The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill utilizes npx to download and run the markdownlint-cli2 package from the NPM registry, allowing for automated style and formatting checks on articles at runtime.
[COMMAND_EXECUTION]: The agent is instructed to execute shell commands for linting and fixing markdown files as part of the six-step review process defined in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface when handling user articles for brainstorming and review.
Ingestion points: User-provided text and articles are ingested in SKILL.md for processing in both 'Brainstorming' and 'Review' modes.
Boundary markers: Absent; the instructions do not include specific delimiters or warnings to the model to ignore instructions that may be embedded within the user's article text.
Capability inventory: The skill is capable of executing shell commands through npx and writing to the local file system, specifically creating material.md files as part of the structural diagnosis step.
Sanitization: Absent; no validation or sanitization is performed on the user's article content before it is incorporated into the agent's reasoning process.

writing-assistant