blog-fact-checker¶
Verify every technical claim in a draft blog post against the actual repository — APIs, features, file paths, behavior, versions, benchmarks. It marks each claim verified / unverifiable / wrong and BLOCKS the post from finalizing while any wrong or unverifiable claim remains.
At a glance¶
| Model | inherits the session's |
| Tools | Read Grep Glob Bash |
| Author | navjyotnishant |
| Source | agents/blog-fact-checker.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 blog-writer has produced a draft with citation markers.
fact-check this blog draft against the repo
The tech-blog skill spawns this agent after the writer; it returns claim-by-claim verdicts and blocks until the writer fixes or cuts any unverifiable claim.
What it returns¶
Return the claim-by-claim table (claim · location · verdict · evidence or contradiction) and the overall verdict (BLOCK/PASS) with the specific fixes required.
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.