The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local bash setup script (setup-architect.sh) provided by the vendor (tikalk) to initialize the architectural planning environment. This script is used to group ADRs and generate the execution graph.
[DATA_EXFILTRATION]: The skill performs extensive read and write operations on the local filesystem, targeting directories such as .adlc/ and docs/adlc/. These operations are limited to the project workspace and do not attempt to access sensitive system files (e.g., SSH keys or cloud credentials).
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from Architecture Decision Records and user-supplied strings via $ARGUMENTS to generate content.
Ingestion points: ADR files in {REPO_ROOT}/.adlc/drafts/adr/ and the $ARGUMENTS input block in SKILL.md.
Boundary markers: The process uses a Directed Acyclic Graph (DAG) orchestration and specific markdown templates for each view to structure the output.
Capability inventory: The agent has capabilities to read/write files and execute shell scripts within the project root.
Sanitization: The skill enforces a mandatory Functional View checkpoint and a 10-point final verification checklist to ensure output consistency and safety before completion.

architect-implement