agentsclimarketplace

Shelves

Performance & cost

7,122 rows from 1,256 repositories

Same behaviour, less time or less money.

What Performance & cost skills agree on

853 skill files read, by 797 of the 1,117 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 154 measured here is ~1.9k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Check for product marketing context first46 of 797 in 20 filesalso worded as Read product marketing context before asking questions; Read product marketing context first
  2. Measure before optimizing31 of 797 in 25 filesalso worded as Measure performance before optimizing; Measure the baseline before optimizing
  3. Profile first to identify the actual bottleneck23 of 797 in 22 filesalso worded as Find the actual bottleneck.; Identify the bottleneck
  4. Verify your robots.txt allows AI crawlers21 of 797 in 12 filesalso worded as Check robots.txt for AI crawlers; Check robots.txt for blocked AI crawlers
  5. Import directly and avoid barrel files19 of 797 in 15 filesalso worded as Avoid barrel imports; Avoid barrel file imports
  6. Spawn all runs in the same turn18 of 797 in 11 filesalso worded as Spawn with-skill and baseline runs in the same turn; Spawn all test runs in the same turn
  7. Write a draft of the skill17 of 797 in 10 filesalso worded as Write the skill draft; Write the SKILL.md draft
  8. Understand the user's intent17 of 797 in 10 filesalso worded as Understand the user's intent first; Understand the user intent
  9. Use React.cache for per-request deduplication16 of 797 in 11 filesalso worded as Use React.cache() for request deduplication; Use React.cache() for per-request deduplication
  10. Profile before optimizing16 of 797 in 14 filesalso worded as Profile with DevTools before optimizing; Profile before optimising
  11. Include specific numbers with sources15 of 797 in 8 filesalso worded as Include specific numbers and data points; Add specific numbers with sources
  12. Add lazy loading to below-fold images15 of 797 in 10 filesalso worded as Lazy load below the fold images; Add loading lazy to below-fold images
  13. Set width and height attributes15 of 797 in 8 filesalso worded as Set explicit width and height attributes; Set width and height attributes on all img elements
  14. Use Promise.all for independent operations15 of 797 in 11 filesalso worded as Use Promise.all() for independent operations; Use Promise.all for independent async operations
  15. Extract expensive work into memoized components13 of 797 in 8 filesalso worded as Apply memo to expensive components

What they tell it not to do

  1. Do not optimize without a baseline and correctness gate28 of 797 in 21 filesalso worded as Do not optimize until a baseline exists; Do not optimize without profiling first.
  2. Do not use select star19 of 797 in 12 filesalso worded as Avoid select star; Never SELECT star on a list
  3. Do not trap or trick users16 of 797 in 5 filesalso worded as Don't trap or trick users
  4. Do not write custom HTML16 of 797 in 9 filesalso worded as Do not write custom HTML for the viewer; Do not write custom HTML for the review viewer
  5. Do not pre-check opt-ins16 of 797 in 5 filesalso worded as Don't pre-check opt-ins; Do not pre-check opt-ins for GDPR compliance
  6. Do not use testing skills15 of 797 in 9 filesalso worded as Do not use skill-test; Do not use testing skills like skill-test
  7. Do not optimize before you have evidence of a problem14 of 797 in 13 filesalso worded as Do not optimize without evidence of a problem; Don't optimize before you have evidence of a problem.
  8. Do not use keyword stuffing in alt text14 of 797 in 5 filesalso worded as Do not use keyword stuffing; Avoid keyword stuffing
  9. Do not define components inside components12 of 797 in 8 filesalso worded as Don't define components inside components; Never define components inside other components
  10. Do not lazy-load above-fold or hero images12 of 797 in 7 filesalso worded as Do not lazy-load above-the-fold or LCP images; Do not lazy load above-fold hero images

