Results for “pe”

Prevents misguided optimization of MSBuild's ResolveProjectReferences target by explaining that its reported time is wall-clock wait time, not CPU work, and redirects to task self-time analysis.

Scans Android APKs for Firebase security misconfigurations including open databases, storage buckets, authentication issues, and exposed cloud functions. For authorized security research only.

Identify AWS IAM privilege escalation paths by analyzing policies for dangerous permission combinations and least-privilege violations using boto3 and Cloudsplaining-style analysis.

Deploy Zeek network security monitor to capture, parse, and analyze network traffic metadata for threat detection, anomaly identification, and forensic investigation.

Assess the security posture of Kubernetes etcd clusters by evaluating encryption at rest, TLS configuration, access controls, backup encryption, and network isolation.

Manage and use Lambda Labs GPU cloud instances for ML training and inference with SSH access, persistent filesystems, and multi-node clusters.

Makes n8n workflow failures loud, structured, and recoverable by wiring per-node error outputs, retry logic, error-trigger workflows, and proper HTTP response shapes.

Provides multi-language code navigation via persistent LSP daemons, supporting definitions, references, hover, symbols, and diagnostics for Python, TypeScript, Rust, Go, and more.

Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter.

Agent profile for handle CI/CD, environments, build pipelines, deployment topology, secrets, and operational readiness. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Finds the least-privilege Azure RBAC role for an identity, generates CLI commands and Bicep code to assign it, and provides guidance on permissions needed to grant roles.

Manage AWS S3 buckets and objects: create buckets, upload/download files, configure lifecycle policies, set up static websites, manage permissions, and implement cross-region replication.

Query AWS CloudTrail, VPC Flow Logs, S3 access logs, and ALB logs with Athena for forensic investigation of security incidents.

Test for Server-Side Request Forgery vulnerabilities by probing cloud metadata endpoints, internal network services, and protocol handlers through user-controllable URL parameters.

Scan open-source dependencies for known vulnerabilities using Snyk, including CI/CD integration, automated fix PRs, license compliance, and continuous monitoring.

Deploy and operate CAPEv2 sandbox for automated malware analysis with behavioral monitoring, payload extraction, configuration parsing, and anti-evasion capabilities.

Generates modular Terraform infrastructure-as-code for AWS, GCP, or Azure, including VPC, compute, database, cache, CDN, and monitoring with per-environment sizing, remote state, and cost estimates.

Run ML workloads on Modal's serverless GPU cloud: deploy models as auto-scaling APIs, run batch jobs, and schedule tasks with pay-per-second GPU pricing.

Reads BA and TechLead artifacts to produce a sprint plan, task breakdown, and story point estimates, creating one tracked todo per sprint task for live pipeline tracking.

Design and operate Azure Storage services for durability, performance, and secure access. Use this skill when users ask about Blob, Files, Queues, Tables, or Data Lake storage patterns. Covers redundancy, tiering, access models, lifecycle policies, and compliance.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

Deploy an entire redesigned site to AEM Edge Delivery Services by inventorying migrated pages, deduplicating blocks, and driving per-page deployment with tracking and verification.

Write academic papers with a 12-agent pipeline supporting full drafting, revision, citation checks, and LaTeX/DOCX output across multiple disciplines and paper types.

Audit Kubernetes cluster security posture against CIS benchmarks using kube-bench with automated checks for control plane, worker nodes, and RBAC.

Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".

Deep UAT testing for all Perlantir projects. Crawls every page, clicks every button, tests every form, verifies every interaction, takes screenshots for vision analysis, and checks for missing features against project scope. Runs automatically after every deploy.

Orchestrate autonomous AI development pipelines through your Kanban board, managing multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

Query EAS Update health metrics from the CLI: crash rates, install/launch counts, unique users, payload size, and embedded vs OTA user splits per channel.

Guides development of Fastify Node.js backend servers and REST APIs using TypeScript or JavaScript, covering routes, plugins, validation, error handling, authentication, testing, performance, logging, deployment, and more.

Execute cloud-native incident containment across AWS, Azure, and GCP by isolating compromised resources, revoking credentials, preserving forensic evidence, and applying security group restrictions to prevent lateral movement.

Validate Azure deployments against functional, security, performance, and operational criteria before production release. Use this skill when users ask for readiness checks, health verification, or production sign-off gates. Covers Well-Architected Framework validation, SLA verification, and release readiness.

Measure Core Web Vitals on any URL — LCP, CLS, INP, TTFB, FCP — using the browser's own performance APIs. Grades each metric against Google's thresholds and produces an A-F report. Playwright MCP only, no signup.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Performs deep root cause analysis on NVIDIA TAO Visual ChangeNet classification experiments, using image-evidence-driven investigation to diagnose model failures and produce actionable reports.

Capture a full DevTools-protocol trace of any browser automation, bisect the stream into per-page searchable buckets, and attach a trace to an in-progress session for debugging.

Build, deploy, evaluate, debug, and measure latency for a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection and VLM classification.