Loading...
Loading...
Found 1,578 Skills
Use when optimizing multi-factor systems with limited experimental budget, screening many variables to find the vital few, discovering interactions between parameters, mapping response surfaces for peak performance, validating robustness to noise factors, or when users mention factorial designs, A/B/n testing, parameter tuning, process optimization, or experimental efficiency.
Optimize e-commerce checkout flow to reduce cart abandonment. Friction analysis, payment method optimization, trust signals, and checkout UX best practices.
Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query writing unless user asks for performance or index help. Prefer indexing as optimization strategy. Use MongoDB MCP when available.
Analyze text content using both traditional NLP and LLM-enhanced methods. Extract sentiment, topics, keywords, and insights from various content types including social media posts, articles, reviews, and video content. Use when working with text analysis, sentiment detection, topic modeling, or content optimization.
When the user wants to find blog keywords, do keyword research for SEO, or build a keyword list for content. Use when the user mentions "keyword research," "blog keywords," "find keywords," "what should I blog about," "keyword ideas," "long-tail keywords," "striking distance keywords," "keyword gap," "content gap analysis," "competitor keywords," "keyword difficulty," "search volume," "topic clusters," "pillar content keywords," "keyword list," or "what are people searching for." Outputs a ranked JSONL keyword list for downstream content creation. For writing content strategy, see content-strategy. For SEO audits, see seo-audit. For AI search optimization, see ai-seo.
Analyzes codebases to identify refactoring opportunities based on Martin Fowler's catalog of code smells and refactoring techniques. Detects duplicated code, high coupling, complex conditionals, primitive obsession, long functions, and other structural issues. Produces a structured refactoring report with prioritized findings saved to docs/_refacs/. Use when auditing code quality, preparing for a refactoring sprint, or reviewing architectural health. Don't use for style/formatting issues, performance optimization, or security audits.
Profile-driven performance optimization with behavior proofs. Use when: optimize, slow, bottleneck, hotspot, profile, p95, latency, throughput, or algorithmic improvements.
Autonomous LLM training optimization with GPU support. Runs 5-minute training experiments, measures val_bpb, keeps improvements or reverts — repeat forever. Use this skill when the user asks to "train a model autonomously", "optimize LLM training", "run ML experiments", "autoresearch with GPU", "optimize val_bpb", "autonomous ML training", "LLM pretraining loop", "setup ML autoresearch", "GPU training experiments", "pretrain from scratch", "speed up training", "lower my loss", "GPU optimization", "CUDA training", or mentions "train.py", "prepare.py", "bits per byte", "val_bpb", "NVIDIA GPU training", "RTX training", "H100 training", "autonomous model training", "consumer GPU training", "low VRAM training". Always use this skill when the user wants to autonomously optimize any ML training metric.
A complete guide to developing MusicFree desktop theme packs from scratch. It is triggered when users request to write, create, design MusicFree desktop theme packs, or ask to generate themes based on reference images, color schemes, or style keywords. It covers the full process including CSS variable system, color design paradigms, static themes, dynamic iframe themes, resource optimization, packaging testing, and submission to the theme market. This Skill is designed for AI execution, guiding AI to collaborate with community contributors (who may have no front-end experience) to complete theme pack development.
Databricks SQL query optimizer: analyzes a slow SQL query, rewrites it for speed using SQL-level optimizations only, validates byte-for-byte result equivalence, and benchmarks both versions with statistical significance testing. Use this skill whenever the user wants to optimize, speed up, tune, or benchmark a SQL query on Databricks. Trigger on: "/databricks-sql-autotuner", "optimize this SQL", "make this query faster", "tune my Databricks query", "benchmark SQL on Databricks", "speed up this spark SQL", "SQL performance on Databricks", "EXPLAIN this query", "why is my query slow on Databricks", "SQL query optimization Databricks", or whenever a user pastes a SQL query and mentions performance, slowness, or runtime.
When the user wants help with Quality Score analysis, diagnosing low Quality Scores, improving Expected CTR, Ad Relevance, or Landing Page Experience, understanding Ad Rank, reducing CPCs through Quality Score, running a Quality Score audit, or tracking Quality Score over time. Triggers on 'quality score', 'QS', 'expected CTR', 'ad relevance', 'landing page experience', 'ad rank', 'low quality score', 'quality score audit', 'improve quality score', 'CPC too high', or 'below first page bid'. For search campaign structure and RSAs see google-ads-search. For keyword strategy see google-ads-keywords. For landing page optimization see page-cro.
When the user wants to audit a Google Ads account for a lead generation business — reviewing CPL, lead volume, lead quality, form conversion rates, offline conversion imports, and pipeline-focused optimization. Triggers on 'lead gen audit', 'Google Ads audit lead generation', 'CPL audit', 'audit my lead gen account', 'B2B Google Ads audit', 'lead quality audit', 'cost per lead audit', 'lead gen account review', or 'review lead generation Google Ads'. For general account audits see google-ads-account-audit. For ecommerce audits see google-ads-audit-ecommerce.