skill-forge

In the author's own words, from each skill's SKILL.md.

• example-skill

  Example skill that does nothing

  examples/example-skill/SKILL.md on GitHub (opens in a new tab)

• conda-forge

  Performs conda-forge operations. Fixes failing builds by analyzing CI logs, creates new packages via staged-recipes, adds native ARM CI support or explicit cross-compilation to feedstocks, and migrates recipes from v0 to v1 format. Use when working with conda-forge feedstocks, staged-recipes, build failures, recipe migrations, or when the user mentions conda-forge.

  recipes/conda-forge/SKILL.md on GitHub (opens in a new tab)

• matplotlib-data-visualization

  Chart design and data storytelling guidelines for matplotlib. Use when creating visualizations that need to communicate a clear message, tell a story with data, or follow best practices for readability and design. Focuses on visualization principles rather than matplotlib API syntax.

  recipes/matplotlib-data-visualization/SKILL.md on GitHub (opens in a new tab)

• pr-review

  Interactive PR review workflow. Reads existing PR comments (including pending review drafts) before reviewing, drafts severity-grouped findings into a markdown file, iterates with the human, and only after explicit approval pushes them as a pending review on GitHub. Never submits the review — the human writes the summary and submits in the UI.

  recipes/pr-review/SKILL.md on GitHub (opens in a new tab)

• presentation-design

  Slide design and storytelling guidelines for creating presentations. ALWAYS load this skill when the user wants to create, review, or improve presentation slides — regardless of tool (Typst/Polylux, Beamer, PowerPoint, Google Slides, reveal.js, etc.).

  recipes/presentation-design/SKILL.md on GitHub (opens in a new tab)

• pydantic-evals

  Guidelines for evaluating non-deterministic functions with pydantic-evals. Use when writing evals, defining datasets and cases, creating custom evaluators, or testing AI agent outputs with pydantic-evals.

  recipes/pydantic-evals/SKILL.md on GitHub (opens in a new tab)

• rattler-build

  Build conda packages with rattler-build: create new recipes, build and debug them, create patches, and inspect built packages. Use when working with rattler-build recipes, conda package building, or when the user mentions rattler-build.

  recipes/rattler-build/SKILL.md on GitHub (opens in a new tab)

• sqlalchemy

  Python SQL toolkit and Object Relational Mapper (ORM). Use when working with databases in Python, defining models, building queries, managing sessions, or interacting with SQL databases using Python objects.

  recipes/sqlalchemy/SKILL.md on GitHub (opens in a new tab)

• textual

  Build terminal user interfaces (TUIs) with Textual, a Python framework for creating rich, interactive applications in the terminal. Handles widgets, layouts, CSS styling, events, screens, and async workers. Use when building TUI apps or when the user mentions textual.

  recipes/textual/SKILL.md on GitHub (opens in a new tab)

• typst

  Create beautifully typeset documents with Typst, a modern markup-based typesetting system. Handles academic papers, scientific documents, mathematical equations, tables, and document layouts. Use when creating PDFs, typesetting documents, or when the user mentions typst, document formatting, or mathematical typesetting.

  recipes/typst/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• superpowersby obra An agentic skills framework & software development methodology that works. 300k stars · 15 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 293k stars · 30 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 181k stars · 19 skills