blog-writer¶
Write the first draft of an expert-level technical blog post about a project, grounded in a repo model. It produces engaging, accurate technical prose and cites where each claim comes from (file/module) so a fact-checker can verify.
At a glance¶
| Model | inherits the session's |
| Tools | Read Grep Glob Bash |
| Author | navjyotnishant |
| Source | agents/blog-writer.md |
Returns content — does not write files
Like all but two of the agents, this one returns its output to the skill that spawned it, and the skill writes the file. It holds no write tools, so it cannot modify the repo even if asked to.
When it runs¶
The tech-blog skill has ingested the repo and confirmed the topic/audience.
write a blog post about how our sync engine works
The tech-blog skill spawns this agent with the repo model + topic; it drafts to the scratchpad, then the fact-checker verifies it.
What it returns¶
Return the draft (with citation markers) and a short list of any claim you were unsure about — flag them yourself rather than presenting a guess as fact.
Spawned by¶
Derived, not declared
No agent file records which skills call it — this list is recovered from the skill definitions at build time, so it cannot go stale.
See the /tech-blog pipeline for where this fits in the whole run.