What they expect to be installed

  1. python66 of 797
  2. grep39 of 797
  3. git38 of 797
  4. node35 of 797 in 33 files
  5. Lighthouse30 of 797 in 28 files
  6. python328 of 797
  7. npx25 of 797 in 18 files
  8. curl25 of 797
  9. npm24 of 797 in 19 files
  10. jq20 of 797 in 15 files

What they ask it to produce

  1. SKILL.md26 of 797 in 19 filesalso worded as Refactored SKILL.md
  2. benchmark.json24 of 797 in 17 filesalso worded as benchmark.md; benchmark_report.json
  3. Evals/evals.json24 of 797 in 17 filesalso worded as evals.json; eval_metadata.json
  4. Performance audit report22 of 797 in 21 filesalso worded as Performance review report; performance report
  5. Test hypotheses17 of 797 in 7 files
  6. Popup design16 of 797 in 5 filesalso worded as Popup design specifications
  7. Recommendations16 of 797 in 9 filesalso worded as recommended
  8. Before and after measurements14 of 797also worded as Before and after metrics; before and after numbers

When Performance & cost authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 797 authors, with the skills that name each one

How Performance & cost skills are built

6,266 skill directories by 1,149 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 3 files, 20.7 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill391 of 1,149 authors, 3,031 of 6,266 skills
  2. files ship beside it758 of 1,149 authors, 3,235 of 6,266 skills
  3. executable scripts ship inside326 of 1,149 authors, 883 of 6,266 skills

The folders they converge on

  1. references/535 of 1,149 authors, 1,930 of 6,266 skills
  2. scripts/303 of 1,149 authors, 820 of 6,266 skills
  3. agents/209 of 1,149 authors, 392 of 6,266 skills
  4. assets/161 of 1,149 authors, 332 of 6,266 skills
  5. eval-viewer/93 of 1,149 authors, 119 of 6,266 skills
  6. rules/79 of 1,149 authors, 134 of 6,266 skills
  • Skill creator

    anthropics/skills/skills/skill-creator Skill

    in 1 stackno license168,934 repo

    Public repository for Agent Skills

  • Golang benchmark

    samber/cc-skills-golang/skills/golang-benchmark Skill

    2,949 repo

    🧑‍🎨 A collection of Golang agentic skills that works

  • Impeccable

    silverstein/minutes/.agents/skills/impeccable Skill

    1,426 repo

    Every meeting, every idea, every voice note — searchable by your AI. Open-source, privacy-first conversation memory layer.

  • Seo geo

    ReScienceLab/opc-skills/skills/seo-geo Skill

    1,282 repo

    Agent Skills for Solopreneurs

  • Code execution

    mhattingpete/claude-skills-marketplace/code-operations-plugin/skills/code-execution Skill

    660 repo

    Claude Code Skills for software engineering workflows - Git automation, testing, and code review

  • Auditing compose performance

    skydoves/compose-performance-skills/audit/auditing-compose-performance Skill

    469 repo

    ⚡️ A curated library of Agent Skills focused on Jetpack Compose performance.

  • Rust skills

    leonardomso/rust-skills Skill

    398

    A collection of 265 rules across 26 categories that AI coding agents can use to write idiomatic, fast, and safe Rust.

  • Wp performance review

    elvismdev/claude-wordpress-skills/skills/wp-performance-review Skill

    222 repo

    Professional WordPress engineering skills for Claude Code - performance optimization, security auditing, Gutenberg block development, and theme/plugin best practices.

  • Lighthouse mcp

    priyankark/lighthouse-mcp/io.github.priyankark/lighthouse-mcp MCP server

    201 repo

    MCP server for Google Lighthouse performance metrics

  • Embedded ai deployment

    matlab/agent-skills-playground/demos/embedded-ai-deployment/skills/embedded-ai-deployment Skill

    no license162 repo

    A sandbox for prototyping and demonstrating Agent Skills for MATLAB and Simulink work.

