Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automate Twitter/X with posting, engagement, and user management via inference.sh CLI. Apps: x/post-tweet, x/post-create (with media), x/post-like, x/post-retweet, x/dm-send, x/user-follow. Capabilities: post tweets, schedule content, like posts, retweet, send DMs, follow users, get profiles. Use for: social media automation, content scheduling, engagement bots, audience growth, X API. Triggers: twitter api, x api, tweet automation, post to twitter, twitter bot, social media automation, x automa
.claude/skills/aiskillstore-twitter-automation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -4% | 0% |
Automate Twitter/X via inference.sh CLI.
> Requires inference.sh CLI (infsh). Get installation instructions: npx skills add inference-sh/skills@agent-tools
bashinfsh login # Post a tweet infsh app run x/post-tweet --input '{"text": "Hello from inference.sh!"}'
| App | App ID | Description | |-----|--------|-------------| | Post Tweet | x/post-tweet | Post text tweets | | Create Post | x/post-create | Post with media | | Like Post | x/post-like | Like a tweet | | Retweet | x/post-retweet | Retweet a post | | Delete Post | x/post-delete | Delete a tweet | | Get Post | x/post-get | Get tweet by ID | | Send DM | x/dm-send | Send direct message | | Follow User | x/user-follow | Follow a user | | Get User | x/user-get | Get user profile |
bashinfsh app run x/post-tweet --input '{"text": "Just shipped a new feature! 🚀"}'
bashinfsh app sample x/post-create --save input.json # Edit input.json: # { # "text": "Check out this AI-generated image!", # "media_url": "https://your-image-url.jpg" # } infsh app run x/post-create --input input.json
bashinfsh app run x/post-like --input '{"tweet_id": "1234567890"}'
bashinfsh app run x/post-retweet --input '{"tweet_id": "1234567890"}'
bashinfsh app run x/dm-send --input '{ "recipient_id": "user_id_here", "text": "Hey! Thanks for the follow." }'
bashinfsh app run x/user-follow --input '{"username": "elonmusk"}'
bashinfsh app run x/user-get --input '{"username": "OpenAI"}'
bashinfsh app run x/post-get --input '{"tweet_id": "1234567890"}'
bashinfsh app run x/post-delete --input '{"tweet_id": "1234567890"}'
bash# 1. Generate image infsh app run falai/flux-dev-lora --input '{"prompt": "sunset over mountains"}' > image.json # 2. Post to Twitter with the image URL infsh app run x/post-create --input '{ "text": "AI-generated art of a sunset 🌅", "media_url": "<image-url-from-step-1>" }'
bash# 1. Generate video infsh app run google/veo-3-1-fast --input '{"prompt": "waves on a beach"}' > video.json # 2. Post to Twitter infsh app run x/post-create --input '{ "text": "AI-generated video 🎬", "media_url": "<video-url-from-step-1>" }'
bash# Full platform skill (all 150+ apps) npx skills add inference-sh/skills@agent-tools # Image generation (create images to post) npx skills add inference-sh/skills@ai-image-generation # Video generation (create videos to post) npx skills add inference-sh/skills@ai-video-generation # AI avatars (create presenter videos) npx skills add inference-sh/skills@ai-avatar-video
Browse all apps: infsh app list
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,234 | 6,067 | -46% | 1 | 1 | 0% | 2,046 | 1,546 | -24% | 0 | 0 | — |
case-02 | fail→pass | 16,144 | 5,837 | -64% | 1 | 1 | 0% | 3,395 | 2,381 | -30% | 0 | 0 | — |
case-03 | fail→pass | 9,108 | 3,640 | -60% | 1 | 1 | 0% | 1,474 | 1,900 | +29% | 0 | 0 | — |
case-04 | pass→pass | 17,702 | 16,724 | -6% | 1 | 1 | 0% | 4,073 | 5,093 | +25% | 0 | 0 | — |
case-05 | pass→pass | 15,595 | 15,418 | -1% | 1 | 1 | 0% | 3,126 | 4,197 | +34% | 0 | 0 | — |
case-06 | pass→pass | 10,933 | 6,898 | -37% | 1 | 1 | 0% | 2,289 | 2,558 | +12% | 0 | 0 | — |
case-07 | fail→pass | 12,395 | 2,932 | -76% | 1 | 1 | 0% | 2,385 | 1,701 | -29% | 0 | 0 | — |
case-08 | fail→pass | 11,127 | 4,076 | -63% | 1 | 1 | 0% | 2,081 | 1,998 | -4% | 0 | 0 | — |
case-09 | fail→pass | 8,167 | 3,052 | -63% | 1 | 1 | 0% | 1,483 | 1,753 | +18% | 0 | 0 | — |
case-10 | fail→pass | 7,118 | 2,423 | -66% | 1 | 1 | 0% | 1,381 | 1,618 | +17% | 0 | 0 | — |
case-11 | fail→pass | 14,511 | 2,601 | -82% | 1 | 1 | 0% | 2,231 | 1,652 | -26% | 0 | 0 | — |
case-12 | fail→pass | 10,071 | 2,791 | -72% | 1 | 1 | 0% | 1,628 | 1,655 | +2% | 0 | 0 | — |
case-13 | fail→pass | 10,431 | 3,337 | -68% | 1 | 1 | 0% | 1,849 | 1,821 | -2% | 0 | 0 | — |
case-14 | fail→pass | 9,324 | 3,499 | -62% | 1 | 1 | 0% | 1,760 | 1,846 | +5% | 0 | 0 | — |
case-15 | fail→pass | 8,674 | 3,257 | -62% | 1 | 1 | 0% | 1,491 | 1,715 | +15% | 0 | 0 | — |
case-16 | fail→pass | 11,068 | 2,960 | -73% | 1 | 1 | 0% | 2,038 | 1,690 | -17% | 0 | 0 | — |
case-17 | fail→pass | 11,274 | 3,557 | -68% | 1 | 1 | 0% | 1,958 | 1,857 | -5% | 0 | 0 | — |
case-22 | fail→pass | 6,840 | 1,890 | -72% | 1 | 1 | 0% | 1,218 | 1,486 | +22% | 0 | 0 | — |
case-18 | fail→pass | 9,659 | 3,240 | -66% | 1 | 1 | 0% | 1,761 | 1,755 | -0% | 0 | 0 | — |
case-19 | fail→pass | 5,466 | 4,435 | -19% | 1 | 1 | 0% | 912 | 1,350 | +48% | 0 | 0 | — |
case-20 | fail→pass | 10,667 | 3,152 | -70% | 1 | 1 | 0% | 2,043 | 1,793 | -12% | 0 | 0 | — |
case-21 | fail→pass | 6,752 | 1,697 | -75% | 1 | 1 | 0% | 1,224 | 1,416 | +16% | 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 +86 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/21/2026 | +73% |
Other measured skills in the registry, with their headline benchmark lift.