Performance & cost
7,008 rows, by stacks then stars
853 of these skill files have been read, by 797 distinct authors, and what they tell an agent counted. What Performance & cost authors agree on, and what they forbid
napoler/skill-fix/skills/skill-creator Skill
1★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Thanasimos/Thanas-flare-builders-toolkit/gas-optimize Skill
1★ repoAnalyze a Solidity contract for gas optimization opportunities. Identifies savings with specific techniques, gas numbers, and before/after code. Covers L1 and L2 considerations.
GNSubrahmanyam/agentic-skills/skills/redis Skill
1★ repoComprehensive Redis framework with data structures, caching patterns, session management, and performance optimization. Use when implementing caching, session storage, task queues, or real-time features.
lifesight/lifesight/skills/lifesight-budget-optimization Skill
1★ repoUse when the user wants to reallocate, optimize, or plan marketing budget across channels with Lifesight — "optimize my budget", "where should I move spend", "what's the best allocation for Q4", "how do I hit $X revenue", "should I increase budget", "what if I shift spend from X to Y". Runs the MIA optimization flow cleanly, applies the workspace guardrails, and pressure-tests the result before recommending it. Routed to from the `lifesight` router after the workspace is calibrated.
lifesight/lifesight/skills/lifesight-core Skill
1★ repoUse at the start of ANY conversation that will call a Lifesight MCP tool (ask_mia, query_ad_data, search_knowledge_base, get_current_budget, list_models, set_active_workspace). Load this BEFORE the first data call. Triggers: budget optimization, iROAS / iRevenue, marketing measurement, incrementality, MMM, channel performance, "what's working", board prep, CFO reporting, anomaly detection, scenario planning — any request that touches Lifesight measurement data. Also load whenever a Lifesight tool errored, returned a wall of data, stalled mid-question, or leaked internal field names.
Ocean1346/bigquery-expert/skills/bigquery-optimization Skill
1★ repoUse when writing, reviewing, or optimizing BigQuery SQL, asking about BigQuery best practices, working with .sql files targeting BigQuery, or troubleshooting slow/expensive BigQuery queries. Symptoms: high slot consumption, full table scans, expensive joins, slow queries, high bytes billed.
The same file is in 1 other repository
ssurmic/claude-investment-skills/tax-optimize Skill
no license1★ repoCalculate optimal trim strategy with tax math. Compares Sell-Now (STCG/LTCG depending on holding period) vs Wait-for-LTCG vs Hedge-with-Puts (no taxable event). Computes lot identification (FIFO/HIFO/Specific Lot), tax loss harvesting opportunities. Asks for shares + buy date + income bracket + state. Triggers in English ("should I sell X for tax", "tax on selling X", "LTCG vs STCG on X", "trim X tax efficient") or Chinese ("X 减仓税务", "X 卖出税多少", "现在卖还是等长期", "X 减仓最省税").
zhijunio/skills/skill-creator Skill
1★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
SWEStash/swe-workflow-skills/plugins/architect/skills/performance-optimization Skill
1★ repoIdentify and resolve performance bottlenecks via static analysis — N+1 queries, algorithmic complexity, query optimization, caching, memory leaks, bundle size, connection management. Triggers: this is slow, optimize, performance, N+1, query optimization, caching, bundle size, memory leak, latency, response time, scale, bottleneck.
SWEStash/swe-workflow-skills/plugins/backend/skills/performance-optimization Skill
1★ repoIdentify and resolve performance bottlenecks via static analysis — N+1 queries, algorithmic complexity, query optimization, caching, memory leaks, bundle size, connection management. Triggers: this is slow, optimize, performance, N+1, query optimization, caching, bundle size, memory leak, latency, response time, scale, bottleneck.
SWEStash/swe-workflow-skills/plugins/frontend/skills/performance-optimization Skill
1★ repoIdentify and resolve performance bottlenecks via static analysis — N+1 queries, algorithmic complexity, query optimization, caching, memory leaks, bundle size, connection management. Triggers: this is slow, optimize, performance, N+1, query optimization, caching, bundle size, memory leak, latency, response time, scale, bottleneck.
