agentsclimarketplace

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

  • Case 03893

    knownasnaffy/prompthound/dataset/case_03893 Skill

    no license0★ repo

    企业级性能测试工具包,支持HTTP接口压测、负载测试、性能基准测试和报告生成。 Enterprise-grade performance testing toolkit supporting HTTP load testing, stress testing, benchmark testing and report generation.

  • Case 03964

    knownasnaffy/prompthound/dataset/case_03964 Skill

    no license0★ repo

    Monitor traffic efficiency and conversion load during major promos (Black Friday, Cyber Monday, Christmas peaks, flash sales) and advise dynamic ad spend, restock, and traffic allocation. Use in the first ~4 hours after a promo goes live, when ROI drops below breakeven during a sale, when hero SKUs sell out instantly, when the user mentions scaling or cutting ads mid-campaign, server or checkout strain, or "traffic is huge but orders aren't." Steps implied: real-time (or latest) traffic → conversion efficiency → if strong, recommend scaling spend or shifting budget to winners; if weak, recommend landing-page and funnel checks before spend. Also trigger on stockouts under load, CAC spike during promos, or reallocating budget between campaigns. Do NOT use for evergreen SEO-only plans with no live promo window, or pure creative briefs without performance or inventory context.

  • Case 04019

    knownasnaffy/prompthound/dataset/case_04019 Skill

    no license0★ repo

    Analyze and optimize OpenClaw system prompt token usage by compressing workspace files (AGENTS.md, SOUL.md, USER.md, TOOLS.md, IDENTITY.md, HEARTBEAT.md, MEMORY.md). Performance-first approach: only safe compressions that preserve agent behavior quality. Use when: (1) system prompt feels bloated or costs are high, (2) user wants to audit token usage of workspace files, (3) MEMORY.md has grown large with stale entries, (4) periodic prompt hygiene check. NOT for: modifying OpenClaw core system instructions, safety rules, or tool definitions.

  • Case 04147

    knownasnaffy/prompthound/dataset/case_04147 Skill

    no license0★ repo

    Autonomous agent health, optimization, and cleanup. Use when: (1) running scheduled cron jobs for agent maintenance, (2) responding to "optimize", "cleanup", "health check", "clear stalls", or "self-maintain" requests, (3) performing BMAD-style retrospective and continuous improvement, (4) checking sub-agent sessions, process health, memory usage, and context bloat, (5) ensuring fast response times and autonomous operation. This skill handles all self-optimization workflows including stale session cleanup, context compaction, and performance monitoring.

  • Case 04171

    knownasnaffy/prompthound/dataset/case_04171 Skill

    no license0★ repo

    Monitor traffic efficiency and conversion load during major promos (Black Friday, Cyber Monday, Christmas peaks, flash sales) and advise dynamic ad spend, restock, and traffic allocation. Use in the first ~4 hours after a promo goes live, when ROI drops below breakeven during a sale, when hero SKUs sell out instantly, when the user mentions scaling or cutting ads mid-campaign, server or checkout strain, or "traffic is huge but orders aren't." Steps implied: real-time (or latest) traffic → conversion efficiency → if strong, recommend scaling spend or shifting budget to winners; if weak, recommend landing-page and funnel checks before spend. Also trigger on stockouts under load, CAC spike during promos, or reallocating budget between campaigns. Do NOT use for evergreen SEO-only plans with no live promo window, or pure creative briefs without performance or inventory context.

  • Case 04208

    knownasnaffy/prompthound/dataset/case_04208 Skill

    no license0★ repo

    Professional resume analysis and optimization for UK job market. Use when user needs to (1) Analyze resume quality against a job description, (2) Get ATS compatibility score and keyword suggestions, (3) Optimize bullet points with quantifiable achievements, (4) Generate an improved version with tracked changes and annotations. Supports .docx format input/output.

