Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Provides a collection of role-based and task-specific prompt templates. Includes ready-to-use examples for coding, writing, analysis, and creative tasks, alongside prompt refinement techniques.
Maintains reusable prompts that produced strong results for ReVision tools or Claude Code tasks in the repository. Helps look up existing prompts before recreating them.
Helps find AI prompts and reusable prompt templates through prompts.chat. Supports retrieving relevant prompts and improving them for the user's needs.
Transforms vague prompts or feature requests into precise, testable specifications using EARS (Easy Approach to Requirements Syntax) grounded in relevant domain theories (GTD, BJ Fogg, Gestalt). Use when requirements lack triggers or measurable outcomes, or the user asks to "optimize my prompt" / "improve this requirement" / "make this more specific".
Improves prompt wording and reliability through iterative refinement. Covers agent, system, and developer prompts, reusable templates, migration between OpenAI, Claude, and Gemini, and prompt evaluations.
Provides prompting techniques for Replicate video generation models. Applies to writing video prompts and building video generation features.
Creates evaluation configurations, Python custom assertions, and LLM-as-judge rubrics. Supports prompt testing, model comparisons, and management of few-shot examples.
Covers rates, aggregations, label matching, histogram quantiles, guarded ratios, staleness detection, and forecasting. Validates and optimizes queries, designs recording rules and burn-rate calculations, and investigates excessive cardinality.
Runs instant and range PromQL queries against Prometheus-compatible engines and discovers metrics, labels, and metadata. Provides table, CSV, JSON, and graph output for investigating latency, errors, saturation, and time series.
Uses Proof's web API to create documents, suggest edits, add comments, share review links, and run human-in-the-loop review cycles. Supports Proof URLs and synchronization of Proof documents to local files.
Produces test files, property-based tests, and state machine tests from Allium specifications. Helps identify required tests and compare coverage against specification obligations.
Creates and evaluates property-based tests with Hypothesis, fast-check, proptest, jqwik, rapid, Echidna, and Medusa. Covers generators, meaningful assertions, and distinguishing incorrect properties from genuine bugs in minimized counterexamples.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name