SWEStash/swe-workflow-skills/plugins/mobile/skills/performance-optimization Skill
1★ repoIdentify and resolve performance bottlenecks via static analysis — N+1 queries, algorithmic complexity, query optimization, caching, memory leaks, bundle size, connection management. Triggers: this is slow, optimize, performance, N+1, query optimization, caching, bundle size, memory leak, latency, response time, scale, bottleneck.
SWEStash/swe-workflow-skills/plugins/strategy/skills/finops-cost-optimization Skill
1★ repoUnderstand and reduce cloud spend — cost visibility and allocation (tagging, ownership), unit economics, rightsizing, autoscaling, commitment discounts (reserved instances, savings plans), storage/egress traps, architecture cost review, budgets and anomaly alerts. Triggers: cloud costs, AWS bill, cut costs, cost optimization, FinOps, why is our bill so high, rightsizing, reserved instances, savings plan, egress fees, cost per customer. Whether to build or buy a capability → build-vs-buy; making code faster → performance-optimization.
SWEStash/swe-workflow-skills/skills/finops-cost-optimization Skill
1★ repoUnderstand and reduce cloud spend — cost visibility and allocation (tagging, ownership), unit economics, rightsizing, autoscaling, commitment discounts (reserved instances, savings plans), storage/egress traps, architecture cost review, budgets and anomaly alerts. Triggers: cloud costs, AWS bill, cut costs, cost optimization, FinOps, why is our bill so high, rightsizing, reserved instances, savings plan, egress fees, cost per customer. Whether to build or buy a capability → build-vs-buy; making code faster → performance-optimization.
SWEStash/swe-workflow-skills/skills/performance-optimization Skill
1★ repoIdentify and resolve performance bottlenecks via static analysis — N+1 queries, algorithmic complexity, query optimization, caching, memory leaks, bundle size, connection management. Triggers: this is slow, optimize, performance, N+1, query optimization, caching, bundle size, memory leak, latency, response time, scale, bottleneck.
morzecrew/agent-skills/skills/measure-before-optimizing Skill
1★ repoSkills that make AI coding agents prove their work — reproduce before fixing, run before claiming, enforce what you build
The same file is in 1 other repository
simonkoehler/event-skills/event-marketing Skill
1★ repoPlan and execute marketing strategy and channel mix to promote B2B events. Generates marketing strategies, promotion timelines, channel playbooks, registration funnel designs, campaign briefs, and demand generation plans. Plans the promotion strategy — event-content writes the actual copy. Use this skill whenever someone asks to create an event marketing plan, design a promotion strategy, plan email campaigns for event registration, create a social media promotion calendar, design paid advertising for an event, build a registration funnel, plan referral or ambassador programs, write campaign briefs, optimize registration conversion, or analyze marketing channel performance. Also triggers for event launch strategies, early-bird promotion plans, last-chance registration campaigns, and multi-channel promotion. Part of the event-management-skills collection — handles promotion strategy while event-content handles the actual copy.
harrylabsj/hermes-skills/skills/token-cost-guard Skill
no license1★ repoMonitor agent token usage and model cost from the active ecosystem's own records, compare the current run with the previous snapshot, and send an alert report when cost growth exceeds a threshold. In OpenClaw it reads OpenClaw session logs; in Hermes agent it reads Hermes logs/state.db instead of OpenClaw. Use when users ask to track token spend, calculate realtime token cost, detect spending spikes, monitor DeepSeek/Kimi/GPT model usage, or set up cost alerts for OpenClaw or Hermes agents.
g0dam/video-studio-skills/video-taste-profiler Skill
1★ repoAnalyze a creator, account, public video set, local video file, or uploaded reference into a reusable AI-video taste profile. Use when the user wants to learn a video's style, extract a creator's repeatable visual grammar, build a taste directory, compare video references, or create a non-infringing director-style profile for later scripts, shotboards, render prompts, and release assets.
