The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous examples of shell commands that execute local Python scripts from a specific backend directory.
Evidence in SKILL.md: python3 scripts/backend/intel.py list, python3 scripts/backend/intel.py --dry-run pipeline open CASE-0001 seeds.txt.
[DYNAMIC_EXECUTION]: The instructions include a command that executes Python code directly from a shell string using the -c flag to inspect local module metadata.
Evidence in SKILL.md: python3 -c "import sys; sys.path.insert(0,'scripts/backend'); import intel; print(len(intel.DISPATCH))".
[DATA_EXFILTRATION]: The skill describes functionality for sending data to external platforms such as ANY.RUN and MISP, which involves transmitting local indicators or files.
Evidence in SKILL.md: References to anyrun --submit, misp push/publish, and engage-harvest.
[EXTERNAL_DOWNLOADS]: The skill lists various third-party dependencies and tools required for specific features like graph generation and reporting, which requires user installation from external sources.
Evidence in SKILL.md: Mentions of claude-agent-sdk, matplotlib, graphviz, pandoc, xelatex, and mmdc.

dym-cti-expert-cli-dispatcher