Add implementation brainstorming agent + skill

[starlightretailceo]

Summary

• Agent (implementation-brainstormer.agent.md): Turns rough feature ideas, bug fixes, or product requests into multiple implementation options, scored tradeoffs, and a first testable slice.
• Skill (skills/implementation-brainstorming/SKILL.md): Reusable brainstorming framework with option-generation prompts, scoring rubric, risk prompts, recommendation template, and first-slice checklist.

Motivation

This replaces the closed format-migrator idea from #2072 with a more generally useful brainstorming implementation. Instead of duplicating platform migration behavior Copilot already handles, it helps users move from vague intent to practical, ranked implementation paths and a reviewable first PR-sized slice.

Test plan

• Ran npm run build to regenerate README indexes.
• Confirmed the new implementation-brainstorming skill validates in npm run skill:validate output.
• Use the agent on a real feature idea and verify it produces ranked options plus a first testable slice.

Note: full local npm run skill:validate currently reports an unrelated pre-existing aws-cloudwatch-investigation name issue on current main; the new skill itself validates successfully.

[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	[implementation-brainstorming] 📊 implementation-brainstorming: 845 BPE tokens [chars/4: 982] (detailed ✓), 9 sections, 1 code blocks
ℹ️	Found 1 agent(s)
ℹ️	Validated 1 agent(s)
ℹ️	✅ All checks passed (1 skill(s), 1 agent(s))

Full validator output

Found 1 skill(s)
[implementation-brainstorming] 📊 implementation-brainstorming: 845 BPE tokens [chars/4: 982] (detailed ✓), 9 sections, 1 code blocks
Found 1 agent(s)
Validated 1 agent(s)
✅ All checks passed (1 skill(s), 1 agent(s))

[github-actions]

🔒 PR Risk Scan Results

Scanned 4 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	1
ℹ️ Info	0

Severity	Rule	File	Line	Match
🟠	package-exec-command	docs/README.skills.md	31	| [acreadiness-assess](../skills/acreadiness-assess/SKILL.md)<br />`gh skills install github/awesome-copilot acreadiness-assess` | Run the AgentRC readiness assessment on the curre

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

[starlightretailceo]

Risk scan note: the package-exec-command soft-gate finding points at docs/README.skills.md line 31 for acreadiness-assess, which is unchanged from current main. This PR only adds the generated implementation-brainstorming row later in the skills index; all required checks are green.

[aaronpowell]

what do you find that this agent brings over using the built-in Plan agent with skills?