looties-io/looties-skills/google-ai-seo-optimization Skill
1★ repoGoogle-specific SEO workflow for AI Overviews and AI Mode readiness. Use when auditing or optimizing a site for generative AI features on Google Search, including crawlability, indexability, snippet eligibility, Googlebot access, JavaScript SEO, structured data accuracy, Search Console checks, and mythbusting AEO/GEO tactics.
k-anss/whetstone/skills/stress-test-the-plan Skill
1★ repoRed-team a decision or plan: surface its fatal flaw, expose hidden assumptions, and trace how it fails over multiple rounds — deliberately pessimistic, no comfort, no rubber-stamping. Trigger when the user says "stress-test this plan", "red-team my decision", "find the holes", "what am I missing", or "argue against this". Do NOT trigger — and the skill must say so — when the user is in emotional distress, or has already decided and is executing (then only "how to die less", not "should you do it"). It also declares its own bias: it is deliberately pessimistic and can talk a good opportunity out of existence; the real call sits between this and a normal read.
kastriasani/google-ads-skills/skills/google-ads-media-plan Skill
1★ repoBuild a quarterly Google Ads media plan, budget, and 90-day rollout roadmap. Allocates a monthly or quarterly budget across campaign types (Brand Search, Non-brand Search, Shopping, Performance Max, Demand Gen, Display, YouTube) by CAC, CPA, and ROAS efficiency, with conservative, moderate, and aggressive scenarios and a phased launch plan. Use when the user asks to plan a Google Ads budget, build a paid search media plan or roadmap, split spend across campaign types, forecast conversions or ROAS, decide brand vs non-brand allocation, size a quarterly or monthly PPC budget, or plan a phased campaign rollout. Triggers on phrases like media plan, budget allocation, campaign roadmap, paid search forecast, how much should I spend on Google Ads, and quarterly PPC plan.
Amazon dsp bidding and optimization
scumunna/programmatic-skills/skills/amazon-dsp-bidding-and-optimization Skill
1★ repoChoose the optimization goal and tune bidding and budget on an Amazon DSP campaign. Use when the user asks about Amazon DSP bidding, Amazon DSP optimization, DSP bid strategy, how to optimize an Amazon DSP campaign, DSP budget pacing, which optimization goal to pick (reach, cost per click, cost per action, return on ad spend, video completion rate, detail page view rate), bid optimization, supply and audience optimization, in-flight management, or why a line item is underdelivering.
Curation and supply path optimization
scumunna/programmatic-skills/skills/curation-and-supply-path-optimization Skill
1★ repoOptimize the path from bid to impression. Use when the user asks about supply path optimization, SPO, path explosion or duplicate paths, reducing SSPs or resellers, direct vs reseller supply, OpenPath, Blue Lists, DSP inventory-source or exchange controls, sellers.json / ads.txt / SupplyChain Object, schain, OpenSincera or supply transparency data, or why the same impression is being bought through many routes.
scumunna/programmatic-skills/skills/dv360-pacing-and-optimization Skill
1★ repoDiagnose and fix pacing, and run the optimization loop in DV360. Use when the user asks about pacing, under-delivery, over-delivery, spend is behind or ahead, a campaign that will not spend its budget, impression loss, even vs ASAP vs ahead pacing, daily vs flight pacing, how to optimize a campaign, why a line item is underpacing, or how to reallocate budget. Covers the pacing math (even daily target, expected spend to date, pacing index) and the ordered fix trees for under and over-delivery.
