The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the lean and lake command-line interfaces to check mathematical proofs and manage project builds. These operations are limited to the skill's mathematical reasoning functions.\n- [COMMAND_EXECUTION]: Executes a local environment check script, scripts/check_lean.sh, which verifies the installation of required Lean tools. This script is a local vendor resource.\n- [EXTERNAL_DOWNLOADS]: Uses the Lake build tool which may download the standard mathlib library from its official repository when project initialization requires advanced mathematical lemmas.\n- [PROMPT_INJECTION]: Contains an attack surface for indirect prompt injection through the parsing of user-provided mathematical claims.\n
Ingestion points: Mathematical claims, lemmas, and proofs provided by the user in SKILL.md.\n
Boundary markers: Absent; the skill does not explicitly use delimiters to isolate user-provided math from the agent's internal logic.\n
Capability inventory: Ability to execute shell commands via lean and lake binaries.\n
Sanitization: None; input is parsed directly into the mathematical analysis workflow.

mathematician