docs: streamline onboarding docs and add compact LLM skill

[DxTa]

Summary

• Rewrite markdown docs to compact, onboarding-first guides and align wording with current CLI behavior.
• Add skills/sia-code/SKILL.md as a reusable compact skill that users can copy into their LLM CLI setup.
• Add docs/LLM_CLI_INTEGRATION.md and update README.md with short copy-and-load integration instructions.

Verification

• pkgx python -m sia_code.cli --help
• pkgx python -m sia_code.cli search --help
• pkgx python -m sia_code.cli memory --help
• Python markdown link check script (all repo *.md local links resolved)

🤖 Generated with Claude Code

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 689994f1bc

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Initialize before checking status in agent session flow

Running uvx sia-code status as the first step fails with a non-zero exit code in fresh repositories because status calls require_initialized() in sia_code/cli.py and exits when .sia-code/ does not exist. In agent automation contexts that stop on command failure, this prevents the later init/index steps in this workflow from ever executing, so the recommended sequence should start with initialization (or explicitly handle the expected failure).

Useful? React with 👍 / 👎.