The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown documentation and natural language instructions related to improving the flow and argumentative structure of scientific papers.
[NO_CODE]: There are no scripts, binaries, or command-line instructions provided within the skill. The logic is entirely instructional for the AI agent.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (user-provided manuscript drafts). However, there is no security risk as the skill does not utilize any tools or capabilities that involve the file system, network, or system shell. It purely provides stylistic and structural guidance.
[EXTERNAL_DOWNLOADS]: No external URLs or remote resources are referenced for download or execution. The reference to references/section-contracts.md appears to be a pointer to a local file within the user's workspace.

results-section-revision