Google ads optimization and troubleshooting
scumunna/programmatic-skills/skills/google-ads-optimization-and-troubleshooting Skill
1★ repoDiagnose and fix a Google Ads account that is underperforming, and apply optimization score and recommendations with judgment. Use when the user says Google Ads is "not delivering", "no impressions", "no conversions", a campaign is "limited by budget" or "eligible (limited)", a bid strategy is "learning" or "misconfigured" or "limited", an ad is "disapproved", impression share is low, or asks about optimization score, why Search and Performance Max overlap, or why conversions are not tracking. Walk the triage flow first, then the matching playbook.
scumunna/programmatic-skills/skills/google-ads-performance-max Skill
1★ repoSet up, tune, and decide when to run a Google Ads Performance Max campaign. Use when the user asks about Performance Max, PMax, asset groups, audience signals, listing groups, search themes, final URL expansion, brand exclusions or brand safety in PMax, negative keywords in PMax, the PMax channel performance report, AI Max for Search, PMax vs Search, "should I use Performance Max", why PMax reporting is limited, or how to feed PMax good signals.
scumunna/programmatic-skills/skills/google-ads-shopping-and-feed Skill
1★ repoSet up Google Merchant Center and the product feed, optimize product data for query coverage, diagnose disapprovals, and decide how Shopping campaigns sit next to Performance Max. Use when the user asks about Google Shopping, Merchant Center or Merchant Center Next, product feed, feed optimization, feed quality, product attributes, GTIN or product identifiers, product titles and images, supplemental feeds or feed rules, product disapprovals or the diagnostics view, product-level CPA or ROAS, Shopping vs Performance Max, or Shopping campaign priority.
Meta campaign setup and optimization
scumunna/programmatic-skills/skills/meta-campaign-setup-and-optimization Skill
1★ repoBuild, QA, and optimize Meta campaigns across Sales, Leads, Traffic, Awareness, Engagement, App Promotion, Advantage+ automation, manual campaign structures, creative testing, audiences, placements, budgets, learning, and reporting. Use when the user asks how to plan or improve Facebook or Instagram campaigns beyond Conversions API setup.
Microsoft campaign setup and optimization
scumunna/programmatic-skills/skills/microsoft-campaign-setup-and-optimization Skill
1★ repoBuild, QA, and optimize Microsoft Advertising campaigns across Search, Performance Max, Shopping, Audience, conversion tracking, UET, asset groups, search themes, product feeds, budgets, imports, brand controls, learning, and reporting. Use when the user asks how to improve Microsoft Ads or Bing campaigns beyond UET or PMax-only setup.
Microsoft performance max and shopping
scumunna/programmatic-skills/skills/microsoft-performance-max-and-shopping Skill
1★ repoBuild and optimize Microsoft Advertising Performance Max and feed-based Shopping campaigns. Use when the user asks about Microsoft (Bing) Performance Max, PMax on Microsoft, asset groups, search themes, audience signals, the new customer acquisition goal, Microsoft Shopping campaigns, product ads, Microsoft Merchant Center store, the Content API feed, product partitions, final URL expansion, page feeds, Google Import into Microsoft, PMax vs Shopping, or why a Microsoft PMax campaign is not spending.
Stackadapt optimization and troubleshooting
scumunna/programmatic-skills/skills/stackadapt-optimization-and-troubleshooting Skill
1★ repoDiagnose and fix a StackAdapt campaign that is not delivering or not performing. Use when the user says "StackAdapt not delivering", "StackAdapt underpacing", "StackAdapt troubleshooting", "StackAdapt optimization", "improve StackAdapt performance", "StackAdapt conversion not tracking", "no impressions on StackAdapt", "StackAdapt creative disapproved", "StackAdapt campaign not spending", or "why is my StackAdapt campaign behind pace". Walk the triage flow first, then the matching symptom playbook.
