sergebulaev/x-skills / .codex-marketplace/x-skills/skills/x-post-writer
x-post-writer
VerifiedDraft a single tweet or short auto-thread for X (Twitter) using a 2026 X hook formula (one-liner contrarian, data-point, build-in-public, mini-list, relatable cold-open), picked by goal (replies, reposts, likes, bookmarks). Respects the 280-char limit (25,000 on Premium), runs the humanizer pass, and publishes via Publora on approval. Use to write a tweet from notes. Not for long threads (use x-thread-builder) or auditing a draft (use x-humanizer --mode audit).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.1 KB |
| references/single-tweet-checklist.md | markdown | 2.5 KB |
references/single-tweet-checklist.md
View on GitHub# Single-Tweet Checklist
Run every single-tweet draft through this before showing the approval card.
## Fit
- [ ] Under 280 chars on a standard account. Count emoji as 2 chars each.
- [ ] If over 280 and the user is not on X Premium: tighten, or escalate to a
thread. Never ship a truncated thought.
- [ ] First line stops the scroll on its own (no reliance on a second line).
## Voice scrub
- [ ] At most one em dash (`—`) in the tweet, and none if it reads fine
without it. Replace the excess with a comma, colon or `..`, never a
period. No en dashes (`–`) between clauses, no double dashes (`--`).
- [ ] No cluster of 2026 AI vocab (3+ markers in one tweet = rewrite the
tweet; one is fine): significant, crucial, notably, comprehensive,
insights, robust, leverage, foster, landscape, nuanced, streamline,
elevate, empower, fundamentally, essentially, ultimately; plus "-ing"
clause openers and "the X-tion of" nominalisations.
- [ ] No reveal bridge ("The result?", "Here's what", "Stop X, start Y") and
no "It's not X, it's Y".
- [ ] No sincerity announcement ("let me be honest", "not gonna lie",
"unpopular opinion:" on a popular take) and no hedge the author did not
write.
- [ ] No staccato stack ("Short. Punchy. Done.", "No X. No Y. Just Z.") and
no one-word line for drama. Do not chop a sentence to add punch; uniform
rhythm is fine in a single tweet.
- [ ] At most one rule-of-three triplet, with concrete items.
- [ ] Names capitalized (Stripe, Claude, Vercel). Lowercase sentence starts are
fine if the voice calls for it.
## Substance
- [ ] One idea only. Two ideas means two tweets.
- [ ] At least one odd-precision number with a named referent, or a named
entity, where the claim allows it. A bare number does not count.
- [ ] A clear primary goal: replies, reposts, likes, or bookmarks. Not all four.
## Format
- [ ] 0 or 1 hashtag, at the end.
- [ ] 0 or 1 emoji, and only if it earns its place. None on a serious/contrarian take.
- [ ] No external link in the tweet body (offer to drop it in a reply).
- [ ] Line breaks used as beats, not decoration.
## Close
- [ ] Ends on a landing or a specific question, never "what do you think?".
## Char-count quick reference
| Account | Per-tweet limit | Emoji cost |
|---|---|---|
| Standard | 280 | 2 chars each |
| X Premium | 25,000 | 2 chars each |
Publora reserves ~8 chars per tweet for the `(X/N)` marker when it auto-splits a
long draft into a thread.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |