Browse Skills — Page 213

perf-cpu-offloading

NVIDIA-NeMo/Megatron-Bridge

Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.

perf-cuda-graphs

NVIDIA-NeMo/Megatron-Bridge

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

perf-expert-parallel-overlap

NVIDIA-NeMo/Megatron-Bridge

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.

perf-host-analysis

NVIDIA/skills

>

perf-host-optimization

NVIDIA/skills

Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.

perf-hybrid-context-parallel

NVIDIA-NeMo/Megatron-Bridge

Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

perf-investigation-logger

ComposioHQ/awesome-claude-plugins

"Use when appending structured perf investigation notes and evidence."

perf-lighthouse

tech-leads-club/agent-skills

Run Lighthouse audits locally via CLI or Node API, parse and interpret reports, and set performance budgets. Use when measuring site performance, understanding Lighthouse scores, setting up budgets, or integrating audits into CI. Triggers on: lighthouse, run lighthouse, lighthouse score, performance audit, performance budget. Do NOT use for fixing specific performance issues (use perf-web-optimization or core-web-vitals) or Astro-specific optimization (use perf-astro).

perf-megatron-fsdp

NVIDIA-NeMo/Megatron-Bridge

Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

perf-memory-tuning

NVIDIA-NeMo/Megatron-Bridge

Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.

perf-moe-comm-overlap

NVIDIA-NeMo/Megatron-Bridge

MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

perf-moe-dispatcher-selection

NVIDIA-NeMo/Megatron-Bridge

Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.

perf-moe-hardware-configs

NVIDIA-NeMo/Megatron-Bridge

Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.

perf-moe-long-context

NVIDIA-NeMo/Megatron-Bridge

Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.

perf-moe-optimization-workflow

NVIDIA-NeMo/Megatron-Bridge

Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.

perf-moe-vlm-training

NVIDIA-NeMo/Megatron-Bridge

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.

perf-nsight-compute-analysis

NVIDIA/skills

>

perf-nsight-systems

NVIDIA/skills

>-

perf-optimization

NVIDIA/skills

>

perf-parallelism-strategies

NVIDIA-NeMo/Megatron-Bridge

Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.

perf-profile

pixel-cellar/Claude-Code-Game-Studios

结构化的性能分析工作流。识别瓶颈、与性能预算对比测量，并生成带有优先级排序的优化建议。

perf-profiler

ComposioHQ/awesome-claude-plugins

"Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence."

perf-sequence-packing

NVIDIA-NeMo/Megatron-Bridge

Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying the right CP constraints.

perf-theory-gatherer

ComposioHQ/awesome-claude-plugins

"Use when generating performance hypotheses backed by git history and code evidence."

perf-theory-tester

ComposioHQ/awesome-claude-plugins

"Use when running controlled perf experiments to validate hypotheses."

perf-torch-cuda-graphs

NVIDIA/skills

>-

perf-torch-sync-free

NVIDIA/skills

>-

perf-tp-dp-comm-overlap

NVIDIA-NeMo/Megatron-Bridge

Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

perf-web-optimization

tech-leads-club/agent-skills

Optimize web performance: bundle size, images, caching, lazy loading, and overall page speed. Use when site is slow, reducing bundle size, fixing layout shifts, improving Time to Interactive, or optimizing for Lighthouse scores. Triggers on: web performance, bundle size, page speed, slow site, lazy loading. Do NOT use for Core Web Vitals-specific fixes (use core-web-vitals), running Lighthouse audits (use perf-lighthouse), or Astro-specific optimization (use perf-astro).

perf-workload-profiling

NVIDIA/skills

>

performance

addyosmani/web-quality-skills

Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit".

Performance Accessibility

Community-Access/accessibility-agents

Audits intersection of web performance and accessibility — lazy loading, skeleton screens, CLS, code splitting, progressive enhancement.

performance-analytics

serac-labs/serac

Build ServiceNow Performance Analytics — pa_indicators (count/sum/avg/percentage), pa_breakdowns, pa_thresholds with severity colors, pa_widgets, and pa_dashboards for KPI tracking.

performance-analyzer

aaron-he-zhu/aaron-marketing-skills

Use when the user asks to "analyze influencer campaign performance", "compare influencers", or "find what content worked"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator.

performance-attribution

HKUDS/Vibe-Trading

Performance attribution analysis — Brinson sector/stock-selection attribution, factor alpha/beta decomposition, market-timing evaluation, and benchmark comparison framework.

