Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to write, publish, republish, or optimize posts on Medium.com (canonical tags, distribution, Medium SEO). Also use when the user mentions "Medium," "Medium article," "Medium story," "Medium publishing," "canonical Medium," or "publish on Medium." Not for general parasite SEO when Medium is not the target platform—use parasite-seo. For AI search visibility strategy, use generative-engine-optimization.
.claude/skills/kostja94-medium-posts/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 6% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -21% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -31% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 16% | 0% |
Guides Medium publishing for parasite SEO and content distribution. Medium's domain authority helps content rank faster than on new sites; articles can reach page 1 within days. Use this skill when planning Medium content or republishing from your site.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read Sections 6 (Keywords), 11 (Content Strategy).
Identify:
| Benefit | Detail | |---------|--------| | Fast rankings | Page 1 within days vs months on own domain | | Authority | Leverages Medium's domain authority | | AI-friendly | Frequently cited in AI search results | | Backlinks | Traffic-generating articles attract links |
When republishing: Set canonical to your original URL in Medium settings. Prevents duplicate content penalties; signals original source.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 10,498 | 8,936 | -15% | 1 | 1 | 0% | 1,913 | 2,037 | +6% | 0 | 0 | — |
case-02 | pass→pass | 17,293 | 9,596 | -45% | 1 | 1 | 0% | 2,835 | 2,231 | -21% | 0 | 0 | — |
case-03 | pass→pass | 16,273 | 8,645 | -47% | 1 | 1 | 0% | 2,687 | 1,855 | -31% | 0 | 0 | — |
case-04 | pass→pass | 12,427 | 11,675 | -6% | 1 | 1 | 0% | 2,082 | 2,408 | +16% | 0 | 0 | — |
case-05 | pass→pass | 14,093 | 13,090 | -7% | 1 | 1 | 0% | 2,306 | 2,484 | +8% | 0 | 0 | — |
case-06 | fail→pass | 4,510 | 3,522 | -22% | 1 | 1 | 0% | 851 | 1,098 | +29% | 0 | 0 | — |
case-07 | pass→pass | 14,217 | 11,150 | -22% | 1 | 1 | 0% | 2,487 | 2,479 | -0% | 0 | 0 | — |
case-08 | pass→pass | 13,982 | 12,556 | -10% | 1 | 1 | 0% | 2,329 | 2,576 | +11% | 0 | 0 | — |
case-09 | pass→pass | 11,661 | 8,261 | -29% | 1 | 1 | 0% | 2,024 | 1,762 | -13% | 0 | 0 | — |
case-10 | pass→pass | 11,059 | 10,115 | -9% | 1 | 1 | 0% | 2,121 | 2,262 | +7% | 0 | 0 | — |
case-11 | pass→pass | 13,472 | 11,578 | -14% | 1 | 1 | 0% | 2,203 | 2,376 | +8% | 0 | 0 | — |
case-12 | fail→fail | 11,202 | 8,559 | -24% | 1 | 1 | 0% | 1,802 | 1,796 | -0% | 0 | 0 | — |
case-13 | pass→pass | 8,756 | 4,661 | -47% | 1 | 1 | 0% | 1,455 | 1,305 | -10% | 0 | 0 | — |
case-14 | pass→pass | 8,874 | 2,933 | -67% | 1 | 1 | 0% | 1,465 | 983 | -33% | 0 | 0 | — |
case-15 | pass→pass | 4,381 | 5,544 | +27% | 1 | 1 | 0% | 828 | 1,431 | +73% | 0 | 0 | — |
case-16 | pass→pass | 17,121 | 9,929 | -42% | 1 | 1 | 0% | 2,923 | 2,140 | -27% | 0 | 0 | — |
case-17 | pass→pass | 9,151 | 3,057 | -67% | 1 | 1 | 0% | 1,568 | 1,014 | -35% | 0 | 0 | — |
case-18 | pass→pass | 11,383 | 11,216 | -1% | 1 | 1 | 0% | 2,033 | 2,283 | +12% | 0 | 0 | — |
case-19 | pass→pass | 10,666 | 9,621 | -10% | 1 | 1 | 0% | 1,813 | 2,022 | +12% | 0 | 0 | — |
case-20 | pass→pass | 7,314 | 6,588 | -10% | 1 | 1 | 0% | 1,376 | 1,758 | +28% | 0 | 0 | — |
case-21 | pass→pass | 15,786 | 12,652 | -20% | 1 | 1 | 0% | 2,668 | 2,412 | -10% | 0 | 0 | — |
case-22 | pass→pass | 9,382 | 9,071 | -3% | 1 | 1 | 0% | 1,839 | 2,196 | +19% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.