The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like mkdir -p and mv to create archive directories and move project folders. It also relies extensively on the openspec CLI tool to perform status checks, list changes, and execute the archiving logic.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data retrieved from the project environment via openspec instructions archive and openspec instructions specs. This data includes context, operationGuidance, and rules that the agent is instructed to "read and consider" or "apply relevant project facts, conventions, and constraints."
Ingestion points: The output of openspec instructions archive and openspec instructions specs (Steps 1 and 4 in SKILL.md).
Boundary markers: The skill provides explicit instructions to the agent to keep this external data separate from built-in steps, report conflicts between guidance and controlling inputs, and avoid copying the guidance text verbatim into specs or summaries.
Capability inventory: The agent has the ability to write to the file system (mkdir, mv) and execute various openspec CLI subcommands via Bash.
Sanitization: No programmatic sanitization is performed on the semantic content of the instructions; the skill relies on the agent's adherence to the provided guardrails to prevent malicious override of behavior.

openspec-archive-change