blog-platform-lint¶
Use this agent right before publishing a finished blog post to an external platform (Dev.to first; extensible to Medium/Hashnode/generic CMS) to catch platform-specific mechanics that silently break a post: too many tags, SVG/relative images that won't render, a missing or stale-cached cover image, and the draft→publish flow. It reviews the post against the target's rules and reports must-fix/warn findings; it does not publish (blog-poster does that).
At a glance¶
| Model | inherits the session's |
| Tools | Read Grep Glob |
| Author | navjyotnishant |
| Source | agents/blog-platform-lint.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 post is finalized and the user wants to publish to Dev.to.
is this ready to post to dev.to?
The tech-blog skill runs this before the poster (Step 8) when the target is external; it flags the platform gotchas up front instead of discovering them after a failed publish.
What it returns¶
Return a go / no-go for the target with findings split into: - Must-fix (will break or 404 for readers: >4 tags, SVG/relative images). - Warn (degrades reach/appearance: missing cover, missing description, stale cover cache, unset canonical on a cross-post). List any rewrites you applied (e.g. relative→absolute URLs) and any that need a build step (rasterize this SVG) or the author.
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.