Package new software or update existing packages using Nix
Creates or updates Nix packages for software, handling version bumps, hash calculation, and language-specific build configurations. Triggered when you need to package new software or update existing package definitions.
/plugin marketplace add breakds/claude.bds/plugin install bds-dev@claude.bdsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
js/claude-code/package-lock.jsonjs/claude-code/package.nixjs/js.mdpython/agno/package.nixpython/darts/package.nixpython/python.mdpython/swanboard/package.nixpython/tantivy/package.nixpython/tyro/package.nixrust/codex/package.nixrust/rust.mdCreate new Nix packages or update existing ones, with language-specific examples and guidance.
packages in flake.nix).nix build .#<package-name>, read errors, fix issues, and rebuild until successful.Typically, update the version and source fetching attributes (e.g., fetchFromGitHub). The hash field must also be updated using one of these methods:
Method 1: Calculate the new hash directly
# Get the hash
nix-prefetch-url --type sha256 --unpack https://github.com/owner/repo/archive/refs/tags/v<NEW_VERSION>.tar.gz
# Convert to SRI format
nix hash convert --hash-algo sha256 <old-hash>
Method 2: Let Nix tell you the hash
Set hash = ""; and run the build. The error message will display the correct hash.
For language-specific update steps, see the references below.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.