2.1K skills · sorted by relevance
Create or improve skills for Codewhale by defining their scope, writing clear activation descriptions and workflows, organizing supporting files, and checking discovery. It also helps decide when an external integration or automatic event handler is more appropriate.
Retrieve earlier decisions, preferences, and saved resources from OpenViking across sessions. Store durable information, import documents or repositories, and manage deletion, with guidance on how project memory is shared between directories and repository clones.
Turn recurring procedures and specialized knowledge into reusable agent skills. It guides the design of SKILL.md, scripts, reference documents, and output assets, then validates the structure and packages the files for distribution.
Review GitHub Actions workflows for unsafe input handling, excessive token permissions, exposed secrets, and changeable action references. Get findings grouped by issue type, with severity ratings, exact YAML locations, and concrete fixes to review.
Generate an .editorconfig file tailored to a project's file types and formatting preferences. Set indentation, line endings, character encoding, and whitespace rules, with a clear explanation of each choice to support consistent formatting across editors.
Convert PDF text and tables into Markdown for later summarizing, searching, or data extraction. Embedded images are saved separately and grouped by page in an appendix. Process individual files or entire folders, including subfolders.
Convert Word documents into Markdown text for summarizing, searching, comparing, or extracting information. The bundled script saves embedded images alongside each document and supports processing entire folders, including subfolders, before the agent analyzes the converted content.
Convert Excel workbooks into Markdown tables organized by sheet, preparing their contents for reading, summarizing, searching, or extracting data. The bundled script also extracts embedded pictures and processes folders of workbooks, including subfolders when requested.
Learn GitHub Copilot CLI through interactive lessons for developers and non-developers. Practice prompts, permissions, file references, and task planning, with progress tracking and answers to specific questions as you work through the material.
Organize SGLang GPU operations when adding or moving code. It guides API placement, operation registration, test organization, and migration checks to preserve existing behavior, references, and continuous integration coverage.
Turn books and documents into reusable agent skills by extracting frameworks, decision rules, techniques, and mistakes to avoid. Generate structured skill files with chapter references and glossaries, or review an analysis before creating files.
Review a diffusers contribution before opening a pull request. Check the full change against project rules, trace potentially unused code, and receive a severity-based report separating required fixes from points to discuss with reviewers.
Investigate repository behavior, architecture, or possible causes without changing files. Trace relevant code and supporting material, then rank explanations by evidence and confidence, with concrete file references and clear distinctions between observations, conclusions, and unresolved questions.
Builds or restyles interfaces against an approved image or live web page. It guides repeated visual checks and pixel comparisons, then preserves reusable styling rules and components alongside screenshots and verification evidence.
Design visually distinctive websites, landing pages, and portfolios as React components, reusable pieces of a web page. Use industry references to guide typography, color, layout, motion, and relevant 3D visuals that fit the brand.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Plan and configure large language model training with OpenRLHF to better match human preferences. Covers training method selection, distributed GPU setup, inference acceleration with vLLM, and troubleshooting memory or training stability issues.
Look up people, companies, and topics in an existing knowledge base before answering. Save authorized information with source references, update related pages and timelines, and maintain links that connect each record to its context.
Extract references between imported documents and classify how they relate, such as relying on, extending, or refuting another work. Store these relationships as typed links so explicit graph queries can trace connections through the collection.
Create, update, validate, and reorganize Agent Skills stored in a repository. It covers SKILL.md metadata, reference files, compatibility links, and validation scripts, supporting maintenance of skill folders, categories, and instructions for agents.
Review documentation, READMEs, guides, or prose against the good-docs-writing style rules. Receive structured findings with file and line references, quoted passages, and concrete rewrites. Files are edited only when explicitly requested.
Design, implement, and review Composio CLI commands, including user interactions, output, errors, and configuration. It guides command wiring and service changes using Effect and effect/cli, with references for implementation patterns.
Maintain Composio's documentation site and record documentation decisions. Work on content, Fumadocs configuration, changelogs, automation prompts, and review guidance, including ADR-style records that capture decisions and their rationale.
Prepare an English pull request title, description, and branch suggestion from completed local changes. It reviews Git changes, includes untracked files, and formats issue references so the draft is ready to paste into GitHub.