Tiktok creative and catalog optimization
scumunna/programmatic-skills/skills/tiktok-creative-and-catalog-optimization Skill
1★ repoBuild and optimize TikTok campaigns through creative, catalog, Smart+, pixel and Events API readiness, asset groups, product sets, creative fatigue, audience controls, budget, learning, and reporting. Use when the user asks how to improve TikTok ads, Smart+ Web, catalog ads, TikTok Shop or product catalog performance, creative testing, or creator-style direct-response ads.
scumunna/programmatic-skills/skills/ttd-bidding-and-optimization Skill
1★ repoHow buying and optimization work on The Trade Desk at a conceptual level. Use when the user asks about Trade Desk bidding, Koa optimization, Kokai AI, TTD bid strategy, how to optimize a TTD campaign, predictive clearing, KPI prediction, bid factors, seeds, TTD forecasting, or TTD pacing. Covers the publicly documented model of impression valuation and AI-assisted optimization, and flags which exact bidding controls live in the partner platform.
duandigi/duandigi-growth-marketing-skill/skills/channel-performance-audit Skill
1★ repoUse this skill when auditing one marketing channel from account summary down to campaigns, content, audiences, queries, landing pages, conversions, qualified outcomes, revenue, and operational constraints.
chobizzy/llm-wiki/skills/skill-creator Skill
1★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 66 other repositories
fullREFIT/skills/skills/gamma-claude-skill Skill
1★ repoTransform raw content into Gamma.app-optimized presentations, documents, and webpages. Use when users need to create professional Gamma content from unstructured materials, optimize existing content for Gamma, or need guidance on Gamma settings and workflows. Handles tier-specific limitations (Free/Plus/Pro/Ultra), structure-first methodology, and SPLICE image prompting.
Aiweline/WelineFramework/.codex/skills/php84-performance Skill
1★ repoAiweline/WelineFramework/dev/ai/skills/php84-performance Skill
1★ repoDeprecated compatibility alias for historical PHP 8.4 performance references.
8421bit/NioPD-Skills/plugins/niopd/skills/NioPD-PO-aarrr-metrics Skill
1★ repoApplies AARRR (Pirate Metrics) framework to analyze and optimize the customer lifecycle funnel. Use for growth analysis, conversion optimization, or lifecycle marketing strategy.
thada2402/AutoResearchClaw/researchclaw/skills/builtin/domain/rl-policy-optimization Skill
1★ repoBest practices for reinforcement learning policy optimization. Use when working on RL agents, PPO, SAC, or reward design.
mitchuski/agentprivacy-skills/agentprivacy-skills-v5/role/agentprivacy-braid-reasoning Skill
1★ repoBounded reasoning architecture for privacy-preserving AI agents using BRAID Mermaid graphs. Activates when discussing Generator/Solver split architecture, Performance-Per-Dollar (PPD) inference economics, BRAID Parity Effect (small model + structure ≥ large model), Mermaid reasoning graph construction, node atomicity, procedural scaffolding vs answer leakage, terminal verification loops, Numerical Masking Protocol, cached reasoning graph libraries, split- architecture deployment, or any task where reasoning structure should be decoupled from reasoning execution for cost efficiency and privacy preservation. Use whenever designing how dual agents reason, not just what they reason about.
mitchuski/agentprivacy-skills/agentprivacy-skills-v5/role/agentprivacy-guild-efficiency Skill
1★ repoGuild efficiency and shared-parent coordination for 0xagentprivacy V5. Activates when discussing G(guilds) network term, O(1) vs O(N²) scaling, shared reasoning libraries, guild coordination economics, or why some networks scale gracefully while others collapse.
andrmaz/spec-driven-architecture/.agents/skills/vercel-react-best-practices Skill
1★ repoReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
The same file is in 7 other repositories
yunseo-kim/agent-toolbox/catalog/skills/react-best-practices Skill
no license1★ repoReact and Next.js performance optimization guidelines from Vercel Engineering. Contains 57 rules across 8 categories prioritized by impact. Use when writing, reviewing, or refactoring React/Next.js code for performance — components, data fetching, bundle optimization, re-renders, and server-side patterns.
medy-gribkov/arcana/skills/asset-optimization Skill
1★ repoOptimize game assets through compression, format conversion, and streaming. Covers textures, meshes, audio, and automated batch processing workflows.
