The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell scripts to initialize and maintain a local state file located at ~/.config/senpi/state.json. It utilizes node -p to parse and extract values from this JSON file. This behavior is found in SKILL.md and references/next-steps.md.
[EXTERNAL_DOWNLOADS]: The documentation in SKILL.md provides installation instructions that fetch the skill's source files directly from the author's official GitHub repository at Senpi-ai/senpi-skills.
[PROMPT_INJECTION]: The skill processes data fetched from external MCP tools and interpolates this into user-facing templates, creating a surface for indirect prompt injection.
Ingestion points: Data enters the system via MCP tool outputs (e.g., discovery_get_top_traders) as described in references/discovery-guide.md and the local state.json file in SKILL.md.
Boundary markers: No explicit delimiters or "ignore instructions" warnings are used to separate external data from the agent's core instructions when displaying content to the user.
Capability inventory: The skill has the capability to execute financial trades (creating and closing mirror strategies) via the Senpi MCP tools documented in references/strategy-management.md and can perform file-write operations to the local file system.
Sanitization: The skill does not describe specific sanitization, escaping, or validation routines for data received from the MCP server before it is processed and presented.

senpi-getting-started-guide