The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various shell commands including git fetch, git rev-parse, grep, and git grep. These commands are used to interact with the local documentation repository and a user-specified Dify codebase to verify terminology consistency and resolve commit references.
[DYNAMIC_EXECUTION]: The skill invokes project-specific Python scripts, specifically tools/translate/check-glossary-keys.py and tools/translate/derive-termbase.py. These scripts are used to validate glossary keys against the codebase and regenerate termbases after approved edits.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from documentation files and external codebase files, creating a potential surface for indirect prompt injection.
Ingestion points: The skill reads content from markdown files (.md, .mdx), glossary.md, and internationalization JSON files in the Dify repository.
Boundary markers: Not explicitly defined; the skill parses and extracts bolded terms and headings for comparison.
Capability inventory: The skill has the ability to execute shell commands (grep, git), run local Python scripts, and perform file writes to glossary.md upon user approval.
Sanitization: No explicit sanitization or validation of the content extracted from the files is performed before it is used in search queries or displayed in reports.

dify-docs-terminology-check