Add multi-source research skill

[denial123789]

Summary

Adds a runtime-neutral multi-source-search Agent Skill for GitHub Copilot that:

• bounds search and page-reading loops
• distinguishes provider diversity from repeated queries
• canonicalizes URL identity before counting independent sources
• keeps supporting and contradicting evidence in disjoint sets
• caps confidence by independent-source count
• treats retrieved pages as untrusted input and keeps research read-only
• declares its host requirements through the standard compatibility field

This addresses a specialized research gap rather than duplicating general model behavior: the output is an auditable claim/source ledger with explicit contradiction and stopping rules.

I am affiliated with SandBase. The contribution is a runtime-neutral adaptation of the Apache-2.0 source linked in the Skill; it does not require a SandBase account, external CLI, or paid service.

Validation

• npm run skill:validate ✅ (all 411 skills valid)
• npm run build ✅
• bash eng/fix-line-endings.sh ✅
• git diff --check ✅
• generated install entry verified in docs/README.skills.md
• upstream PR checks: build, Vally spec compliance, valid references, spelling, line endings, README validation, and risk scan all pass

Install after merge:

gh skills install github/awesome-copilot multi-source-search

[github-actions]

🔒 PR Risk Scan Results

Scanned 1 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	0
ℹ️ Info	0

✅ No matching risk patterns were detected in changed files.

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

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

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

[github-actions]

🔍 Vally Lint Results

✅ All checks passed

Scope	Checked
Skills	1
Agents	0
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	✅ multi-source-search (2/2 checks passed)
ℹ️	✓ [spec-compliance] All 1 skill(s) are spec-compliant.
ℹ️	✓ spec-compliance: All spec checks passed.
ℹ️	✓ [valid-refs] All file references across 1 skill(s) are valid.
ℹ️	✓ valid-refs: All file references resolve to existing files within the skill directory.
ℹ️	1 skill(s) linted, 1 passed

Full linter output

### Linting skills/multi-source-search
✅ multi-source-search (2/2 checks passed)
    ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
        ✓ spec-compliance: All spec checks passed.
    ✓ [valid-refs] All file references across 1 skill(s) are valid.
        ✓ valid-refs: All file references resolve to existing files within the skill directory.

1 skill(s) linted, 1 passed