  • Pi en progressive

    share-skills/pi/claude-code/pi-en-progressive Skill

    107 repo

    PI(π)—— When The Art of War Meets Cognitive Science for Ai

  • Skill arkts syntax assistant

    SummerKaze/skill-arkts-syntax-assistant Skill

    83

    ArkTS language learning and development assistant

  • Cosmosdb best practices

    AzureCosmosDB/cosmosdb-agent-kit/skills/cosmosdb-best-practices Skill

    50 repo

    A collection of skills for AI coding agents working with Azure Cosmos DB. Skills are packaged instructions and scripts that extend agent capabilities.

  • Cloud finops

    OptimNow/cloud-finops-skills/skills/cloud-finops Skill

    no license45 repo

    Open-source, FinOps Foundation aligned FinOps knowledge skill and mcp for AI coding assistants. 28 reference files spanning cloud cost (AWS/Azure/GCP/OCI), AI inference economics, Kubernetes, data platforms, allocation, chargeback, anomaly management, waste detection, GreenOps. Installs into 11 AI tools. Refreshed monthly. Built by OptimNow

  • Markifact: AI Performance Marketing

    markifact/markifact-mcp/com.markifact/mcp MCP server

    43 repo

    AI marketing agent for Google Ads, Meta, GA4, TikTok, LinkedIn, Shopify, HubSpot and more.

  • Wordpress plugin dev

    Zulut30/Wordpress-skills/skills/wordpress-plugin-dev Skill

    42 repo

    Professional Agent Skill for building, auditing, testing, and releasing modern WordPress plugins with Codex, Cursor, and Claude Code.

  • Autostar claude ai skill

    chrisvoncsefalvay/autostar/autostar-claude-ai-skill Skill

    39 repo

    Autoresearch ALL THE THINGS. RLVR for the masses.

  • Agent optimize

    skillberry-ai/cap-evolve/skills/algorithms/agent-optimize Skill

    37 repo

    Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

  • Code review

    KarmaloopAI/Jiva/examples/personas/code-reviewer/skills/code-review Skill

    35 repo

    Jiva is a CLI-first, open source autonomous AI agent and open alternative to Claude. Written in TypeScript with native support for Sarvam-105B and gpt-oss-120b, it autonomously plans and executes tasks from your terminal. Supports MCP servers, a built-in Skills system, and Jiva Personas - a plugin framework fully compatible with Claude Plugins.

  • X impact checker

    tonkotsuboy/x-impact-checker/skills/x-impact-checker Skill

    35 repo

    AI agent skill to analyze X (Twitter) posts for viral potential using the actual recommendation algorithm

  • Performance Skill

    wieslawsoltes/Performance-Skill Skill

    32

    Cross-platform .NET performance engineering skill for coding agents, covering CPU, memory, GC, benchmarking, concurrency, startup, native profiling, GPU rendering, and production diagnostics on macOS, Windows, and Linux.

  • Ad creative

    jmxt3/gitscape.ai/.agents/skills/ad-creative Skill

    32 repo

    Scan any agent skill — authored or compiled — for prompt injection, secrets, and malicious execution before it touches your agent. Or compile the long tail on the fly.

  • Spark advisor

    yaooqinn/spark-history-cli/skills/spark-advisor Skill

    28 repo

    CLI tool for querying Apache Spark History Server REST API

  • Skill creator

    panaversity/agentfactory-business-plugins/.claude/skills/skill-creator Skill

    28 repo

    Marketplace of domain-specific plugins for AI agents (Cowork, Claude Code, OpenClaw). Build autonomous business workflows for finance, banking, legal operations, and sales using modular agent skills and commands.

  • Code review

    stellarlinkco/skills/skills/code-review Skill

    no license25 repo

    Agent skills for long-running execution, high-recall code review, and measurable self-improvement loops.

  • PostgreSQL performance Tuner MCP Server

    isdaniel/pgtuner_mcp/io.github.isdaniel/pgtuner_mcp MCP server

    25 repo

    provides AI-powered PostgreSQL performance tuning capabilities.