performance-benchmarking

elophanto/EloPhanto

Measure, analyze, and improve system performance with load testing, Core Web Vitals optimization, and capacity planning. Adapted from msitarzewski/agency-agents.

performance-budget

mohitagw15856/pm-claude-skills

Define and document performance budgets for a web service or application. Use when asked to set performance targets, define SLOs for latency or throughput, establish Core Web Vitals targets, create a performance baseline, or document performance regression policy. Produces a structured performance budget covering key user journeys, Core Web Vitals, backend latency SLOs, measurement tooling, CI enforcement, and breach response process.

performance-check

indranilbanerjee/digital-marketing-pro

Pull live marketing metrics for a performance snapshot: KPIs vs targets, trend comparison, and cross-platform overview. Use when checking current marketing performance, monitoring KPI health, comparing to benchmarks, or getting a quick status update across analytics platforms.

performance-cycle

techwolf-ai/ai-first-toolkit

Evidence gathering for performance review cycles. Gathers goal completion evidence, peer feedback, development progress, scope changes, and values alignment, organised along the org's performance framework dimensions, with organizational values as the 'how' lens. Surfaces evidence gaps. Never suggests ratings, only organises evidence for the manager's judgment.

performance-engineer

benjaminasterA/antigravity-awesome-skills

Expert performance engineer specializing in modern observability,

performance-engineer-v2

diegosouzapw/awesome-omni-skills

performance-engineer workflow skill. Use this skill when the user needs Expert performance engineer specializing in modern observability, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

performance-engineer-v3

diegosouzapw/awesome-omni-skills

performance-engineer workflow skill. Use this skill when the user needs Expert performance engineer specializing in modern observability, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

performance-extraction

yogsoth-ai/de-anthropocentric-research-engine

Systematically extract performance data and conditions from papers — 30 methods, 150 data points, 40 web searches budget

performance-insights

anthropics/commerce-agents

Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales, traffic, conversion, and customers or this operation's equivalents that the snapshot alone does not answer. Not needed when the snapshot's headline figures and their change on the prior period answer the question, how a period went included.

performance-management

mkurman/zorai

>

performance-monitor

aaron-he-zhu/aaron-marketing-skills

Use when the user asks to "generate an SEO report", "出月报", "set SEO alerts", or "排名掉了提醒我"; two modes — report builds multi-metric traffic/ranking/authority/content dashboards, and alert configures threshold notifications for future ranking, traffic, technical, backlink, competitor, and AI-visibility changes. Not for raw position-by-position deltas — use rank-tracker. SEO报告/绩效仪表盘/SEO预警/排名监控

performance-optimization

addyosmani/agent-skills

Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.

performance-optimizer

diegosouzapw/awesome-omni-skills

Performance Optimizer workflow skill. Use this skill when the user needs Identifies and fixes performance bottlenecks in code, databases, and APIs. Measures before and after to prove improvements and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

performance-optimizer-v2

diegosouzapw/awesome-omni-skills

Performance Optimizer workflow skill. Use this skill when the user needs Identifies and fixes performance bottlenecks in code, databases, and APIs. Measures before and after to prove improvements and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

performance-profiler

alirezarezvani/claude-skills

Systematic performance profiling for Node.js, Python, and Go applications. Identifies CPU, memory, and I/O bottlenecks, generates flamegraphs, analyzes bundle sizes, optimizes database queries, runs load tests with k6 and Artillery. Always measures before and after. Use when investigating a slow endpoint, planning a performance budget, or hunting a memory leak in production.

performance-profiling

softspark/ai-toolkit

Performance: golden signals, p50/p95/p99, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, bottleneck, memory leak.

performance-profiling-v2

diegosouzapw/awesome-omni-skills

Performance Profiling workflow skill. Use this skill when the user needs Performance profiling principles. Measurement, analysis, and optimization techniques and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

performance-report

modu-ai/cowork-plugins

|

performance-report

anthropics/knowledge-work-plugins

Build a marketing performance report with key metrics, trend analysis, wins and misses, and prioritized optimization recommendations. Use when wrapping a campaign, when preparing weekly, monthly, or quarterly channel summaries for stakeholders, or when you need data translated into an executive summary with next-period priorities.

performance-review

mohitagw15856/pm-claude-skills

Write structured, balanced performance reviews from bullet-point inputs. Use when asked to write a performance review, self-assessment, peer review, 360 feedback, or manager evaluation. Produces a complete, fair, professionally written review covering achievements, areas for growth, and development goals.

