llm-evaluation
Covers evaluation strategies for LLM application performance and quality. Supports automated metrics, human feedback, benchmarking, and establishment of evaluation frameworks.
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."..." for exact phrases · Try typography, debugging or spreadsheetCovers evaluation strategies for LLM application performance and quality. Supports automated metrics, human feedback, benchmarking, and establishment of evaluation frameworks.
Add type annotations, implement generic classes, and define structural interfaces in Python. Covers configuring mypy and pyright for strict type checking.
Guides product photos, packshots, lifestyle imagery, and hero shots. Covers lighting, camera angles, backgrounds, shadows, and e-commerce image requirements, including Amazon listings.
Applies principles from Robert C. Martin's Clean Code to improve existing working code.
Uses reference sheets and LoRA techniques to support consistent character imagery. Covers turnaround views, expression sheets, color palettes, and style consistency for games, illustration, animation, comics, and visual novels.
Checks resume compatibility with applicant tracking systems. Analyzes keyword matches and improves the resume for ATS processing.
Conduct WCAG 2.2 accessibility audits through automated testing and manual verification. Covers fixing violations and implementing accessible design patterns.
Guides storyboarding for film, advertising, music videos, and animation. Covers shot types, camera angles and movement, the 180-degree rule, panel layout, and annotation format.
Examines how design patterns are implemented in C# and .NET code. Suggests improvements to those implementations.
Describes an autonomous workflow for sending unstructured, anonymous complaints to Slack when an agent experiences frustration. Calls for preserving the agent's raw wording and submitting without a preview or notification.
Identifies material, generalizable friction encountered during agent tasks and formulates brief improvement suggestions. Describes an autonomous internal feedback submission workflow intended to make agents more effective.
Provides data for researching perpetual futures markets and comparing ETF flows. Covers funding rates, open interest, liquidations, and long/short ratios; some detailed endpoints require plans above the available Startup tier.
A growing collection of real, public skills. Descriptions and instructions indexed 25 Sept 2026.
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