  • Wp elementor skill

    guramzhgamadze/WordPress-Elementor-Skill/wp-elementor-skill Skill

    21 repo

    This is WordPress and Elementor skill.md made for Claude.ai

  • Liquid glass

    2dubu/liquid-glass/plugins/liquid-glass/skills/liquid-glass Skill

    18 repo

    Claude Code skill for iOS 26 Liquid Glass - API references, code generation, migration guides, and troubleshooting

  • Perfetto performance analysis

    Gracker/Perfetto-Skills/skills/perfetto-performance-analysis Skill

    no license18 repo

    Portable Agent Skill for evidence-based Android, Linux, and Chromium Perfetto analysis.

  • Prompt optimization

    shinpr/rashomon/plugins/rashomon/skills/prompt-optimization Skill

    17 repo

    Measure prompt and skill improvements with blind A/B comparison.

  • Fabric data agent perf remediate

    PatrickGallucci/fabric-skills/skills/fabric-data-agent-perf-remediate Skill

    16 repo

    Copilot, Claude AI Skills for Microsoft Fabric

  • Geo aeo optimization

    schwepps/skills/geo-aeo-optimization Skill

    16 repo

    Claude Code skills marketplace - documentation-based skills that extend Claude Code with specialized workflows

  • Bigquery cost optimization

    justvinhhere/bigquery-expert/skills/bigquery-cost-optimization Skill

    15 repo

    BigQuery Skills - Claude Code plugin that makes Claude a BigQuery expert. 5 skills covering query optimization, SQL generation, schema design, cost optimization, and BigQuery-specific features. Detects 11 anti-patterns, generates optimized SQL, designs schemas, and estimates costs.

  • Skill creator

    a-tokyo/agent-skills/.agents/skills/skill-creator Skill

    15 repo

    🧠 AI Agent skills for LLMs and AI Agents - Claude, Codex, Cursor etc.

  • Prompts review

    v0lka/skills/agentic/prompts-review Skill

    15 repo

    A set of AI agent skills for research and development tasks.

  • Optimise skill

    yungbose/upskill/optimise-skill Skill

    14 repo

    The recursive self-improvement loop for your skills (including itself) — runs a retro after every session and turns corrections into permanent skill improvements, so skills compound instead of plateauing.

  • Autoresearch ml

    proyecto26/autoresearch-ai-plugin/skills/autoresearch-ml Skill

    12 repo

    AI Agent plugin for Autoresearch with AI (Claude, OpenClaw, etc) to improve anything!

  • Eval surfer

    di37/EvalSurfer/skills/eval-surfer Skill

    11 repo

    Skill-first, agent-native evaluation protocol for AI apps

  • Skill creator

    isomoes/skills/.agents/skills/skill-creator Skill

    10 repo

    Custom skills for agents to support academic paper writing and thesis management

  • Gatling best practices

    rcampos09/performance-testing-skills/skills/gatling-best-practices Skill

    no license10 repo

    Open-source Claude Code skills for performance and load testing. Install any skill to get AI-guided test generation for your stack.

  • Autoresearch

    a-tokyo/agent-skills-harness/.agents/skills/autoresearch Skill

    10 repo

    A factory for building production-grade agent skills — benchmarked against gold standards, autonomously improved via an autoresearch loop, and verified by independent multi-agent consensus.

  • Swift patterns

    efremidze/swift-patterns-skill/swift-patterns Skill

    9 repo

    Modern Swift/SwiftUI Best Practices (Agent Skills)

  • Database analyzer skill

    netresearch/composer-agent-skill-plugin/examples/database-analyzer-skill Skill

    9 repo

    Composer plugin enabling universal Agent Skill distribution and management for PHP projects

  • Google ads analysis

    itallstartedwithaidea/MiniAgent/skills/google-ads-analysis Skill

    no license9 repo

    The Cowork Agent for Everything — trainable advertising AI + 14 platform MCP servers + agent skills. Based on minimind (42k stars). Train from zero in 2 hours.

