The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from pull request titles, bodies, linked issues, and review threads to establish intent and decide on a disposition. This content could contain malicious instructions designed to influence the agent's behavior during the modernization process.\n
Ingestion points: Processes PR title, body, linked issues, and review threads as described in the 'Establish the PR's intent' section of SKILL.md.\n
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat this external content as untrusted or to ignore any embedded instructions.\n
Capability inventory: The agent has the ability to perform git operations (fetch, rebase, push) and execute repository checks as outlined in the 'Rebase without losing intent' section of SKILL.md.\n
Sanitization: No sanitization or validation of the PR-sourced text is performed before it is used for decision-making.\n- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to manage branches and verify code changes.\n
Evidence: Instructions include using git fetch, git rebase, git range-diff, and git push --force-with-lease.\n
Evidence: The skill directs the agent to run 'focused checks' on the touched code, which involves executing the repository's local test scripts or build tools.

modernize