  • Case 04317

    knownasnaffy/prompthound/dataset/case_04317 Skill

    no license0★ repo

    提供多策略投资组合优化框架,支持均值-方差、Black-Litterman 和分层风险平价(HRP)算法,内置多种协方差估计方法对比分析。触发场景:(1) 我要给股票组合找最优配置,同时考虑交易成本;(2) 想对比不同风险模型(普通协方差、Ledoit-Wolf收缩、半协方差)哪个预测更准;(3) 用 Black-Litterman 方法结合主观观点来构建组合。

  • Case 04328

    knownasnaffy/prompthound/dataset/case_04328 Skill

    no license0★ repo

    Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

  • Case 04437

    knownasnaffy/prompthound/dataset/case_04437 Skill

    no license0★ repo

    Track, analyze, and optimize AI API costs across OpenAI, Anthropic, OpenRouter, Google, and other LLM providers. Parses billing data, usage logs, or API responses to produce cost breakdowns by model, feature, and time period. Identifies optimization opportunities (model downgrades, caching, prompt compression). Use when asked to analyze API costs, track AI spending, optimize LLM usage, create cost reports, find expensive API calls, compare model pricing, set budget alerts, or audit API usage. Triggers on "API costs", "how much am I spending", "optimize API usage", "cost breakdown", "LLM spending", "token usage", "billing analysis", "reduce API costs", "budget tracking".

  • Case 04504

    knownasnaffy/prompthound/dataset/case_04504 Skill

    no license0★ repo

    Professional resume analysis and optimization for UK job market. Use when user needs to (1) Analyze resume quality against a job description, (2) Get ATS compatibility score and keyword suggestions, (3) Optimize bullet points with quantifiable achievements, (4) Generate an improved version with tracked changes and annotations. Supports .docx format input/output.

  • Case 04555

    knownasnaffy/prompthound/dataset/case_04555 Skill

    no license0★ repo

    Create, optimize, or update AgentSkills with evidence-based design. Two modes: (1) CREATE — build new skills from scratch with proven design patterns. (2) OPTIMIZE — diagnose and fix existing skills across 9 evidence-based dimensions: trigger precision, context efficiency, structured instructions, step decomposition, positive constraints, example design, verification, freedom calibration, progressive loading. Based on 25+ peer-reviewed papers (ACL/NeurIPS/EMNLP 2023-2025), Anthropic/Google/Microsoft official guides, and Claude Code/Cursor community practices. Trigger: "create skill", "optimize skill", "improve skill", "fix skill", "package skill", "skill not working", "skill design", "SKILL.md", "写技能", "优化技能", "skill type", "skill classification", "state management", "技能分类"

  • Case 04662

    knownasnaffy/prompthound/dataset/case_04662 Skill

    no license0★ repo

    A-share quantitative trading backtesting using AKQuant (Rust engine) and AKShare data. Use when user asks to "backtest a stock strategy", "test trading algorithm on Chinese stocks", "analyze stock performance", "run double MA strategy", or "optimize trading parameters". Supports double MA, RSI, and custom strategies for A-shares.

  • Case 04696

    knownasnaffy/prompthound/dataset/case_04696 Skill

    no license0★ repo

    Programmatic backtesting framework for trading strategies. Runs backtests with historical price data (yfinance or CSV), supports momentum/mean-reversion/factor/signal-based strategies, walk-forward optimization, out-of-sample testing, transaction cost modeling, regime-aware splits, and full performance metrics (Sharpe, Sortino, Calmar, max drawdown, CAGR, win rate, profit factor). Distinct from einstein-research-backtest (which provides methodology guidance). Use when a user wants to actually run a backtest, test a specific strategy on historical data, or generate performance metrics.

  • Case 04701

    knownasnaffy/prompthound/dataset/case_04701 Skill

    no license0★ repo

    Codified expertise for production scheduling, job sequencing, line balancing, changeover optimisation, and bottleneck resolution in discrete and batch manufacturing. Informed by production schedulers with 15+ years experience. Includes TOC/drum-buffer-rope, SMED, OEE analysis, disruption response frameworks, and ERP/MES interaction patterns. Use when scheduling production, resolving bottlenecks, optimising changeovers, responding to disruptions, or balancing manufacturing lines.

