The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute bundled Python scripts for document management and cleanup tasks.\n
Evidence: SKILL.md contains logic to execute python {SKILL_DIR}/scripts/split_md.py for file segmenting and python {SKILL_DIR}/scripts/merge_md.py for reassembling translated parts.\n
Evidence: The skill performs maintenance by using rm to delete temporary files like _glossary.md and the _parts/ directory after processing.\n- [PROMPT_INJECTION]: The skill processes arbitrary user-provided Markdown and text files, creating a surface for indirect prompt injection attacks.\n
Ingestion points: The primary agent reads the full content of source files into its context during the Phase 1 read-through specified in SKILL.md.\n
Boundary markers: The skill employs a dedicated sub-agent prompt template in references/subagent-prompt.md which establishes a professional writer persona and provides strict translation-focused constraints to minimize the impact of embedded instructions.\n
Capability inventory: The skill has access to file system read/write tools, shell command execution via Bash, and the ability to delegate tasks to sub-agents.\n
Sanitization: No explicit content sanitization or instruction-filtering is applied to the input text before it is passed to the translation engine, as the intended functionality requires full document processing.

translate