Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
workflow
Standard workflow for implementing features with specs and planning documents. Use when the user says "start a new feature", "how should I plan this", "what's the process", or when starting implementation, planning work, or working on any non-trivial task.
EpicenterHQ/epicenter 4,333
-
styling
CSS and Tailwind styling guidelines for this codebase. Use when the user says "style this", "fix the CSS", "add classes", or when writing Tailwind utilities, using cn(), creating UI components, reviewing CSS code, or deciding on wrapper element structure.
EpicenterHQ/epicenter 4,333
-
testing
Test file conventions for setup functions, factory patterns, test organization, type testing, and naming. Use when the user says "write tests", "add a test", "fix this test", or when writing or modifying *.test.ts files, creating test setup functions, or reviewing test structure.
EpicenterHQ/epicenter 4,333
-
karpathy-mode
This skill should be used to enforce a disciplined coding workflow that avoids common LLM mistakes. It applies when writing code, implementing features, or when the user says /karpathy, /k-mode, or asks for "careful", "disciplined", or "minimal" implementation. Enforces assumption surfacing, simplicity-first coding, surgical changes, and test-driven execution.
adryanev/.dotfiles 2
-
disciplined-work
This skill should be used to execute work plans with strict coding discipline that avoids common LLM mistakes. It merges structured plan execution (phased workflow, incremental commits, quality checks) with disciplined coding guardrails (assumption surfacing, simplicity-first, surgical changes, test-driven execution). Triggers on /disciplined-work, /k-work, "disciplined work", or "careful work".
adryanev/.dotfiles 2
-
github-issues-from-spec
This skill transforms feature specifications, requirements documents, or plans into well-structured GitHub issues. It chunks large features into small, testable issues, creates them via gh CLI, and adds them to the appropriate GitHub project with labels. Use when converting specs to actionable issues.
adryanev/.dotfiles 2
-
test-endpoints
This skill automates API endpoint testing and documentation. It runs curl requests against specified endpoints, captures responses, validates against OpenAPI spec, and generates markdown documentation. Use after implementing new endpoints or when verifying API behavior.
adryanev/.dotfiles 2
-
new-go-endpoint
This skill automates the API-first workflow for creating new Go API endpoints. It handles OpenAPI spec updates, code generation, SQLC query creation, handler implementation, and Redis caching patterns. Use when adding new endpoints to the Lexicon backend.
adryanev/.dotfiles 2
-
troubleshooting
Systematic debugging and problem diagnosis using structured troubleshooting methodologies
applicable to any domain - technical issues, process failures, system problems, or general
obstacles. Use when users report errors, describe malfunctions, encounter unexpected behavior,
or need help diagnosing root causes. Triggers include 'debug this,' 'troubleshoot,' 'why isn't
this working,' 'getting an error,' 'something's wrong with,' 'how do I fix,' or any problem
description.
jkitchin/skillz 23
-
citation-verifier
Verify citations and references in scientific documents to detect hallucinated or invalid sources.
Extracts DOIs, URLs, arXiv IDs, PubMed IDs, and ISBNs from Markdown, LaTeX, org-mode, and plain text,
then validates them using API lookups and web fetches.
Use this skill when:
- Reviewing AI-generated content for citation accuracy
- Validating references in papers, reports, or documentation
- Checking if DOIs/URLs resolve to actual papers
- Auditing a document for broken or fake citations
jkitchin/skillz 23
-
pycse
Use when performing regression analysis with confidence intervals, solving ODEs, fitting models to experimental data, or caching expensive scientific computations - provides convenient wrappers around scipy that automatically calculate confidence intervals and prediction bounds for linear, nonlinear, and polynomial regression
jkitchin/skillz 23
-
planning
Structured planning and project breakdown using proven methodologies for goals, projects,
and strategic initiatives. Use when users need to create plans, break down complex projects,
set milestones, estimate timelines, identify dependencies, or develop action plans.
Triggers include 'help me plan,' 'create a roadmap for,' 'break down this project,'
'what are the steps to,' or 'how should I approach.'
jkitchin/skillz 23
-
version-control
Expert guidance for Git version control, trunk-based development workflows, and GitHub best practices.
Emphasizes Conventional Commits for clean history, short-lived feature branches, frequent integration,
and professional collaboration patterns. Use when users need help with git commands, branching strategies,
commit messages, PRs, merge conflicts, or git troubleshooting. Triggers include 'git,' 'commit,' 'branch,'
'merge,' 'rebase,' 'PR,' 'pull request,' or version control questions.
jkitchin/skillz 23
-
tdd
Test-Driven Development facilitation using the red-green-refactor cycle. Guides users through
writing tests first, implementing minimal code to pass, and refactoring for quality. Use when
users want to practice TDD, need help writing tests before code, are developing new features
test-first, or want guidance on test structure and implementation. Triggers include 'use TDD,'
'test-driven development,' 'write tests first,' 'red-green-refactor,' or requests to develop
functionality with tests.
jkitchin/skillz 23
-
code-reviewer
Comprehensive code review and analysis for software quality assurance. Use when Claude needs to review code in any format including (1) Individual files (Python, R, JavaScript, etc.), (2) Directory structures and project organization, (3) Scripts and automation code, (4) Jupyter notebooks and data analysis workflows, (5) Documentation assessment and improvement suggestions, (6) Bug detection and logic verification, (7) Testing coverage and strategy evaluation, (8) Code consistency and maintainability analysis. Provides actionable improvement recommendations across all aspects of software development.
jkitchin/skillz 23
-
ralph-wiggum
Autonomous AI coding loop for unattended development - lets Claude work continuously on tasks while you sleep, with mandatory sandbox enforcement for safety
jkitchin/skillz 23
-
brainstorming
Structured brainstorming and ideation facilitation using proven creativity techniques.
