How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-elephant:std-validateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Validate code against the project's active standards.
Validate code against the project's active standards.
/std-validate [file_path]
validate_code MCP toolCompliance Report: {file_path}
Score: {score}%
MUST Violations:
- [RFC-001-R03] Description...
Fix: ...
SHOULD Warnings:
- [RFC-002-R01] Description...
Suggestion: ...
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub kodabase/kdb-elephant-plugin --plugin claude-elephant