chore: Add AI review guidelines and shared agent skills

[mvadari]

High Level Overview of Change

Both AI reviewers on this repo (Copilot and Ripple's ai-review bot) had only repo orientation to work from, so they defaulted to generic code-review behavior on a repo of prose specs: nits on things prettier and CI already enforce, no coverage of the checks that matter.

• Add a Review Guidelines section to copilot-instructions.md. It defers structural review to the conformity skill and lists what CI already owns, so it cannot drift from templates/.
• Symlink .ai-review/instructions.md to it, so both bots read one file. The Copilot path stays a real file, since GitHub reads it out of the git tree where a symlink blob is just a path string.
• Add two skills under .agents/skills (native to Cursor, Codex, Gemini and Augment), symlinked into .claude/skills for Claude Code: xls-template-conformity and spec-from-rippled.
• Ignore per-developer AI assistant state.

Context of Change

Improved processes using AI

Type of Change

• Infrastructure (CI, workflows, scripts, website)

[xrplf-ai-reviewer]

Documentation/infrastructure-only change adding AI review guidelines, shared agent skills, and symlink wiring. Reviewed the diff for correctness of the new prose, symlink targets, gitignore patterns, and cross-references. No code logic, security, or infrastructure risk found — this is markdown/config content, so most standard review categories don't apply. Only minor documentation-consistency observations, none blocking.

[xrplf-ai-reviewer]

This is a docs/config-only chore (new skill files, symlinks, gitignore entries, and a review-guidelines section added to copilot-instructions.md). Symlink targets were checked and resolve correctly, and the new prose doesn't contain factual contradictions. The one thing worth a second look is a hardcoded XLS number threshold in the new review-guidelines section that will silently go stale as new specs are numbered.

[Copilot]

Pull request overview

This PR improves AI-assisted review quality for XRPL-Standards by documenting repo-specific review guidance (focused on XLS spec defects rather than generic code nits) and adding shared Agent Skills intended to standardize structure/spec validation and spec↔implementation reconciliation workflows.

Changes:

• Updates .github/copilot-instructions.md with AI review guidelines and repository layout notes referencing shared skills and intended bot reuse.
• Adds two shared Agent Skills under .agents/skills/ (xls-template-conformity, spec-from-rippled) including supporting reference material.
• Extends .gitignore to exclude per-developer AI assistant local state files and caches.

Reviewed changes

Copilot reviewed 8 out of 9 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
.gitignore	Ignores per-developer AI assistant local state/caches; includes commentary about what is/ isn’t committed.
.github/copilot-instructions.md	Renames and expands AI agent instructions; adds an AI review guidelines section and references to shared skills/bot reuse.
.agents/skills/xls-template-conformity/SKILL.md	Adds a skill playbook for validating XLS documents against templates and validator tooling.
.agents/skills/xls-template-conformity/references/beyond-the-template.md	Adds manual review checks that templates/validator can’t express (consistency, reality checks, substance).
.agents/skills/spec-from-rippled/SKILL.md	Adds a workflow for reconciling XLS specs against rippled changes with evidence-by-path/line expectations.
.agents/skills/spec-from-rippled/references/rippled-map.md	Adds a mapping guide from rippled artifacts to Amendment-template spec sections.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[xrplf-ai-reviewer]

This MR adds documentation/prose (skills, review guidelines, symlinks, gitignore entries) with no executable code changes. Everything is markdown, config symlinks, or ignore rules. Reviewed all files; found no correctness, security, or infrastructure issues in the changed lines — the content is well-scoped and internally consistent with what CI already enforces. No blocking issues to flag.