Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brianrwagner/tweet-draft-reviewer
Review tweet drafts in Claude Code against 8 voice rules. Scores 1-10, breaks down every rule, and rewrites anything that scores below 7.
Passed 16 of 21 test cases with the skill, and 3 of 21 without it.
and 19 more in the full report
16 fixed2 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
Check this draft for me: 'We replaced Jira with Linear across 4 teams. Sprint planning dropped from 2 hours down to 15 minutes.'
| Checked | Without skill | With skill |
|---|---|---|
| Marks Rule 5 (Corey Test) as passing for providing named tools and concrete numerical metrics. | Missed | Passed |
The instructions your model reads when the skill loads.
Paste a tweet draft and get a score out of 10, a rule-by-rule breakdown, and a rewrite if the score is below 7. Takes 30 seconds. Saves you from posting something that sounds like a chatbot wrote it.
Built on 8 voice rules distilled from real content analysis — what separates high-engagement tweets from the ones that get skimmed.
Single draft:
Review this tweet draft: [paste tweet here]
Batch scan:
Review all tweet drafts in my content/tweet-drafts/ folder.
When this skill is invoked, follow these phases exactly.
Determine input mode:
Mode A — Direct paste: User provided draft text inline. Proceed to PHASE 2 with that text.
Mode B — Folder scan: User asked to review drafts folder. Run:
VAULT="${VAULT_PATH:-$(pwd)}"
find "$VAULT/content/tweet-drafts" -name "*.md" 2>/dev/null | while read f; do
if ! grep -q 'reviewed: true' "$f" 2>/dev/null; then
test cases passed, vs 3 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.