The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local repository scripts and system commands to facilitate the release process.
Executes node scripts/release-packages.mjs for listing and validating packages.
Executes pnpm install to update the project lockfile.
Executes git commands for branching, committing, and merging code.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted or third-party data that could influence the agent's behavior during critical release steps.
Ingestion points: Reads content from apps/cli/RELEASING.md, CHANGELOG.md, and issue descriptions from a Linear integration.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within these data sources.
Capability inventory: The agent has the ability to execute local scripts, perform git operations, and trigger GitHub Action workflows (including live releases).
Sanitization: No sanitization or validation logic is specified for the text ingested from changelogs or external issue trackers.

release