  • Case 04744

    knownasnaffy/prompthound/dataset/case_04744 Skill

    no license0★ repo

    Captures and analyzes Android Perfetto traces via CLI and config files. Covers trace collection (CPU, GPU, memory, rendering, power), editing TraceConfig (.pbtx), and analyzing jank, latency, overdraw, and power. Trace query can be done in Perfetto UI or via trace_processor command-line tool (PerfettoSQL). Use when working with Perfetto, systrace, Android performance, trace configs, or analyzing .perfetto-trace files.

  • Case 04758

    knownasnaffy/prompthound/dataset/case_04758 Skill

    no license0★ repo

    Codified expertise for production scheduling, job sequencing, line balancing, changeover optimisation, and bottleneck resolution in discrete and batch manufacturing. Informed by production schedulers with 15+ years experience. Includes TOC/drum-buffer-rope, SMED, OEE analysis, disruption response frameworks, and ERP/MES interaction patterns. Use when scheduling production, resolving bottlenecks, optimising changeovers, responding to disruptions, or balancing manufacturing lines.

  • Case 04785

    knownasnaffy/prompthound/dataset/case_04785 Skill

    no license0★ repo

    Optimize LLM token usage and API costs for the openclaw-manager proxy platform. Provides model-tier routing (route simple prompts to glm-4.7-flashx instead of glm-4.7), heartbeat cost reduction (force heartbeat calls to use the cheapest model with optimized intervals), context lazy loading (generate optimized AGENTS.md that loads only necessary context files per prompt complexity), and platform-level usage analytics (query real usage_records from PostgreSQL to generate reports and quota-matching advice). Use this skill whenever the user mentions token optimization, reducing API costs, model routing, heartbeat optimization, context loading strategy, usage reports, quota analysis, or anything related to saving money on LLM API calls in the openclaw-manager project. Also trigger when the user asks about which model to use for different task types, or wants to analyze per-instance token consumption patterns.

  • Case 04878

    knownasnaffy/prompthound/dataset/case_04878 Skill

    no license0★ repo

    Captures and analyzes Android Perfetto traces via CLI and config files. Covers trace collection (CPU, GPU, memory, rendering, power), editing TraceConfig (.pbtx), and analyzing jank, latency, overdraw, and power. Trace query can be done in Perfetto UI or via trace_processor command-line tool (PerfettoSQL). Use when working with Perfetto, systrace, Android performance, trace configs, or analyzing .perfetto-trace files.

  • Case 04916

    knownasnaffy/prompthound/dataset/case_04916 Skill

    no license0★ repo

    A-share quantitative trading backtesting using AKQuant (Rust engine) and AKShare data. Use when user asks to "backtest a stock strategy", "test trading algorithm on Chinese stocks", "analyze stock performance", "run double MA strategy", or "optimize trading parameters". Supports double MA, RSI, and custom strategies for A-shares.

  • Case 04967

    knownasnaffy/prompthound/dataset/case_04967 Skill

    no license0★ repo

    Monitor traffic efficiency and conversion load during major promos (Black Friday, Cyber Monday, Christmas peaks, flash sales) and advise dynamic ad spend, restock, and traffic allocation. Use in the first ~4 hours after a promo goes live, when ROI drops below breakeven during a sale, when hero SKUs sell out instantly, when the user mentions scaling or cutting ads mid-campaign, server or checkout strain, or "traffic is huge but orders aren't." Steps implied: real-time (or latest) traffic → conversion efficiency → if strong, recommend scaling spend or shifting budget to winners; if weak, recommend landing-page and funnel checks before spend. Also trigger on stockouts under load, CAC spike during promos, or reallocating budget between campaigns. Do NOT use for evergreen SEO-only plans with no live promo window, or pure creative briefs without performance or inventory context.

