The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts including funder_fit_scorer.py, proposal_structure_validator.py, and budget_realism_checker.py. These scripts are part of the skill package and perform analytical tasks on JSON data provided by the user. They use standard Python libraries and do not exhibit any dangerous behaviors such as network communication, shell spawning, or unauthorized file access.
[PROMPT_INJECTION]: The instructions are tailored to grant writing workflows and do not contain any patterns intended to bypass AI safety guardrails, override system instructions, or extract system prompts.
[EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or reference remote scripts. All logic is contained within the provided Python scripts and markdown references.
[DATA_EXFILTRATION]: There are no indicators of data exfiltration. The skill processes grant proposal data locally and outputs results to the agent's context or local files as requested by the user.

grants