abyssale-automation
Automate Abyssale tasks via Rube MCP (Composio). Always search tools first for current schemas.
69
53%
Does it follow best practices?
Impact
100%
16.66xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./composio-skills/abyssale-automation/SKILL.mdEvaluation results
100%
93%Abyssale Integration Runbook
Connection setup and tool discovery workflow
Search tools first step
0%
100%
RUBE_SEARCH_TOOLS structure
0%
100%
Abyssale use_case query
0%
100%
RUBE_MANAGE_CONNECTIONS step
0%
100%
Session ID passed to connection check
0%
100%
ACTIVE status check
33%
100%
Auth link fallback
0%
100%
Search before execute ordering
0%
100%
No hardcoded tool slugs
0%
100%
Confirm connection before execute
37%
100%
Without context: $0.3072 · 1m 26s · 15 turns · 18 in / 5,169 out tokens
With context: $0.3030 · 1m 15s · 16 turns · 18 in / 4,253 out tokens
100%
100%Abyssale Multi-Step Banner Generation Script
Session management and memory parameter usage
Single session throughout
0%
100%
Session generated once
0%
100%
Memory parameter present
0%
100%
Memory parameter empty object
0%
100%
Tool slugs from search
0%
100%
RUBE_SEARCH_TOOLS before execute
0%
100%
Schema-compliant arguments
0%
100%
Connection check included
0%
100%
Session ID in connection check
0%
100%
ACTIVE check before tools
0%
100%
Without context: $0.3502 · 1m 26s · 19 turns · 20 in / 5,337 out tokens
With context: $0.3541 · 1m 20s · 20 turns · 280 in / 4,335 out tokens
100%
87%Abyssale Template Catalog and Bulk Banner Export
Bulk operations, pagination, and full schema retrieval
RUBE_REMOTE_WORKBENCH for bulk
0%
100%
run_composio_tool in workbench
0%
100%
Pagination token check
25%
100%
Continue fetching until complete
75%
100%
RUBE_GET_TOOL_SCHEMAS usage
0%
100%
schemaRef trigger condition
0%
100%
RUBE_SEARCH_TOOLS first
0%
100%
Memory parameter in execute calls
0%
100%
Session reuse across steps
0%
100%
Schema-compliant arg construction
14%
100%
Without context: $0.3672 · 1m 49s · 22 turns · 392 in / 7,587 out tokens
With context: $0.2404 · 1m 7s · 11 turns · 170 in / 4,376 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.