amplitude-automation
Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first for current schemas.
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill amplitude-automation67
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
83%
21%Amplitude Event Tracking Integration
Event sending workflow and setup sequence
Search tools first
0%
30%
Connection management call
0%
100%
Active connection check
0%
100%
Millisecond timestamps
100%
100%
Event type required
100%
100%
User identifier per event
100%
100%
Event category validation
0%
0%
Batch sending
100%
100%
Async processing note
100%
100%
Defensive response parsing
100%
100%
Without context: $1.6481 · 12m 41s · 65 turns · 178 in / 18,028 out tokens
With context: $0.4734 · 4m 35s · 20 turns · 23 in / 6,962 out tokens
66%
1%Customer Support Investigation Runbook
User ID resolution and activity pagination
Search tools first
0%
0%
Connection management call
0%
0%
Active status verification
0%
0%
FIND_USER prerequisite
86%
73%
Internal ID for activity
100%
93%
ID source distinction
100%
90%
Pagination via offset
100%
91%
Limit parameter usage
100%
100%
Reverse chronological order
25%
100%
Defensive response parsing
62%
62%
Without context: $0.2947 · 3m 35s · 12 turns · 17 in / 5,790 out tokens
With context: $0.5694 · 4m 30s · 21 turns · 25 in / 9,528 out tokens
56%
21%Automated Cohort Membership Management
Async cohort membership update pattern
Search tools first
0%
0%
Connection management call
0%
0%
List cohorts for name lookup
33%
66%
Cohort ID extraction
70%
90%
Archived cohort filtering
12%
0%
Behavioral cohort requirement
62%
87%
Memberships structure
30%
100%
Status check after update
50%
91%
Poll until terminal state
66%
100%
Chunking large updates
8%
0%
Without context: $0.2966 · 3m 36s · 16 turns · 19 in / 6,007 out tokens
With context: $0.5444 · 5m 9s · 23 turns · 27 in / 8,153 out tokens
- Evaluated
- Agent
- Claude Code
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.