The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests instructions from external Meticulous review comments and automated fix prompts, which introduces a surface where external content could influence the agent's actions during code modification.
Ingestion points: External instructions and metadata are retrieved via the meticulous CLI and MCP tools, specifically through commands such as get_test_run_diffs, get_diff_comments, and get_agent_swarm_run_case in SKILL.md.
Boundary markers: The skill does not implement explicit delimiters or specific instructions to isolate external data from the agent's core operational logic.
Capability inventory: The agent is granted capabilities to modify source code, perform git operations (commit, push), and interact with pull request management tools (gh, glab).
Sanitization: The skill instructions do not specify a process for validating or sanitizing the content retrieved from the external Meticulous platform before it is used to drive code changes.
[COMMAND_EXECUTION]: The skill employs various command-line interfaces to perform its defined tasks.
It uses git for version control operations, including committing changes with specific trailers and pushing to remote branches.
It interacts with GitHub (gh), GitLab (glab), and Bitbucket for pull request communication.
It utilizes the meticulous CLI for interacting with the Meticulous testing service.
[EXTERNAL_DOWNLOADS]: The skill fetches data and configuration from external sources during its workflow.
It retrieves test run diffs, check reports, and image assets from the meticulous.ai and app.meticulous.ai domains.
It references the meticulous-cli-update skill for maintaining its tooling.

meticulous-fix