The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized command execution were detected within the skill file.
[NO_CODE]: The skill consists purely of natural language instructions (markdown) designed to guide the AI agent's behavior during interactive sessions. It does not include any scripts, binaries, or automated shell commands.
[EXTERNAL_DOWNLOADS]: The skill references a public GitHub repository (addyosmani/agent-skills) for its source documentation and MIT license. These references are documented neutrally and originate from a well-known community source.
[INDIRECT_PROMPT_INJECTION]: The skill involves a workflow that ingests user input through an interview process and allows for that input to be persisted to the local file system.
Ingestion points: User responses during the interactive interview are captured and restated by the agent in the SKILL.md (Step 4).
Boundary markers: The skill does not explicitly define markers or delimiters to isolate user-provided data from the rest of the agent's instructions.
Capability inventory: The skill instructs the agent to offer to save the final confirmed intent to a local file path (docs/intent/[topic].md).
Sanitization: No explicit sanitization or escaping of user input is specified before the content is written to a file or re-processed by the agent.

interview-me