Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fetch Twitter/X post content by URL using jina.ai API to bypass JavaScript restrictions. Use when Claude needs to retrieve tweet content including author, timestamp, post text, images, and thread replies. Supports individual posts or batch fetching from x.com or twitter.com URLs.
.claude/skills/nicepkg-twitter-reader/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 303% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -59% | 0% |
Fetch Twitter/X post content without needing JavaScript or authentication.
You need a Jina API key to use this skill:
bashexport JINA_API_KEY="your_api_key_here"
For a single tweet, use curl directly:
bashcurl "https://r.jina.ai/https://x.com/USER/status/TWEET_ID" \ -H "Authorization: Bearer ${JINA_API_KEY}"
For multiple tweets, use the bundled script:
bashscripts/fetch_tweets.sh url1 url2 url3
Python script for fetching individual tweets.
bashpython scripts/fetch_tweet.py https://x.com/user/status/123 output.md
Bash script for batch fetching multiple tweets.
bashscripts/fetch_tweets.sh \ "https://x.com/user/status/123" \ "https://x.com/user/status/456"
https://x.com/USER/status/IDhttps://twitter.com/USER/status/IDhttps://x.com/... (redirects work automatically)JINA_API_KEY: Required. Your Jina.ai API key for accessing the reader API| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 3,383 | 19,780 | +485% | 1 | 1 | 0% | 555 | 2,234 | +303% | 0 | 0 | — |
case-02 | fail→fail | 8,568 | 5,252 | -39% | 1 | 1 | 0% | 1,551 | 766 | -51% | 0 | 0 | — |
case-03 | fail→pass | 10,169 | 3,842 | -62% | 1 | 1 | 0% | 1,634 | 1,066 | -35% | 0 | 0 | — |
case-04 | pass→pass | 16,677 | 11,277 | -32% | 1 | 1 | 0% | 2,650 | 2,326 | -12% | 0 | 0 | — |
case-09 | fail→pass | 7,486 | 2,222 | -70% | 1 | 1 | 0% | 1,302 | 818 | -37% | 0 | 0 | — |
case-05 | pass→pass | 8,968 | 8,301 | -7% | 1 | 1 | 0% | 1,546 | 1,806 | +17% | 0 | 0 | — |
case-06 | pass→pass | 11,772 | 7,163 | -39% | 1 | 1 | 0% | 2,015 | 1,589 | -21% | 0 | 0 | — |
case-07 | pass→pass | 4,647 | 2,119 | -54% | 1 | 1 | 0% | 771 | 770 | -0% | 0 | 0 | — |
case-08 | pass→pass | 3,964 | 2,432 | -39% | 1 | 1 | 0% | 596 | 785 | +32% | 0 | 0 | — |
case-10 | fail→pass | 6,276 | 2,442 | -61% | 1 | 1 | 0% | 1,005 | 806 | -20% | 0 | 0 | — |
case-11 | fail→pass | 9,893 | 1,516 | -85% | 1 | 1 | 0% | 1,556 | 634 | -59% | 0 | 0 | — |
case-12 | fail→pass | 5,956 | 1,563 | -74% | 1 | 1 | 0% | 939 | 637 | -32% | 0 | 0 | — |
case-13 | pass→pass | 5,860 | 1,927 | -67% | 1 | 1 | 0% | 865 | 669 | -23% | 0 | 0 | — |
case-14 | pass→pass | 17,065 | 4,145 | -76% | 1 | 1 | 0% | 2,606 | 1,039 | -60% | 0 | 0 | — |
case-15 | fail→pass | 6,517 | 1,364 | -79% | 1 | 1 | 0% | 1,047 | 561 | -46% | 0 | 0 | — |
case-16 | fail→pass | 10,142 | 2,543 | -75% | 1 | 1 | 0% | 1,554 | 827 | -47% | 0 | 0 | — |
case-17 | pass→pass | 12,281 | 4,429 | -64% | 1 | 1 | 0% | 1,883 | 893 | -53% | 0 | 0 | — |
case-18 | fail→pass | 7,180 | 1,852 | -74% | 1 | 1 | 0% | 1,149 | 687 | -40% | 0 | 0 | — |
case-19 | fail→pass | 3,353 | 1,636 | -51% | 1 | 1 | 0% | 498 | 616 | +24% | 0 | 0 | — |
case-20 | fail→pass | 5,632 | 1,470 | -74% | 1 | 1 | 0% | 894 | 641 | -28% | 0 | 0 | — |
case-21 | fail→pass | 5,413 | 1,119 | -79% | 1 | 1 | 0% | 907 | 564 | -38% | 0 | 0 | — |
case-22 | fail→pass | 12,511 | 5,004 | -60% | 1 | 1 | 0% | 2,110 | 1,201 | -43% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +59 percentage points is the difference between those two pass rates over the 21 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.