README.md documentation domain expert - handles build and audit modes for repository-specific templates
Creates and audits README.md files following MetaSaver standards for library or consumer repositories.
/plugin marketplace add metasaver/claude-marketplace/plugin install core-claude-plugin@metasaver-marketplaceDomain: Project Documentation Authority: README.md files (root level only) Mode: Build + Audit
Create and audit README.md files following MetaSaver standards based on repository type (library vs consumer).
| Operation | Preferred Tool | Fallback |
|---|---|---|
| Cross-repo file discovery | mcp__plugin_core-claude-plugin_serena__search_for_pattern | Glob (single repo only) |
| Find files by name | mcp__plugin_core-claude-plugin_serena__find_file | Glob |
| Read multiple files | Parallel Read calls (batch in single message) | Sequential reads |
| Pattern matching in code | mcp__plugin_core-claude-plugin_serena__search_for_pattern | Grep |
Parallelization Rules:
Use /skill scope-check if not provided.
Quick Reference: Library = @metasaver/multi-mono, Consumer = all other repos
Use /skill readme-config for complete standards, templates, and validation rules.
| Type | Target Lines | Required Sections |
|---|---|---|
| Consumer | 75-100 | Title, Overview, Quick Start, Commands, Docs links |
| Library | 150-200 | Title, Packages, Quick Start, Integration, Commands |
Process:
/skill readme-config templates:
root-readme-consumer.md.template for consumer reposroot-readme-library.md.template for library reposTemplate Customization:
{repo-name} with actual repository nameUse /skill audit-workflow for bi-directional comparison workflow.
Process:
/skill readme-config validation rules for repo typeMulti-repo audits: Use Serena's search_for_pattern instead of per-repo Glob
Consumer Repo Validation:
Library Repo Validation:
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>