Loading...
Loading...
Found 453 Skills
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
Guides QA engineers through daily testing activities—morning review, test case creation, automation, exploratory testing, bug reporting, and end-of-day wrap-up. Use when planning or executing day-to-day testing or when the user asks about daily testing workflow.
Design manual testing and exploratory testing plans, including test charters, heuristic methods, and session records. Default output is Markdown, Excel/CSV/JSON is available upon request. Use for manual testing.
Guide for querying databases through DBHub MCP server. Use this skill whenever you need to explore database schemas, inspect tables, or run SQL queries via DBHub's MCP tools (search_objects, execute_sql). Activates on any database query task, schema exploration, data retrieval, or SQL execution through MCP — even if the user just says "check the database" or "find me some data." This skill ensures you follow the correct explore-first workflow instead of guessing table structures.
Use this skill when performing exploratory data analysis, statistical testing, data visualization, or building predictive models. Triggers on EDA, pandas, matplotlib, seaborn, hypothesis testing, A/B test analysis, correlation, regression, feature engineering, and any task requiring data analysis or statistical inference.
Systematic 4-phase codebase exploration: Detect, Explore, Map, Summarize. Use when starting work on an unfamiliar codebase, onboarding to a new project, reviewing a repository for the first time, or building context before debugging or code review. Use for "explore codebase", "what does this project do", "understand architecture", or "onboard me". Do NOT use for modifying files, running applications, performance optimization, or deep domain analysis.
Context-driven aesthetic exploration with anti-cliche validation: typography, color, animation, atmosphere. Use when starting a frontend needing distinctive aesthetics, refreshing generic designs, or auditing for "AI slop" patterns. Use for "distinctive frontend", "unique aesthetics", "avoid generic design", "creative frontend". Do NOT use for quick prototypes, strict brand compliance, backend projects, or data visualization.
Runs tilth CLI for structural code navigation — reads files with smart outlining, searches symbols/text/regex, finds files by glob, and maps codebases. Use instead of read/grep/find for all source code exploration.
Exploratory Data Analysis skill for CSV and parquet datasets with deterministic profiling, drift/anomaly scans, contract generation and validation, and optional memory writeback into skill-system-memory. The implementation is Polars-first (lazy scan for large files and early `--sample` head), includes high-cardinality guards for profile/importance/contract flows, and supports categorical correlation with Cramer's V. Use when building or reviewing tabular fraud/risk/data-quality workflows, profiling new datasets, checking leakage or drift, or saving/validating data contracts.
Generate reproducible analysis artifacts — SQL queries, Python visualizations, and summary tables — as you work through a BigQuery data analysis. Use when asked to conduct a deep dive, exploratory analysis, or investigation that goes beyond a simple data lookup.
Create algorithmic art with seed-based randomness and interactive parameter exploration using p5.js. Use this skill when users request to create art with code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art instead of copying existing artists' works to avoid copyright infringement.