The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches TLA+ model checking tools (tlaplus/tlaplus) and Java (temurin-25) from well-known public repositories using the mise tool. These downloads are pinned to specific versions, and the TLA+ binary is verified against a SHA-256 checksum for integrity.
[EXTERNAL_DOWNLOADS]: Installs the Node.js packages pele@1.8.0 and @resvg/resvg-js@2.6.2 from the official NPM registry to handle chart rendering tasks.
[COMMAND_EXECUTION]: Executes shell commands including npm, java, and mise to manage the lifecycle of dependencies and perform the model checking process.
[DYNAMIC_EXECUTION]: Utilizes dynamic imports to load and execute JavaScript modules at runtime, including user-defined mapping files and the installed rendering library.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of TLA+ specifications and Mermaid diagrams. This input is used to scaffold and influence the logic of mapping files that are subsequently executed as JavaScript code.
Ingestion points: User-provided .tla (TLA+ specification) and .mmd (Mermaid chart) files processed by scripts/statechart.mjs and related scripts.
Boundary markers: No specific boundary markers or instruction-ignoring warnings are implemented for the data ingested from these files.
Capability inventory: The skill's scripts have the ability to spawn subprocesses (executing java, npm, mise), write files to the local file system, and perform network operations for software installation.
Sanitization: While the skill generates mapping file templates based on the model's structure, it does not sanitize or validate the logic within these files before they are imported and executed.

statechart