performance-review

anthropics/knowledge-work-plugins

Structure a performance review with self-assessment, manager template, and calibration prep. Use when review season kicks off and you need a self-assessment template, writing a manager review for a direct report, prepping rating distributions and promotion cases for calibration, or turning vague feedback into specific behavioral examples.

performance-review-prep

Significant-Gravitas/skills-catalog

Assemble a review pack from dated, job-related evidence and flag vague or one-sided wording.

performance-review-writer

github/awesome-copilot

Draft performance reviews, self-assessments, peer reviews, and upward feedback in your own voice. Analyzes your contributions, emails, and meeting history via WorkIQ, then produces honest, impact-focused drafts using the STAR format. USE FOR: write my performance review, draft self-assessment, peer review, 360 feedback, annual review, mid-year review, upward feedback, write review for colleague, performance appraisal.

performance-reviewer

TerminalSkills/skills

>-

performance-table-assembly

yogsoth-ai/de-anthropocentric-research-engine

Assemble unified comparison table with confidence interval annotations

performance-testing-review-ai-review

benjaminasterA/antigravity-awesome-skills

You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C

performance-testing-review-ai-review-v2

diegosouzapw/awesome-omni-skills

AI-Powered Code Review Specialist workflow skill. Use this skill when the user needs You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

performance-testing-review-multi-agent-review

benjaminasterA/antigravity-awesome-skills

Use when working with performance testing review multi agent review

performance-testing-review-multi-agent-review-v2

diegosouzapw/awesome-omni-skills

Multi-Agent Code Review Orchestration Tool workflow skill. Use this skill when the user needs working with performance testing review multi agent review and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

performing-access-recertification-with-saviynt

mukul975/Anthropic-Cybersecurity-Skills

Configure and execute access recertification campaigns in Saviynt Enterprise Identity Cloud to validate user entitlements, revoke excessive access, and maintain compliance with SOX, SOC2, and HIPAA.

performing-access-review-and-certification

mukul975/Anthropic-Cybersecurity-Skills

Conduct systematic access reviews and certifications to ensure users have appropriate access rights aligned with their roles. This skill covers review campaign design, reviewer selection, risk-based p

performing-account-takeover-attacks

xalgord/xalgorix

Systematically testing authentication, recovery, and identity flows for account takeover (ATO) — including

performing-active-directory-bloodhound-analysis

mukul975/Anthropic-Cybersecurity-Skills

Use BloodHound and SharpHound to enumerate Active Directory relationships and identify attack paths from compromised users to Domain Admin.

performing-active-directory-compromise-investigation

mukul975/Anthropic-Cybersecurity-Skills

Investigate Active Directory compromise by analyzing authentication logs, replication metadata, Group Policy changes, and Kerberos ticket anomalies to identify attacker persistence and lateral movement paths.

performing-active-directory-forest-trust-attack

mukul975/Anthropic-Cybersecurity-Skills

Enumerate and audit Active Directory forest trust relationships using impacket for SID filtering analysis, trust key extraction, cross-forest SID history abuse detection, and inter-realm Kerberos ticket assessment.

performing-active-directory-penetration-test

mukul975/Anthropic-Cybersecurity-Skills

Conduct a focused Active Directory penetration test to enumerate domain objects, discover attack paths with BloodHound, exploit Kerberos weaknesses, escalate privileges via ADCS/DCSync, and demonstrate domain compromise.

performing-active-directory-vulnerability-assessment

mukul975/Anthropic-Cybersecurity-Skills

Assess Active Directory security posture using PingCastle, BloodHound, and Purple Knight to identify misconfigurations, privilege escalation paths, and attack vectors.

performing-adversary-in-the-middle-phishing-detection

mukul975/Anthropic-Cybersecurity-Skills

Detect and respond to Adversary-in-the-Middle (AiTM) phishing attacks that use reverse proxy kits like EvilProxy, Evilginx, and Tycoon 2FA to bypass MFA and steal session tokens.

performing-agentless-vulnerability-scanning

mukul975/Anthropic-Cybersecurity-Skills

Configure and execute agentless vulnerability scanning using network protocols, cloud snapshot analysis, and API-based discovery to assess systems without installing endpoint agents.

