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.Enables video understanding through native passthrough for small files. For larger files, it falls back to frame extraction and audio transcription to support descriptions, summaries, and recording transcripts.
Uses a modeling report to write reproducible code, run solvers, and verify constraints. Produces a results report and data-driven PDF charts suitable for inclusion in a paper.
Helps choose agent or completion mode and create a LaunchDarkly config. Covers adding variations with models and prompts and verifying the setup.
Create copy for user interfaces where the words themselves are the deliverable. Cover microcopy, error messages, empty states, and calls to action.
Examines Django views, DRF viewsets, ORM queries, and Python code that handles user authorization. Focuses on object permissions, tenant isolation, IDOR, and broken access controls.
Organizes coding tasks as Markdown specifications that move through inbox, active, and archive stages. Claude Code or Codex implements tasks, which must pass a review gate; also covers installing and scaffolding the loop-factory CLI.
Uses Microsoft MarkItDown for local and batch conversion of Office, PDF, and data formats. Covers streams, plugins, vision OCR, Azure extraction, and the official MCP server.
Supports systematic experimentation with configuration variations. Helps test different models, prompts, and parameters to identify which performs best.
Covers PostgreSQL query optimization, indexing, partitioning, replication, backups, recovery, and production operations. Includes MVCC, VACUUM, connection pooling, monitoring, high availability, and scaling patterns.
Determine the appropriate prototype fidelity and method before building. Align the approach with the design question and the decision the prototype should inform.
Define a single library component in a detailed specification. Cover its props, states, variants, accessibility requirements, and usage rules.
Assess an existing design or implemented interface against WCAG. Produce accessibility findings with severity ratings and steps to resolve them.
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