Loading...
Loading...
Found 2,695 Skills
Expert guidance for authoring and maintaining Helm charts following standardized conventions, global registry support, templating best practices, and Kubernetes deployment patterns.
Vertex Ai Deployer - Auto-activating skill for ML Deployment. Triggers on: vertex ai deployer, vertex ai deployer Part of the ML Deployment skill category.
Execute use when generating conventional commit messages from staged git changes. Trigger with phrases like "create commit message", "generate smart commit", "/commit-smart", or "/gc". Automatically analyzes changes to determine commit type (feat, fix, docs), identifies breaking changes, and formats according to conventional commit standards.
K6 Script Generator - Auto-activating skill for Performance Testing. Triggers on: k6 script generator, k6 script generator Part of the Performance Testing skill category.
Build, validate, and deploy LLM-as-Judge evaluators for automated quality assessment of LLM pipeline outputs. Use this skill whenever the user wants to: create an automated evaluator for subjective or nuanced failure modes, write a judge prompt for Pass/Fail assessment, split labeled data for judge development, measure judge alignment (TPR/TNR), estimate true success rates with bias correction, or set up CI evaluation pipelines. Also trigger when the user mentions "judge prompt", "automated eval", "LLM evaluator", "grading prompt", "alignment metrics", "true positive rate", or wants to move from manual trace review to automated evaluation. This skill covers the full lifecycle: prompt design → data splitting → iterative refinement → success rate estimation.
Use this skill when crafting, reviewing, or improving prompts for LLM pipelines — including task prompts, system prompts, and LLM-as-Judge prompts. Triggers include: requests to write or refine a prompt, diagnose why an LLM produces inconsistent or incorrect outputs, bridge the gap between intent and model behavior, reduce ambiguity in instructions, add few-shot examples, structure complex prompts, or improve output formatting. Also use when the user needs help distinguishing specification failures (unclear instructions) from generalization failures (model limitations), or when iterating on prompts based on observed failure modes. Do NOT use for general coding tasks, document creation, or non-LLM writing.
Search Product Hunt launches, products, and makers via the GraphQL V2 API. Use when the user asks about Product Hunt launches, trending products, or wants to research a product's reception. Requires a free developer token (~2 min setup).
Create publication-quality matplotlib/seaborn charts with readable axes, tight layout, and curated palettes.
Detect, classify, and QC viral contigs.
Search 2.4M+ full-text PubMed Central Open Access papers for literature reviews, trends, and data extraction.
College Football (CFB) data via ESPN public endpoints — scores, standings, rosters, schedules, game summaries, AP/Coaches rankings, and news for NCAA Division I FBS. Zero config, no API keys. Use when: user asks about college football scores, standings, rankings, team rosters, schedules, game results, or CFB news. Includes AP Top 25, Coaches Poll, and CFP rankings. Don't use when: user asks about NFL (use nfl-data), other college sports (use cbb-data for basketball), or non-sports topics.
Run Docker commands within a container environment, including starting the Docker daemon and managing containers. Use when building, running, or managing Docker containers and images.