The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python utility script to calculate precise character counts for generated text.
Evidence: python3 skills/shared/scripts/wordcount.py count and ../../shared/scripts/wordcount.py count are referenced in SKILL.md to validate the social_count of generated hooks.
[DYNAMIC_EXECUTION]: The skill uses runtime script execution to perform deterministic validation of its own output, which is a common pattern for enforcing formatting constraints.
Evidence: The agent is instructed to pass generated lines to the wordcount script and re-generate or compress lines if they exceed a specific threshold (40 characters).
[INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary user-provided themes which are subsequently passed to a script for length validation. This represents a vulnerability surface where untrusted data interacts with shell commands.
Ingestion points: User prompt (theme text) extracted in SKILL.md (Step 1).
Boundary markers: None. The instructions do not specify using delimiters or sanitization when passing the user-derived text to the wordcount script.
Capability inventory: The skill possesses the capability to execute shell commands via python3 to run a local script.
Sanitization: No explicit sanitization of user-provided content is defined before the content is piped into the script via stdin.

skill-hook-generator