Prevent invalid blog-writer script execution and add safe fallback behavior /python/agents/agents-skills-tutorial

[yashshri1313]

Fixed a reliability issue in the agent-skills-tutorial flow where the agent could attempt run_skill_script for the blog-writer skill even though that skill has no scripts/ directory (for example, attempts like create_introduction.py).

Changes made

1. app/skills/blog-writer/SKILL.md
   • Added an Important Constraint section:
   • no scripts/ directory exists for this skill
   • do not call run_skill_script
   • use load_skill_resource (references/style-guide.md) and write content directly
2. app/agent.py
   • Updated the root instruction for write/research/optimize flow:
   • only use run_skill_script when the skill explicitly contains script resources
   • if SCRIPT_NOT_FOUND is returned, do not retry script execution; continue with skill instructions/resources

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.