feat: add re-create skill

[Prince-1652]

Pull Request Description

Adds re-create skill, which acts as a controlled erasure and rebuild protocol for AI assistants. It is designed as a last-resort measure when a file, module, or component suffers from deep structural rot or accumulated technical debt that makes it impossible to patch or partially refactor. Instead of compounding the problem with more targeted fixes, this skill forces the AI to fully document the blast radius, preserve essential logic, and require explicit user confirmation before executing a full rewrite.

Change Classification

• Skill PR
• Docs PR
• Infra PR

Issue Link (Optional)

N/A

Quality Bar Checklist ✅

All applicable items must be checked before merging.

• Standards: I have read docs/contributors/quality-bar.md and docs/contributors/security-guardrails.md.
• Metadata: The SKILL.md frontmatter is valid (checked with npm run validate).
• Risk Label: I have assigned the correct risk: tag (none, safe, critical, offensive, or unknown for legacy/unclassified content).
• Triggers: The "When to use" section is clear and specific.
• Limitations: The skill includes a ## Limitations (or equivalent accepted constraints) section.
• Security: If this is an offensive skill, I included the "Authorized Use Only" disclaimer.
• Safety scan: If this PR adds or modifies SKILL.md command guidance, remote/network examples, or token-like strings, I ran npm run security:docs (or equivalent hardening check) and addressed any findings.
• Automated Skill Review: If this PR changes SKILL.md, I checked the skill-review GitHub Actions result and addressed any actionable feedback.
• Manual Logic Review: If this PR changes SKILL.md or risky guidance, I manually reviewed the logic, safety, failure modes, and risk: label instead of relying on automated checks alone.
• Local Test: I have verified the skill works locally.
• Repo Checks: I ran npm run validate:references if my change affected docs, workflows, or infrastructure.
• Source-Only PR: I did not manually include generated registry artifacts (CATALOG.md, skills_index.json, data/*.json) in this PR.
• Credits: I have added the source credit in README.md (if applicable).
• License provenance: If this skill imports from an external source_repo, I have declared license: and license_source: in the frontmatter, or confirmed the upstream repo carries no restricting license.
• Maintainer Edits: I enabled Allow edits from maintainers on the PR.

Screenshots (if applicable)

N/A