agenty-automation
Automate Agenty tasks via Rube MCP (Composio). Always search tools first for current schemas.
67
51%
Does it follow best practices?
Impact
97%
4.40xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./composio-skills/agenty-automation/SKILL.mdEvaluation results
93%
81%Automating Competitor Monitoring with Agenty
Core workflow pattern: search-connect-execute sequence
Search tools first
25%
100%
Connection check step
0%
100%
ACTIVE status gate
0%
100%
Execute tool used
0%
100%
Memory param included
0%
100%
Session ID generated
40%
100%
Session ID reused
20%
100%
Tool slug from search
18%
72%
Schema-compliant args
10%
60%
Without context: $0.4950 · 2m 36s · 24 turns · 130 in / 10,065 out tokens
With context: $0.6283 · 2m 41s · 24 turns · 284 in / 9,338 out tokens
99%
57%Agenty Run Audit: Complete Historical Data Export
Pagination handling and complete data retrieval
Search tools first
66%
100%
Connection verified
0%
100%
Pagination token checked
75%
100%
Loop until complete
94%
100%
Memory param present
0%
100%
Session ID reused
0%
100%
Tool slug from search
20%
90%
Without context: $1.4072 · 5m 30s · 31 turns · 3,679 in / 8,059 out tokens
With context: $0.8818 · 2m 53s · 37 turns · 80 in / 7,881 out tokens
100%
87%Scaling Lead Enrichment: Processing Hundreds of URLs with Agenty
Bulk operations via RUBE_REMOTE_WORKBENCH
Search tools first
0%
100%
Connection verified
0%
100%
RUBE_REMOTE_WORKBENCH used
0%
100%
run_composio_tool invoked
0%
100%
Does NOT loop RUBE_MULTI_EXECUTE_TOOL
100%
100%
Memory param present
0%
100%
Session ID reused
0%
100%
Bulk rationale given
37%
100%
Without context: $0.6731 · 4m 12s · 23 turns · 88 in / 9,942 out tokens
With context: $0.3876 · 1m 40s · 19 turns · 25 in / 5,293 out tokens
- Repository
- ComposioHQ/awesome-claude-skills
- Commit
2790447
- 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.