  • Case 04983

    knownasnaffy/prompthound/dataset/case_04983 Skill

    no license0★ repo

    A股量化组合优化。当用户说"组合优化"、"portfolio optimization"、"均值方差"、"风险平价"、"最优权重"、"Black-Litterman"、"最小方差"、"最大夏普"、"怎么分配权重"、"等风险贡献"时触发。基于现代投资组合理论,对给定标的池进行量化权重优化,支持均值方差/最小方差/风险平价/等权等多种方法,输出最优配置权重和有效前沿。支持研报风格(formal)和快速优化风格(brief)。

  • Case 05122

    knownasnaffy/prompthound/dataset/case_05122 Skill

    no license0★ repo

    Discover hidden APIs behind web pages and replace expensive browser snapshots with lightweight API calls. Saves ~15-20x tokens and 2x speed on browser automation tasks. **Use when:** (1) You just completed a browser snapshot workflow and want to optimize it (2) User asks to "find the API" or "make this faster" for a browser task (3) A snapshot is too large, truncated, or unreliable (4) You need structured data from a web page (tables, lists, details) (5) User mentions "api discovery", "snapshot to api", "browser optimization"

  • Case 05210

    knownasnaffy/prompthound/dataset/case_05210 Skill

    no license0★ repo

    Amazon listing builder and optimizer for sellers. Two modes: (A) Create — build keyword-optimized listings from scratch using keyword lists + product characteristics + AI copywriting, (B) Optimize — audit existing listings, find keyword gaps, score across 8 dimensions, and rewrite with missing keywords. Integrates with amazon-keyword-research for keyword input. Works on 12 Amazon marketplaces. No API key required. Use when: (1) creating a new Amazon listing from keywords, (2) auditing an existing listing for SEO and conversion, (3) checking keyword coverage in title/bullets/description, (4) generating listing copy with target keywords and tone, (5) comparing listings against competitors, (6) preparing a listing for launch or relaunch.

  • Case 05218

    knownasnaffy/prompthound/dataset/case_05218 Skill

    no license0★ repo

    Analyze OpenClaw agent configuration and API usage patterns to identify cost-saving opportunities. Diagnose inefficient heartbeat configs, estimate daily/weekly API spend, and generate actionable recommendations to reduce LLM API costs. Essential for any agent operator running 24/7 on a budget. Use when: agent costs are higher than expected, heartbeat config needs review, or monthly API bill surprises you.

  • Case 05219

    knownasnaffy/prompthound/dataset/case_05219 Skill

    no license0★ repo

    A-share quantitative trading backtesting using AKQuant (Rust engine) and AKShare data. Use when user asks to "backtest a stock strategy", "test trading algorithm on Chinese stocks", "analyze stock performance", "run double MA strategy", or "optimize trading parameters". Supports double MA, RSI, and custom strategies for A-shares.

  • Case 05281

    knownasnaffy/prompthound/dataset/case_05281 Skill

    no license0★ repo

    提供多策略投资组合优化框架,支持均值-方差、Black-Litterman 和分层风险平价(HRP)算法,内置多种协方差估计方法对比分析。触发场景:(1) 我要给股票组合找最优配置,同时考虑交易成本;(2) 想对比不同风险模型(普通协方差、Ledoit-Wolf收缩、半协方差)哪个预测更准;(3) 用 Black-Litterman 方法结合主观观点来构建组合。

  • Case 05391

    knownasnaffy/prompthound/dataset/case_05391 Skill

    no license0★ repo

    Analyze and optimize OpenClaw system prompt token usage by compressing workspace files (AGENTS.md, SOUL.md, USER.md, TOOLS.md, IDENTITY.md, HEARTBEAT.md, MEMORY.md). Performance-first approach: only safe compressions that preserve agent behavior quality. Use when: (1) system prompt feels bloated or costs are high, (2) user wants to audit token usage of workspace files, (3) MEMORY.md has grown large with stale entries, (4) periodic prompt hygiene check. NOT for: modifying OpenClaw core system instructions, safety rules, or tool definitions.

