Add evidence-gated Hermes agent architecture builder skill 🤖🤖🤖

[kotlyar]

Summary

Adds hermes-agent-builder-en, a guided discovery and architecture-design skill for deciding what belongs in deterministic workflows, tools, reusable skills, temporary subagents, persistent profiles, and orchestration.

Why this is useful

The skill addresses a recurring failure mode in agent-system design: turning job titles, platforms, or large prompts into separate agents before outcome ownership, persistent state, lifecycle, authority, and coordination needs are understood. It interviews users in plain language and records explicit evidence gates before producing an implementation-ready kit.

Included resources

• discovery interview and optional answer hints
• profile and orchestrator decision criteria
• control-interface and storage guidance
• free and open-source web-interface defaults
• implementation-kit templates and deterministic packager
• packaging tests for ready, draft, and secret-file cases

Validation

• npm run skill:validate
• npm run build
• npx --yes @microsoft/vally-cli lint skills/hermes-agent-builder-en --verbose
• python skills/hermes-agent-builder-en/scripts/test_package_delivery.py -v

All checks pass locally.

Upstream source

The maintained bilingual source is released under MIT at https://github.com/kotlyar/agent-architecture-builder/releases/tag/v1.0.1.

[github-actions]

🔒 PR Risk Scan Results

Scanned 13 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	0
ℹ️ Info	2

Severity	Rule	File	Line	Match
ℹ️	skill-script-touched	skills/hermes-agent-builder-en/scripts/package_delivery.py	1	skills/hermes-agent-builder-en/scripts/package_delivery.py
ℹ️	skill-script-touched	skills/hermes-agent-builder-en/scripts/test_package_delivery.py	1	skills/hermes-agent-builder-en/scripts/test_package_delivery.py

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

[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	✅ hermes-agent-builder-en (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/hermes-agent-builder-en
✅ hermes-agent-builder-en (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

[kotlyar]

The nested metadata.hermes value reported by the first lint run has been replaced with flat string metadata in commit 57b1903. The updated head now passes @microsoft/vally-cli spec compliance and valid-reference checks (2/2), and all current pull-request checks are green. The corrected upstream release is v1.0.1.