The Agent Skills Directory

[SAFE]: The skill consists of a markdown file containing instructional prompts and educational documentation. No executable code (Python, JavaScript, or Shell scripts) is present within the skill.
[SAFE]: No external dependencies or remote script downloads (e.g., via curl or wget) were identified. All references in the skill are to academic literature in the form of text.
[SAFE]: The skill does not perform any network operations or data exfiltration. It has no mechanism to send information to external servers.
[SAFE]: No access to sensitive system files, environment variables, or hardcoded credentials was found. The skill operates purely within the text-based context of an LLM prompt.
[SAFE]: The prompt instructions are pedagogically sound and focus on designing learning materials. They do not contain any patterns associated with prompt injection, safety filter bypasses, or malicious behavior overrides.
[SAFE]: Although the skill defines input fields for student profiles and common errors which represent an ingestion surface for potentially untrusted data, the lack of dangerous capabilities (no file writing, no shell access, no network operations) ensures that any potential indirect prompt injection would have no practical security impact. Ingestion points: student_profiles and common_errors in SKILL.md; Boundary markers: Absent; Capability inventory: None; Sanitization: Absent.

worked-example-fading-designer