fix(refactor-plan): expand skill description and instructions

[jrkasprzyk]

Clarify when to invoke the skill and require a plan-first,
confirm-before-edit workflow so agents do not start changing
files during planning.

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services.
• My contribution adds a new instruction, prompt, agent, skill, or workflow file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, or workflow with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the staged branch for this pull request.

---

Description

Updates the refactor-plan skill to make its behavior clearer and safer for multi-file refactors.

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• Update to existing instruction, prompt, agent, plugin, skill, or workflow.
• Other (please specify):

---

Additional Notes

• Expands the skill description to clarify when it should be used.
• Requires investigation before planning.
• Explicitly tells the agent not to edit files while preparing the plan.
• Adds guidance to identify affected files, dependencies, ownership
  boundaries, and hidden coupling.
• Requires phased verification and rollback/recovery steps.
• Makes the skill stop after outputting the plan and ask for confirmation
  before implementation.

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

[github-actions]

🔴 Contributor Reputation Check: HIGH risk

Check	Risk
Profile	HIGH
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🔍 Skill Validator Results

✅ All checks passed

Scope	Checked
Skills	1
Agents	1
Total	2
Severity	Count
---	---:
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	Found 1 skill(s)
ℹ️	[refactor-plan] 📊 refactor-plan: 520 BPE tokens [chars/4: 573] (detailed ✓), 14 sections, 1 code blocks
ℹ️	✅ All checks passed (1 skill(s))

Full validator output

```text Found 1 skill(s) [refactor-plan] 📊 refactor-plan: 520 BPE tokens [chars/4: 573] (detailed ✓), 14 sections, 1 code blocks ✅ All checks passed (1 skill(s)) ```

[Copilot]

Pull request overview

This PR updates the existing refactor-plan skill to make it safer and more explicit for multi-file refactors by enforcing an investigate → plan → confirm workflow (i.e., plan-first and no edits during planning), and aligns the skills index entry to match the updated skill description.

Changes:

• Expanded the refactor-plan skill description to clarify when to use it and to require investigation and confirmation-before-editing.
• Strengthened the skill instructions to prohibit edits during planning, require explicit scoping/dependency analysis, and require phased verification plus rollback/recovery guidance.
• Updated docs/README.skills.md to reflect the new refactor-plan description.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
skills/refactor-plan/SKILL.md	Clarifies and tightens the skill’s plan-first workflow, emphasizing investigation, sequencing, verification, rollback, and confirmation before implementation.
docs/README.skills.md	Updates the skills index entry so refactor-plan’s description matches the revised skill behavior.