The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to perform repository analysis and automate release workflows.
Executes git commands to retrieve commit history, tags, diffs, and contributor information.
Utilizes package manager commands such as npm version, npm publish, and cargo publish to manage software versions and distribution.
Invokes platform-specific tools like the GitHub CLI (gh) and GitLab CLI (glab) to fetch pull/merge request metadata and create remote releases.
[PROMPT_INJECTION]: The skill's core functionality involves processing untrusted external data, creating an attack surface for indirect prompt injection.
Ingestion points: The agent reads and analyzes commit messages, pull request titles, and descriptions from the repository environment.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potentially malicious commands embedded within the commit history or PR bodies.
Capability inventory: The skill possesses broad execution capabilities, including shell access, file modification (CHANGELOG.md), and the ability to trigger remote release actions.
Sanitization: The skill does not implement sanitization or validation of the ingested text before incorporating it into the agent's context for summarization and categorization.
[EXTERNAL_DOWNLOADS]: The skill interacts with well-known developer platforms to retrieve necessary metadata.
Fetches pull request and release information from GitHub using the official gh CLI.
Retrieves merge request data from GitLab using the official glab CLI.

changelog