performing-ai-assisted-vulnerability-discovery

xalgord/xalgorix

Using LLMs to accelerate vulnerability research and pentest workflows — generating syntax-valid fuzzing

performing-ai-driven-osint-correlation

mukul975/Anthropic-Cybersecurity-Skills

>-

performing-alert-triage-with-elastic-siem

mukul975/Anthropic-Cybersecurity-Skills

Perform systematic alert triage in Elastic Security SIEM to rapidly classify, prioritize, and investigate security alerts for SOC operations.

performing-android-app-static-analysis-with-mobsf

mukul975/Anthropic-Cybersecurity-Skills

>

performing-api-fuzzing-with-restler

mukul975/Anthropic-Cybersecurity-Skills

>

performing-api-inventory-and-discovery

mukul975/Anthropic-Cybersecurity-Skills

>

performing-api-rate-limiting-bypass

mukul975/Anthropic-Cybersecurity-Skills

>

performing-api-security-testing-with-postman

mukul975/Anthropic-Cybersecurity-Skills

>

performing-arp-spoofing-attack-simulation

mukul975/Anthropic-Cybersecurity-Skills

>

performing-asset-criticality-scoring-for-vulns

mukul975/Anthropic-Cybersecurity-Skills

Develop and apply a multi-factor asset criticality scoring model to weight vulnerability prioritization based on business impact, data sensitivity, and operational importance.

performing-authenticated-scan-with-openvas

mukul975/Anthropic-Cybersecurity-Skills

Configure and execute authenticated vulnerability scans using OpenVAS/Greenbone Vulnerability Management with SSH and SMB credentials for comprehensive host-level assessment.

performing-authenticated-vulnerability-scan

mukul975/Anthropic-Cybersecurity-Skills

Authenticated (credentialed) vulnerability scanning uses valid system credentials to log into target hosts and perform deep inspection of installed software, patches, configurations, and security sett

performing-automated-malware-analysis-with-cape

mukul975/Anthropic-Cybersecurity-Skills

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

performing-aws-account-enumeration-with-scout-suite

mukul975/Anthropic-Cybersecurity-Skills

Perform comprehensive security posture assessment of AWS accounts using ScoutSuite to enumerate resources, identify misconfigurations, and generate actionable security reports.

performing-aws-privilege-escalation-assessment

mukul975/Anthropic-Cybersecurity-Skills

>

performing-bandwidth-throttling-attack-simulation

mukul975/Anthropic-Cybersecurity-Skills

>

performing-binary-exploitation-analysis

mukul975/Anthropic-Cybersecurity-Skills

>

performing-blind-ssrf-exploitation

mukul975/Anthropic-Cybersecurity-Skills

Detect and exploit blind Server-Side Request Forgery vulnerabilities using out-of-band techniques, DNS interactions, and timing analysis to access internal services and cloud metadata endpoints.

performing-bluetooth-security-assessment

mukul975/Anthropic-Cybersecurity-Skills

Assess Bluetooth Low Energy device security by scanning, enumerating GATT services, and detecting vulnerabilities

performing-brand-monitoring-for-impersonation

mukul975/Anthropic-Cybersecurity-Skills

Monitor for brand impersonation attacks across domains, social media, mobile apps, and dark web channels to detect phishing campaigns, fake sites, and unauthorized brand usage targeting your organization.

performing-clickjacking-attack-test

mukul975/Anthropic-Cybersecurity-Skills

Testing web applications for clickjacking vulnerabilities by assessing frame embedding controls and crafting proof-of-concept overlay attacks during authorized security assessments.

performing-cloud-asset-inventory-with-cartography

mukul975/Anthropic-Cybersecurity-Skills

Perform comprehensive cloud asset inventory and relationship mapping using Cartography to build a Neo4j security graph of infrastructure assets, IAM permissions, and attack paths across AWS, GCP, and Azure.

performing-cloud-forensics-investigation

mukul975/Anthropic-Cybersecurity-Skills

Conduct forensic investigations in cloud environments by collecting and analyzing logs, snapshots, and metadata from AWS, Azure, and GCP services.

performing-cloud-forensics-with-aws-cloudtrail

mukul975/Anthropic-Cybersecurity-Skills

Perform forensic investigation of AWS environments using CloudTrail logs to reconstruct attacker activity, identify compromised credentials, and analyze API call patterns.

performing-cloud-incident-containment-procedures

mukul975/Anthropic-Cybersecurity-Skills

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.

performing-cloud-log-forensics-with-athena

mukul975/Anthropic-Cybersecurity-Skills

>