blog-reviewer¶
Critique a fact-checked technical blog draft for structure, clarity, technical depth, narrative flow, and audience fit — returning actionable editorial notes (not a rewrite).
At a glance¶
| Model | inherits the session's |
| Tools | Read Grep Glob |
| Author | navjyotnishant |
| Source | agents/blog-reviewer.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 draft has passed fact-checking and needs an editorial critique before final editing.
review this blog draft
The tech-blog skill spawns this agent after the fact-checker; its notes feed the editor.
What it returns¶
Return a prioritized punch-list: each note = location + issue + concrete suggestion. Separate must-fix (hurts comprehension/credibility) from nice-to-have (polish). Don't rewrite the prose; point the editor at what to change and why.
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.