The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions require the agent to execute a bundled validation script, scripts/check_clean_srt.py, using the local Python interpreter to verify the integrity and formatting of the processed subtitles.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data in the form of SRT subtitle files.
Ingestion points: The agent reads user-provided .srt files as specified in SKILL.md and agents/openai.yaml.
Boundary markers: The skill produces structured SRT output. The instructions contain strict negative constraints (e.g., "do not rewrite", "do not summarize") that limit the agent's susceptibility to instructions embedded within the subtitle text.
Capability inventory: The skill possesses the capability to read local files and execute the bundled Python script scripts/check_clean_srt.py.
Sanitization: The provided validation script (scripts/check_clean_srt.py) automatically checks the output for timing drifts, length violations, and residue of filler words, serving as a sanitization layer for the final output.

subtitle-refine