入式网络调试工具，用于发现接口、抓包、分析 pcap/pcapng、做连通性测试、端口扫描和流量统计。 当用户提到 Wireshark、tshark、Npcap、抓包、网络联调、端口扫描、连通性排查、pcap 分析、 网络接口、ping 测试、traceroute、流量统计、Modbus TCP、EtherNet/IP 等网络协议调试时自动触发， 也兼容 /net 显式调用。即使用户只是说"抓个包看看"、"扫一下端口"、"网络通不通"或"分析一下这个 pcap"， 只要上下文中出现具体工具名（tshark、Wireshark、Npcap）、协议名（Modbus TCP、EtherNet/IP、ICMP 等）、 调试动作（抓包、端口扫描、连通性测试、ping、traceroute、流量统计、pcap 分析）或网络接口操作，就应触发此 skill。

Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor, Midjourney, image AI, video AI, coding agents, or any other AI tool.

Reduces churn through cancel flows, dunning, and win-back. Use when the user requests 'churn', 'cancel flow', 'dunning', 'win-back', 'failed payment', 'retention rate', or 'save offer'.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.