feat(run-workflow): add run-workflow and run-featured-workflow skills

[thagarwal-sjc]

Description

Ports the run-workflow and run-featured-workflow skills from the run-workflow MCP server repo into a new plugins/creative-cloud/run-workflow plugin, adapted to this repo's conventions:

• Frontmatter: replaced origin: internal with license: Apache-2.0 + metadata.version/visibility (required by the license-field CI check).
• Added .claude-plugin/plugin.json, .mcp.json (hosted endpoint https://run-workflow.adobe.io/mcp), and .tessl-plugin/plugin.json so the plugin is discoverable and eligible for Tessl evals.
• Added .github/CODEOWNERS entry for the new path.
• Removed two dead relative links in the source SKILL.md files that pointed at docs/skills not included in this port (docs/mcp-server/featured-workflows.md, firefly-api-specs).
• Added 3 eval scenarios (evals/<scenario>/{task.md,criteria.json}) covering the bare-ID inspect-only rule, list_actions-first discovery, and featured-workflow routing.

No existing plugin files were modified beyond the CODEOWNERS addition.

Related Issue

No existing GitHub issue for this — happy to open one first if that's required before merge.

Motivation and Context

Brings the run-workflow MCP skills (Adobe Firefly workflow discovery/compose/run/publish, plus predefined featured workflows) into the shared Adobe skills repo so other agents/users can install them the same way as the other creative-cloud skills.

How Has This Been Tested?

• npm run validate (skills-ref spec check) — both skills valid.
• Local replication of the license-field and codeowners-coverage CI jobs — both pass.
• tessl review run (quality/security review): run-workflow scored 89%, run-featured-workflow scored 99% (both well above the 50% CONTRIBUTING threshold).
• tessl eval run (real agent eval, baseline vs. with-skill): average score baseline 39% → with-skill 82%. Two scenarios (bare-ID inspect, discovery-before-answering) show baseline 0-20% vs. skill 100% — the skill fixes clear failure modes. The third scenario (featured-workflow-routing) shows the skill scoring lower than baseline (47% vs 97%) — investigated and this is a known eval-sandbox limitation (no live IMS credential available to authenticate against the real hosted MCP server, so the with-skill run correctly attempted real tool calls and hit 403s, while the unguided baseline "solved" it by writing a self-contained mock implementation instead of calling any real tool). Documented inline in evals/featured-workflow-routing/task.md under "Known limitation".

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)

Checklist:

• I have signed the Adobe Open Source CLA.
• My code follows the code style of this project.
• My change requires a change to the documentation.
• I have updated the documentation accordingly.
• I have read the CONTRIBUTING document.
• I have added tests to cover my changes.
• All new and existing tests passed.

[trieloff]

The skill.md seems long, this will likely get flagged by Tessl