Use when users want to generate ideas, explore solutions, break through creative blocks,
or need facilitated ideation sessions. Triggers include requests like 'help me brainstorm,'
'generate ideas for,' 'creative solutions to,' or 'think of alternatives.'
jkitchin/skillz 23
-
video-storytelling
Create coherent video story sequences with AI-generated images and narrated audio.
Combines image-generation and elevenlabs skills to produce complete video stories with
visual and narrative consistency across all scenes. Maintains character appearance,
style, lighting, and voice consistency throughout the story.
Use this skill when the user requests:
- Video stories with narration
- Animated story sequences
- Educational video content
- Character-driven narratives with visuals
- Multi-scene story videos
- Narrated image sequences
Features: Visual consistency locks, character persistence, multi-turn image generation,
character voice narration, automatic video assembly
Default: 1 title scene + 5 story scenes
Dependencies: image-generation skill, elevenlabs skill, ffmpeg
jkitchin/skillz 23
-
presentations
Create slide presentations in multiple formats: Marp (Markdown, default), Beamer (LaTeX),
Jupyter Notebook slides, and PowerPoint (python-pptx). Supports scientific, business, and
developer content with math, code, charts, and tables. Converts existing documents into slides
or creates from scratch. Auto-compiles to PDF/HTML/PPTX.
Use this skill when the user requests:
- Creating a presentation or slide deck
- Converting a document, paper, or report into slides
- Making conference talk, lecture, or meeting slides
- Generating PowerPoint, PDF slides, or HTML slideshows
- Beamer, Marp, reveal.js, or notebook slideshow creation
jkitchin/skillz 23
-
image-generation
AI-powered image generation and editing using Google Gemini, Google Imagen, and OpenAI models.
Generate images from text descriptions, edit existing images, create logos/stickers,
apply style transfers, and produce product mockups.
Use this skill when the user requests:
- Image generation from text descriptions
- Image editing or modifications
- Logos, stickers, or graphic design assets
- Product mockups or visualizations
- Style transfers or artistic effects
- Iterative image refinement
Available models:
- Google Gemini: gemini-2.5-flash-image (Nano Banana), gemini-3-pro-image-preview (Nano Banana Pro)
- Google Imagen: imagen-4.0-generate-001, imagen-4.0-ultra-generate-001, imagen-4.0-fast-generate-001
- OpenAI: gpt-image-1.5 (recommended), gpt-image-1, dall-e-3, dall-e-2
Inspired by: https://github.com/EveryInc/every-marketplace/tree/main/plugins/compounding-engineering/skills/gemini-imagegen
jkitchin/skillz 23
-
elevenlabs
AI-powered audio generation using ElevenLabs API - text-to-speech with lifelike voices,
sound effects generation, and music creation from text descriptions. Generate natural-sounding
speech in 32 languages, create custom sound effects for games and videos, and compose
royalty-free music tracks.
Use this skill when the user requests:
- Voice generation or text-to-speech conversion
- Audio narration for content (videos, audiobooks, podcasts)
- Sound effects for games, videos, or applications
- Music generation from text descriptions
- Multi-speaker dialogue or conversation audio
- Voice cloning or custom voice creation
- Audio streaming for real-time applications
Capabilities: Text-to-speech (32 languages, 100+ voices), sound effects generation,
music composition, voice cloning, real-time audio streaming
Python SDK: elevenlabs (pip install elevenlabs)
jkitchin/skillz 23
-
python-ase
Expert assistance with the Atomic Simulation Environment (ASE) Python library for atomistic simulations, including structure building, calculator setup, optimization, dynamics, and analysis
jkitchin/skillz 23
-
python-best-practices
Expert guidance for writing professional Python code following industry best practices
including PEP 8 compliance, testing, type hints, error handling, and modern tooling.
Use this skill when writing new Python code, refactoring existing code, setting up
Python projects, implementing tests, or ensuring code quality and maintainability.
Emphasizes: PEP 8, modularity, DRY principle, TDD, virtual environments (uv),
and modern tooling (Ruff, Black, Mypy).
jkitchin/skillz 23
-
materials-properties
Expert assistant for calculating materials properties from first-principles using ASE - structure relaxation, surface energies, adsorption, reaction barriers, phonons, elastic constants, and thermodynamic modeling with proper scientific methodology
jkitchin/skillz 23