Search for package-specific usage rules and best practices from Elixir packages. Use when you need coding conventions, patterns, common mistakes, or good/bad examples for packages like Ash, Phoenix, Ecto, etc.
/plugin marketplace add bradleygolden/claude-marketplace-elixir/plugin install elixir@elixirThis skill is limited to using the following tools:
README.mdFind package-specific best practices and coding conventions from usage-rules.md files.
A community convention where packages include a usage-rules.md file with:
# GOOD, # BAD, # AVOID)deps/<package>/usage-rules.md.usage-rules/<package>-<version>/usage-rules.mdPrimarily the Ash ecosystem:
ash, ash_postgres, ash_phoenix, ash_json_api, ash_graphqlspark, igniter, reactorMost packages (Phoenix, Ecto, etc.) do not have usage-rules.md yet. For those, suggest hex-docs-search skill or official guides.
# Fetch package and extract usage-rules.md
mix hex.package fetch <package> <version> --unpack --output .usage-rules/.tmp/<package>-<version>
# If usage-rules.md exists, copy to cache
if [ -f ".usage-rules/.tmp/<package>-<version>/usage-rules.md" ]; then
mkdir -p ".usage-rules/<package>-<version>"
cp ".usage-rules/.tmp/<package>-<version>/usage-rules.md" ".usage-rules/<package>-<version>/"
fi
# Clean up
rm -rf ".usage-rules/.tmp/<package>-<version>"
Mention adding .usage-rules/ to .gitignore once per session when fetching occurs.
Usage rules files can be large. Extract relevant sections based on user's question:
| User Context | Look for Sections |
|---|---|
| querying, filters | "Querying", "Filters", "Read Actions" |
| actions, create/update | "Actions", "Changes", "Validations" |
| relationships | "Relationships", "Aggregates" |
| errors, validation | "Error Handling", "Validations" |
| authorization | "Policies", "Authorization" |
| testing | "Testing" |
Find section headings with line numbers, then extract the relevant section content.
# GOOD vs # BAD patterns explicitlyhex-docs-search for API documentation (complementary)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.