medy-gribkov/arcana/skills/audio-systems Skill
1★ repoImplement spatial audio, adaptive music, and sound effects with Unity, FMOD, and Wwise. Covers 3D positioning, dynamic mixing, and performance optimization.
medy-gribkov/arcana/skills/cost-optimization Skill
1★ repoCloud cost optimization with concrete examples for right-sizing containers, CDN caching, database query costs, serverless tuning, spot instances, reserved capacity, and build time reduction.
medy-gribkov/arcana/skills/database-design Skill
1★ repoDatabase architecture and query optimization for PostgreSQL and SQLite. Covers schema design, normalization to 3NF, denormalization trade-offs, indexing strategy (B-tree, GIN, partial, covering indexes), EXPLAIN ANALYZE interpretation, migrations with up/down patterns, connection pooling, ORM configuration (Prisma, Drizzle, SQLAlchemy), transactions, isolation levels, and anti-patterns like N+1 queries, missing indexes, and over-normalization. Use when designing schemas, optimizing queries, writing migrations, or debugging database performance.
medy-gribkov/arcana/skills/flutter-mobile Skill
1★ repoFlutter mobile development with widget composition, Riverpod state management, GoRouter navigation, platform channels, responsive layouts, theming, performance optimization, and testing
medy-gribkov/arcana/skills/framer-motion Skill
1★ repoExpert guidance for Motion (Framer Motion) animations - variants, gestures, layout animations, AnimatePresence, scroll triggers, and performance optimization
medy-gribkov/arcana/skills/golang-pro Skill
1★ repoGo 1.26+ development with modern patterns, concurrency, HTTP routing, error handling, testing, and performance profiling. Code-first examples for every pattern. Use PROACTIVELY for Go development, architecture design, or performance optimization.
medy-gribkov/arcana/skills/performance-optimization Skill
1★ repoWeb and backend performance optimization including Core Web Vitals (LCP, FID, INP, CLS), bundle analysis with webpack-bundle-analyzer, code splitting, lazy loading, image optimization (WebP, AVIF, responsive srcset), caching strategies (HTTP Cache-Control, CDN, Redis, application-level), database query optimization (indexing, EXPLAIN ANALYZE, N+1), memory leak detection with Chrome DevTools and Node --inspect, connection pooling, and async processing patterns. Use when diagnosing slow pages, reducing bundle size, optimizing API response times, or fixing memory leaks.
medy-gribkov/arcana/skills/postgres-advanced Skill
1★ repoAdvanced PostgreSQL patterns including window functions, CTEs, JSONB operations, full-text search, partitioning, and performance optimization with EXPLAIN ANALYZE
medy-gribkov/arcana/skills/react-native Skill
1★ repoExpert React Native mobile development for iOS and Android. Covers Expo vs bare workflow, navigation patterns, performance optimization, native modules, and platform-specific code.
medy-gribkov/arcana/skills/tailwind-css Skill
1★ repoApply Tailwind CSS v4 patterns, custom plugins, responsive design, dark mode, cn() utility, and performance optimization. Avoid common anti-patterns.
d-oit/do-web-doc-resolver/.agents/skills/skill-creator Skill
1★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
eglenn-dev/dt-skills/skills/skill-creator Skill
no license1★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 2 other repositories
michelve/hugin-cowork/skills/react-best-practices Skill
1★ repoThis skill should be used when the user is writing, reviewing, or refactoring React code to ensure optimal performance patterns. It provides React performance optimization guidelines from Vercel Engineering, covering tasks involving React components, data fetching, bundle optimization, or performance improvements.
michelve/hugin-cowork/skills/react Skill
1★ repoThis skill should be used when the user is working with React components, hooks, lazy loading, Suspense boundaries, or React-specific TypeScript patterns. It covers core React 19 patterns including hooks, Suspense, lazy loading, component structure, TypeScript best practices, and performance optimization.