  • Skill creator

    rohit-yadav34/second-mind/.agents/skills/skill-creator Skill

    no license8 repo

    Second Mind is a skill that scans your repository and conversation history to capture design decisions, open questions, and session context, storing everything as plain Markdown so project knowledge is portable, human-readable, and easy to resume.

  • Google ads agent

    itallstartedwithaidea/google-ads-gemini-extension/skills/google-ads-agent Skill

    8 repo

    Gemini CLI extension for Google Ads management — campaign analysis, auditing, optimization skills and commands. Ported from production at googleadsagent.ai

  • Skill creator

    Victory-7291/project-scaffold-setup-skills/.agents/skills/skill-creator Skill

    7 repo

    Reusable agent skills for scaffolding C++ and embedded projects

  • Answer engine optimizer

    siddiqss/semantic-seo-suite/skills/answer-engine-optimizer Skill

    7 repo

    Grounded semantic SEO, GEO & off-page as Claude Code skills — with a fabrication guard that refuses to invent numbers. Free & MIT.

  • X twitter social manager skill

    rabden/X-twitter-social-manager-skill Skill

    no license7

    A self-evolving AI Agent Skill (agentskills.io standard) that turns Claude Code, Cursor, Windsurf, or OpenCode into a personalized X (Twitter) social media manager. Features automated onboarding, voice-pattern extraction, algorithm-optimized posting/replying, and self-improving memory logs.

  • Nextjs seo audit

    thisisAhsanIqbal/nextjs-seo-audit Skill

    7

    AI Agent Skills for SEO auditing , 11 SKILL.md files that teach Cursor, Claude Code, Copilot & more to perform comprehensive SEO audits. Zero dependencies.

  • Skill creator

    Poorgramer-Zack/dart-expert-skills/.agents/skills/skill-creator Skill

    no license7 repo

    A comprehensive library of modular Agent Skills for Flutter & Dart development

  • Wp ux design

    xonack/wp-ux-design-claude-skill/skills/wp-ux-design Skill

    6 repo

    WordPress UX Design skill for Claude Code - Core Web Vitals, mobile-first design, typography systems, color management, navigation UX

  • Career ops

    poferraz/career-ops Skill

    6

    An agent skill for Claude Code, Codex, Gemini CLI, Cursor, and more.

  • Caching strategies

    KraitDev/skiLL.Md/skills/architecture/caching-strategies Skill

    6 repo

    skiLL.Md is a structured, open-source collection of reusable, self-contained markdown modules that describe how to perform specific software engineering tasks.

  • Optimize claude fable 5 prompts

    IchenDEV/prompt-optimizer-plugins/plugins/claude-fable-5-prompt-optimizer/skills/optimize-claude-fable-5-prompts Skill

    6 repo

    Dual-protocol prompt optimizer plugins for GPT-5.6 and Claude Fable 5, compatible with Codex and Claude Code.

  • Hardware probe

    yamaru-eu/hardware-probe/io.github.yamaru-eu/hardware-probe MCP server

    6 repo

    Hardware probe for performance diagnostics, thermal monitoring, and LLM optimization.

  • Php code review

    jeeinn/claude-skills/php-code-review Skill

    5 repo

    claude skills for my work

  • Token Optimizer Skill

    samibajwaisking/Token-Optimizer-Skill Skill

    no license5

    Maximum Claude output with minimum tokens. 50+ compression patterns, 10 system prompts, benchmarked results. Star to unlock usage.

  • Apple design backend

    s1gmamale1/apple-design-skills/skills/apple-design-backend Skill

    no license5 repo

    Apple-grade design skill family for Claude Code & Codex — 9 confidence-labeled skills (HIG, Liquid Glass, motion, scrollytelling, OS surfaces, delivery, a11y) with a restraint × surface discipline. One installer links into both ~/.claude/skills and ~/.agents/skills.

  • Skill creator

    crowdin/skills/.agents/skills/skill-creator Skill

    5 repo

    Agent Skills to help developers using AI agents with Crowdin

All 7,122 in the catalog