  • Case 05437

    knownasnaffy/prompthound/dataset/case_05437 Skill

    no license0★ repo

    Analyze OpenClaw agent configuration and API usage patterns to identify cost-saving opportunities. Diagnose inefficient heartbeat configs, estimate daily/weekly API spend, and generate actionable recommendations to reduce LLM API costs. Essential for any agent operator running 24/7 on a budget. Use when: agent costs are higher than expected, heartbeat config needs review, or monthly API bill surprises you.

  • Case 05513

    knownasnaffy/prompthound/dataset/case_05513 Skill

    no license0★ repo

    Caching anti-pattern analyzer -- detects Redis/Memcached misuse, TTL problems, cache invalidation failures, stampedes, architecture issues, and security hygiene gaps in application-level caching

  • Case 05519

    knownasnaffy/prompthound/dataset/case_05519 Skill

    no license0★ repo

    Analyze OpenClaw agent configuration and API usage patterns to identify cost-saving opportunities. Diagnose inefficient heartbeat configs, estimate daily/weekly API spend, and generate actionable recommendations to reduce LLM API costs. Essential for any agent operator running 24/7 on a budget. Use when: agent costs are higher than expected, heartbeat config needs review, or monthly API bill surprises you.

  • Performance optimization

    goonobu-dot/dev-skills-library/skills/performance-optimization Skill

    0★ repo

    Measurement-first performance optimization: profile before changing, verify with numbers, Core Web Vitals targets and remediation steps. Use when the user reports slowness, asks to optimize or speed up code or pages, or says 遅い, パフォーマンス, 高速化, 重い. Never optimize without measuring first. Not for architecture-level scaling decisions (use scalability-design).

  • Scalability design

    goonobu-dot/dev-skills-library/skills/scalability-design Skill

    0★ repo

    System design decision frameworks from system-design-primer: caching strategies, load balancing, DB partitioning/replication, async processing, CAP trade-offs. Use when designing system architecture, choosing infrastructure patterns, discussing scaling, or when the user says スケール, 大量アクセス, アーキテクチャ設計, 負荷分散, キャッシュ戦略. Not for optimizing existing slow code (use performance-optimization) or designing a single module's API (use deep-module-design).

  • Caching strategy

    sandev/engineering-os/skills/design-and-architecture/caching-strategy Skill

    0★ repo

    Add caching that speeds up a system without serving stale or wrong data, choosing what to cache, where, how it expires, and how it's invalidated. Use when introducing or reviewing a cache, debugging stale data, or deciding whether caching is the right fix for a performance problem.

  • Web performance checklist

    yuri-semenenko/ai-engineering-workspace/claude-code/.claude/skills/web-performance-checklist Skill

    0★ repo

    Web performance checklist — Core Web Vitals (LCP/INP/CLS), TTFB diagnosis, and frontend levers (JS/CSS/fonts/images/network/rendering) plus backend (DB N+1, API latency, caching, infra). Use when optimizing performance, diagnosing a slow page or unresponsive interaction, setting a performance budget, or reviewing a perf-sensitive change.

  • Optimization primer

    aoli0919/learn-anything-skills/skills/optimization-primer Skill

    0★ repo

    Explain loss, gradients, local minima, learning rates, constraints, and optimization failure modes for beginners.

  • Swiftui performance audit

    K95M65/AI_ONBOARD/skills/swiftui-performance-audit Skill

    0★ repo

    Audit and improve SwiftUI runtime performance from code review and architecture. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps, and to provide guidance for user-run Instruments profiling when code review alone is insufficient.

    The same file is in 1 other repository

  • Performance review

    JoaoAlavarse/cursor-config/skills/performance-review Skill

    0★ repo

    Evaluates code, architecture and runtime behavior to identify performance bottlenecks and recommend improvements based on measurable impact. Use when reviewing performance, latency, throughput, or resource usage.

