Loading...
Loading...
Found 133 Skills
Use this skill when creating new files that represent architectural decisions — data models, infrastructure configs, auth boundaries, API contracts, CI/CD pipelines, or event systems. Flags irreversible decisions and forces a discussion about trade-offs before committing.
Use Beads (bd tool) for dependency-aware task tracking and long-horizon planning in coding projects. This skill should be used when working on complex multi-step projects that span multiple agent sessions, when discovering new work during implementation, or when explicit task dependency management would improve workflow organization and prevent context loss between sessions.
UV/UVX/Ruff toolchain for DiscoHy Thread Operad with Python packaging and linting
Guide for creating and managing Claude Code plugin marketplaces. Use when setting up a marketplace, validating marketplace.json, or distributing plugins.
Organize and clean up scripts and dependencies in package.json. Use this for requests such as 'I want to clean up package.json', 'I want to organize scripts', or 'I want to remove unused dependencies'. Specifically, it targets the following: (1) Delete or integrate redundant scripts (aliases/passthroughs), (2) Explicitize implicit lifecycle hooks (pre/post), (3) Unify script naming conventions, (4) Detect and remove unused dependency packages, (5) Update documents and CI following script name changes, (6) Regenerate lock files after removing dependencies.
Use this skill when the user wants to manage Python projects, virtual environments, or dependencies using uv, including creating venvs, installing packages, syncing environments, or running Python tools.
Use when working with Python projects that use uv for dependency management, virtual environments, project initialization, or package publishing. Covers setup, workflows, and best practices for uv-based projects.
Effect-TS (Effect) guidance for TypeScript. Use when building, refactoring, reviewing, or explaining Effect code, especially for: typed error modeling (expected errors vs defects), Context/Layer/Effect.Service dependency wiring, Scope/resource lifecycles, runtime execution boundaries, schema-based decoding, concurrency/scheduling/streams, @effect/platform APIs, Effect AI workflows, and Promise/async migration.
Convert project plans to JSONL format (issues + dependencies). Use when users ask "convert plan to jsonl", "create jsonl from plan", "export plan as json" or "convert plan to taks", "create tasks from plan", "export plan as tasks".
Modern Python development with uv, the fast Python package and project manager. Covers project management (uv init, uv add, uv sync, uv lock), virtual environments, Python version management (uv python install/pin), script runners (uv run), tool management (uvx), workspace support for monorepos, and publishing to PyPI. Includes Python patterns for FastAPI, Pydantic, async/await, type checking, pytest, structlog, and CLI tools. Use when initializing Python projects, managing dependencies with uv, configuring pyproject.toml, setting up virtual environments, running scripts, managing Python versions, building monorepos with workspaces, containerizing Python apps, or writing modern Python with type hints.
Python single-file script development using uv and PEP 723 inline metadata. Prevents invalid patterns like [tool.uv.metadata]. Use when creating standalone Python utilities, converting scripts to uv format, managing script dependencies, implementing script testing, or establishing team standards for script development.
Before running Python scripts or installing packages, check for existing virtual environments and reuse them if found. If no virtual environment exists, ask the user to choose: (1) Create new venv in current directory (recommended), (2) Use system Python directly, or (3) Create venv at custom path. This applies to: running .py files, using pip/uv pip install, or any task requiring third-party packages. Exceptions: simple one-liners using only Python standard library.