How this command is triggered — by the user, by Claude, or both
Slash command
/repo-structure:repo-improve [--category=security|docs|ci|community] [--aggressive]This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# Repository Improve Command Apply targeted improvements to specific quality categories. ## Behavior 1. If `--category` specified → improve that category 2. If no category → show interactive menu with recommendations 3. Use appropriate skills (repository-templates, automation-strategies) 4. Report score improvement ## Usage ## Workflow **Interactive mode (no --category):** 1. Calculate current score 2. Present menu: 3. Apply selected improvements **Direct mode (with --category):** 1. Analyze category gaps 2. Propose specific improvements 3. Apply after approval (skip if --aggre...
Apply targeted improvements to specific quality categories.
--category specified → improve that category/repo-improve --category=security # Security improvements only
/repo-improve --aggressive # Apply without prompts
/repo-improve # Interactive menu
Interactive mode (no --category):
Select categories to improve:
[ ] Documentation (+5 pts potential)
[ ] Security (+10 pts potential)
[ ] CI/CD (+8 pts potential)
[ ] Community (+6 pts potential)
Direct mode (with --category):
Report before/after scores.
npx claudepluginhub nsalvacao/nsalvacao-claude-code-plugins --plugin repo-structure/candid-improve-implementationReviews code implementation for approach, clarity, quality improvements; suggests next-version enhancements, supports selection/application with tone, focus, exclude flags, and optional auto-commit.
/improveApplies systematic improvements to code quality, performance, maintainability, and style on target files or directories. Supports --type, --safe, --preview flags.
/sc-improveApplies systematic improvements to code quality, performance, maintainability, and security in target files or directories using multi-persona analysis. Produces validation, summary, and recommendations.
/analyze-and-create-issueAnalyzes codebase for improvements (optionally focused on a domain like security, performance) and creates GitHub or GitLab issues after user confirmation per finding.
/improveImproves code quality, performance, maintainability, or style in a target via analysis, multi-persona refactoring, validation, and documentation. Supports [target], --type, --safe, --interactive flags.
/harness-auditRuns a deterministic repository audit across configurable scopes (repo, hooks, skills, commands, agents) and returns a prioritized scorecard with category scores, failed checks, and top actions.