  • Short video performance review

    slalomboy/talking-head-video-suite/skills/short-video-operations-pack/skills/short-video-performance-review Skill

    0★ repo

    Use when comparable short-video samples need diagnosis across content, audience, conversion, and delivery metrics or a bounded next experiment.

  • Factory capital efficiency

    mahidalhan/openfactory/.agents/skills/factory-capital-efficiency Skill

    0★ repo

    Use when a factory owner asks where capital is tied up, why ROIC is weak, which operating levers could raise profit or capital turns, or what 30-90 day improvement portfolio to prioritize.

  • Vercel optimize

    trugurpala/divan/plugins/react-pack/skills/vercel-optimize Skill

    0★ repo

    Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web Vitals, Bot Management, Fluid compute, or cost breakdown requests.

    The same file is in 64 other repositories

  • Vercel react best practices

    trugurpala/divan/plugins/react-pack/skills/vercel-react-best-practices Skill

    0★ repo

    React 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 445 other repositories

  • Stress test claim

    cxMoonGlade/Theory-First/plugins/theory-first/skills/stress-test-claim Skill

    0★ repo

    Run explicit falsification trip-wires against a frozen, literature-closed computational-science claim. Use when theory-fix assigns a refreshed closure packet, or directly only when the user already has that packet plus the preregistration and raw result artifacts. It checks theorem and symmetry constraints, formulation invariance, mechanism-to-observable bridges, independent ground truth, degenerate interventions, suppressing measurement lenses, preregistration integrity, and downstream propagation. For a merely clean, surprising, hoped-for, or consequential result whose evidence has not been reopened, use theory-fix instead. This skill does not acquire literature or repair the claim itself.

  • Skill creator

    awesome-liuxiao/agent-skill-doctor/benchmarks/public/v1/upstream/anthropic/skill-creator Skill

    no license0★ repo

    Create 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

  • Backend performance

    ahtishamshahzad/agent_dev_flow/.ai/skills/backend/backend-performance Skill

    0★ repo

    Use to diagnose and fix measured backend performance problems — profiling first, then N+1 and query work (with the database pack), caching with explicit invalidation, connection pooling, payload size, and event-loop health. No speculative optimization.

  • Database performance

    ahtishamshahzad/agent_dev_flow/.ai/skills/database/database-performance Skill

    0★ repo

    Use to diagnose and fix measured database performance problems — slow-query identification, EXPLAIN analysis, N+1 elimination, pagination of unbounded reads, connection-pool sizing, and lock-contention diagnosis. Evidence first; indexes via the indexing skill.

  • Mobile performance

    ahtishamshahzad/agent_dev_flow/.ai/skills/mobile/mobile-performance Skill

    0★ repo

    Use to plan and diagnose mobile performance — list rendering, re-renders, image/memory usage, startup, and jank — measured on a representative build. Prefer measured, safe fixes over rewrites. The mobile arm of performance-review.

  • Performance review

    ahtishamshahzad/agent_dev_flow/.ai/skills/performance-review Skill

    0★ repo

    Use to find and plan fixes for real performance bottlenecks — measured, not guessed. Covers rendering/re-renders, data access, network, memory, and startup. Recommends safe, measurable improvements over risky rewrites and validates in a representative build.

  • Web deployment

    ahtishamshahzad/agent_dev_flow/.ai/skills/web/web-deployment Skill

    0★ repo

    Use to plan web deployment — platform selection driven by framework needs (Next.js server/edge features vs Vite static output with SPA fallback), per-environment config and secrets, preview deployments, CDN/caching headers, domains/TLS, and rollback. Deploying/publishing requires explicit approval.

  • Web performance

    ahtishamshahzad/agent_dev_flow/.ai/skills/web/web-performance Skill

    0★ repo

    Use to plan and fix web performance from measurements — Core Web Vitals (LCP/CLS/INP) budgets, code splitting, image/font loading, bundle analysis, caching/CDN, rendering-strategy impact, and dashboard-specific costs (tables, charts). Measure first; fix the measured bottleneck; validate in a production build.

