instagram-automation
Automate Instagram tasks via Rube MCP (Composio): create posts, carousels, manage media, get insights, and publishing limits. Always search tools first for current schemas.
Install with Tessl CLI
npx tessl i github:Lingjie-chen/MT5 --skill instagram-automation73
Quality
65%
Does it follow best practices?
Impact
82%
2.27xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/instagram-automation/SKILL.mdEvaluation results
85%
65%Product Launch Instagram Post Automation
Single image post workflow
RUBE_SEARCH_TOOLS first
0%
0%
RUBE_MANAGE_CONNECTIONS call
0%
100%
ACTIVE status check
0%
100%
INSTAGRAM_GET_USER_INFO for ID
0%
100%
INSTAGRAM_CREATE_MEDIA_CONTAINER
40%
100%
Status poll before publish
0%
100%
Waits for FINISHED status
0%
100%
Correct publish tool
25%
100%
Caption length validation
100%
100%
Public HTTPS URL requirement
55%
100%
Avoids temporary URLs
0%
37%
Without context: $0.4307 · 2m 10s · 25 turns · 22 in / 7,316 out tokens
With context: $0.5097 · 2m 9s · 21 turns · 275 in / 7,645 out tokens
92%
48%Fashion Lookbook Carousel Automation
Carousel post creation
RUBE_SEARCH_TOOLS first
0%
0%
ig_user_id resolution
0%
100%
Item count validation
100%
100%
Individual container per item
100%
100%
Status poll per child container
0%
100%
All children FINISHED before carousel
0%
100%
INSTAGRAM_CREATE_CAROUSEL_CONTAINER
100%
100%
Carousel status poll before publish
0%
100%
Correct carousel publish tool
0%
100%
Mixed media support
100%
100%
Without context: $1.7883 · 7m 17s · 51 turns · 1,812 in / 18,589 out tokens
With context: $0.6048 · 2m 40s · 23 turns · 433 in / 9,853 out tokens
71%
26%Flash Sale Bulk Instagram Publishing
Rate limits and bulk posting
RUBE_SEARCH_TOOLS first
0%
100%
Publishing limit check before batch
100%
100%
25-post limit enforced
100%
100%
Rolling window awareness
100%
100%
Exponential backoff on 429
0%
66%
Status poll before each publish
0%
0%
Correct publish tool
100%
100%
ig_user_id from GET_USER_INFO
0%
100%
RUBE_MANAGE_CONNECTIONS check
0%
0%
Without context: $0.8298 · 3m 34s · 41 turns · 2,134 in / 12,144 out tokens
With context: $1.0345 · 4m 7s · 33 turns · 289 in / 16,758 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.