Draft a blog post or social post from an interview transcript using only the author's own words, where every body sentence is quoted, shaped, or a bare connective, with hooks and closings mined from the transcript first. Use after an interview, or when the author hands over a transcript, voice memo, or notes and asks for a draft in their voice.
97%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
The input is a transcript of the author's own words. The output is a draft ready for review. The interview collected the material. This skill shapes it and never adds to it.
Every sentence in the draft body traces to the transcript. A body sentence can be one of exactly three kinds:
Nothing else. No invented anecdotes, no composite examples, no filling a gap
with plausible material. A gap in the transcript is a question for the
author. Ask it, add the answer to the transcript, then use it. Or draft
around the gap and mark it [GAP: …].
Hooks and closings are the only place new prose is allowed, and only as clearly labeled supplements.
Load the voice skill and read, on every draft and every revision:
If the transcript links a research brief, read it for context. Brief prose never enters the body.
allergist, then taste-lens, then
guardrails-lens.Draft for <channel>: <word count> words, from your transcript.
<draft body>
Hooks (pick one, or say none of these):
1. "<verbatim phrase>": your words (<question ref>)
2. "<verbatim phrase>": your words (closing playback; you liked this one)
3. "<candidate>": machine-written supplement
Closings:
1. "<phrase>": your words (<ref>)
2. "<candidate>": machine-written supplementRevisions follow the same rule. Fix a problem by going back to the transcript for better material, by reshaping, or by cutting. If the transcript can't fix it, ask the author and add their answer to the transcript first.
shortrib-labs/content-loop
1e17068
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.