  • Performance design

    lzx-Bill/Project-Factory-Core/.agents/skills/performance-design Skill

    0★ repo

    Use when designing performance strategy for a project — "performance design", "performance optimization", "latency", "throughput", "benchmark", "caching strategy", "性能设计", "性能优化", "延迟", "吞吐量", "缓存策略". This skill defines performance targets, establishes benchmarks, designs caching strategies, and identifies performance risks. Use after architecture-decisions and before delivery-planning.

  • Skill creator

    lzx-Bill/Project-Factory-Core/.agents/skills/skill-creator Skill

    0★ repo

    Create 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, or optimize a skill description for better triggering accuracy. Also use when a gap in the current skill set is identified.

  • Wechat performance review

    yuanjiemi/yuanjiemi-ai-skills/skills/wechat-performance-review Skill

    no license0★ repo

    复盘微信公众号文章表现:读取用户提供的公众号后台截图、Excel、CSV、手动数据或文章链接,整理阅读量、点赞、分享、爱心/在看和互动率;结合标题、内容结构与 CTA 提炼亮点、可能原因和下一篇优化动作,并写入本地 Excel 复盘库。用户说“复盘这篇公众号文章”“分析这些公众号数据”“看看哪篇文章表现最好”“把后台截图收进复盘库”“对比第3天和第7天数据”等自然语言时必须使用。免费模式不需要 API;文章链接自动采集模式使用用户自己的世界树 API Key,无需飞书 App ID 或 n8n。

  • Optimize prompt

    Paldom/promptimize/skills/optimize-prompt Skill

    0★ repo

    Rewrites and tunes existing prompt text - removes contradictions, applies reasoning-vs-standard regime rules, sizes few-shot examples, fixes structured output, follows current Fable 5 / GPT-5.6 guidance, then checks the rewrite. Use when asked to optimize, improve, rewrite, shorten, tune, fix, or migrate a prompt or system prompt. Not for agent-run goal text, prompt benchmarks, or loop design.

  • Data heavy optimization

    dgabreuu/react-skill-pack/skills/data-heavy-optimization Skill

    0★ repo

    Use when React renders large lists or repeats expensive computations and needs evidence-based virtualization, pagination, or memoization.

  • Holistic performance

    dgabreuu/react-skill-pack/skills/holistic-performance Skill

    0★ repo

    Use when React + Vite applications need a static review of dependencies, assets, and loading before real performance validation.

  • Memoization optimization

    dgabreuu/react-skill-pack/skills/memoization-optimization Skill

    0★ repo

    Use when React component props have unstable identity candidates and memoization decisions need measurement-based guidance.

  • State management optimization

    dgabreuu/react-skill-pack/skills/state-management-optimization Skill

    0★ repo

    Use when React Context shows broad update propagation signals and native React APIs may reduce unnecessary notifications.

  • Databases

    danielleit241/hs-skills/skills/databases Skill

    0★ repo

    Design schemas, write queries for MongoDB and PostgreSQL. Use for database design, SQL/NoSQL queries, aggregation pipelines, indexes, migrations, replication, performance optimization, psql CLI.

  • Optimize

    avnath13/evalpilot/skills/optimize Skill

    0★ repo

    Take the top failure cluster, locate the responsible prompt/code/tool, propose a targeted fix (or a constitutional self-critique revision), apply it on a branch, and re-run to prove or disprove the improvement with a before/after comparison. Use when the user wants to fix a known failure mode and verify it. Do NOT use before error analysis (use analyze-failures) and do NOT build a judge for a code-checkable failure, fix it directly (fix-before-eval). Never claim success without the A/B re-run.

  • Standards go performance

    pecigonzalo/agent-skills/skills/standards-go-performance Skill

    0★ repo

    Use this skill when diagnosing Go performance issues, tuning garbage collection, reviewing performance, or working on allocation-sensitive code. Provides pprof and trace workflows, allocation control, GC tuning guardrails, and runtime metrics patterns.