[FEATURE] Improve CLAUDE.md generation prompt and add prompt loading for future LLM integrations

[ddjain]

Problem Statement

Improve the system prompt used to generate CLAUDE.md and introduce a dedicated prompt-loading approach so we can manage multiple LLM system prompts cleanly as the project grows.

Proposed Solution

• Refine the generator prompt for clearer instructions, constraints, and quality checks.
• Content is now maintained in prompts/claude_md_generator.md instead of an inline Python string.

Prompt loading arrangement

• Add src/agentready/prompts/ package with a load_prompt(name) utility (reads .md files via importlib.resources).
• Move the CLAUDE.md generator prompt into prompts/claude_md_generator.md and wire the fixer to use load_prompt("claude_md_generator").
• Build the Claude CLI command with safe shell quoting (shlex.quote) instead of f-string interpolation.
• Remove the old inline prompt and commented-out block from fixers/documentation.py.
• Include prompts/*.md in package data so prompts are shipped with the package.

Alternatives Considered

A clear and concise description of any alternative solutions or features you've considered.

Acceptance Criteria

• User should be able to generate high quality CLAUDE.md and AGENTS.md file

Priority

How important is this feature to you?

• Critical (blocking my work)
• High (significantly improves workflow)
• Medium (nice to have)
• Low (minor enhancement)

[github-actions]

🎉 This issue has been resolved in version 2.27.2 🎉

The release is available on GitHub release

Your semantic-release bot 📦🚀