twitter-automation
Automate Twitter/X tasks via Rube MCP (Composio): posts, search, users, bookmarks, lists, media. Always search tools first for current schemas.
Install with Tessl CLI
npx tessl i github:davepoon/buildwithclaude --skill twitter-automation73
Quality
65%
Does it follow best practices?
Impact
85%
1.32xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/twitter-automation/SKILL.mdEvaluation results
90%
51%Social Media Campaign Automation Workflow
Media post workflow and non-idempotency handling
RUBE_SEARCH_TOOLS first
0%
100%
USER_LOOKUP_ME prerequisite
0%
0%
Connection verification
37%
100%
Correct image upload tool
20%
100%
Media ID as string
80%
100%
media__media_ids array
25%
100%
Deduplication logic
91%
100%
Non-idempotency awareness
50%
100%
Character limit awareness
0%
100%
URL character count
0%
100%
Correct tool sequence order
100%
100%
Without context: $0.3897 · 1m 55s · 20 turns · 68 in / 6,417 out tokens
With context: $0.6433 · 3m 5s · 23 turns · 28 in / 10,747 out tokens
83%
Tweet Research and Bookmark Collector
Search workflow and bookmark pagination token
RUBE_SEARCH_TOOLS first
0%
0%
USER_LOOKUP_ME before bookmarks
100%
100%
RECENT_SEARCH used for 7-day search
100%
100%
7-day coverage noted
100%
100%
Bookmark pagination_token
100%
100%
Bookmark user ID parameter
100%
100%
Empty results handling
100%
100%
Bookmarks privacy noted
100%
100%
Rate limit awareness
87%
87%
Query operators used
100%
100%
Connection verification
0%
0%
Without context: $1.0375 · 3m 57s · 32 turns · 32 in / 9,876 out tokens
With context: $0.3964 · 1m 32s · 17 turns · 424 in / 5,589 out tokens
84%
14%Twitter Influencer List Membership Report
User lookup constraints and list membership queries
RUBE_SEARCH_TOOLS first
0%
87%
Batch size at most 100
100%
100%
No @ prefix in usernames
100%
100%
User IDs as strings
100%
100%
List membership uses numeric ID
100%
100%
Suspended account error handling
100%
100%
USER_LOOKUP_ME called
0%
0%
Efficient batch lookup
100%
100%
Connection verification
0%
100%
Rate limit awareness
14%
0%
Structured JSON report output
100%
100%
Without context: $0.9633 · 4m 27s · 44 turns · 255 in / 15,235 out tokens
With context: $0.7634 · 3m 42s · 22 turns · 272 in / 13,653 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.