The Agent Skills Directory

[SAFE]: The skill is primarily focused on content generation and documentation. It uses standard file operations (Read, Write, Edit) to manage blog drafts and resources within the local environment. All file paths and tool usage are consistent with the stated purpose of writing and editing blog posts.\n- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves researching topics via an external web-search agent, which introduces a potential surface where untrusted data from the internet could influence the generated content.\n
Ingestion points: Research data retrieved by the web-search-researcher agent as described in step 3 of the workflow in SKILL.md.\n
Boundary markers: The skill uses strict formatting requirements in resources/templates.md and a detailed validation checklist in resources/checklist.md to maintain content structure.\n
Capability inventory: The skill is permitted to use Write and Edit tools (defined in SKILL.md) to save content to the thoughts/blog/ directory.\n
Sanitization: The agent is explicitly instructed in SKILL.md to verify every claim and cite sources, though no automated sanitization of the research data is present.

blog-writer