agent-mail-automation
Automate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.
Install with Tessl CLI
npx tessl i github:haniakrim21/everything-claude-code --skill agent-mail-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/skillEvaluation — 97%
↑ 2.42xAgent success when using this skill
Validation for skill structure
Evaluation results
97%
22%Email Inbox Automation Runbook
Core workflow pattern and session management
RUBE_SEARCH_TOOLS first
0%
100%
RUBE_MANAGE_CONNECTIONS step
30%
100%
ACTIVE status check
100%
100%
RUBE_MULTI_EXECUTE_TOOL usage
100%
100%
Memory parameter
100%
100%
Session ID reuse
100%
100%
New session for new workflow
100%
100%
Pagination handling
100%
100%
No hardcoded tool slugs
40%
70%
Schema compliance note
100%
100%
Rube MCP setup
100%
100%
Without context: $1.4762 · 5m 17s · 34 turns · 855 in / 8,000 out tokens
With context: $0.4455 · 1m 49s · 23 turns · 63 in / 6,239 out tokens
100%
70%Support Email Triage Script
Tool discovery and schema-compliant execution
RUBE_SEARCH_TOOLS before execution
0%
100%
Specific use_case query
0%
100%
Slugs from search results
25%
100%
RUBE_MANAGE_CONNECTIONS check
0%
100%
RUBE_MULTI_EXECUTE_TOOL used
0%
100%
Memory parameter included
0%
100%
Schema-compliant args note
87%
100%
Pagination loop
100%
100%
Session ID in tool calls
0%
100%
No hardcoded slugs in execution
100%
100%
Without context: $0.1627 · 57s · 10 turns · 13 in / 3,144 out tokens
With context: $0.2063 · 52s · 11 turns · 422 in / 3,026 out tokens
94%
78%Quarterly Email Archive Automation
Bulk operations and full schema retrieval
RUBE_REMOTE_WORKBENCH for bulk
0%
100%
run_composio_tool() call
0%
100%
RUBE_GET_TOOL_SCHEMAS for schemaRef
33%
100%
RUBE_SEARCH_TOOLS first
40%
100%
RUBE_MANAGE_CONNECTIONS check
0%
100%
ACTIVE status required
0%
100%
Schema from search results
50%
70%
Session ID maintained
0%
100%
Memory parameter
0%
100%
No hardcoded slugs
33%
50%
Without context: $0.3209 · 1m 21s · 16 turns · 153 in / 4,140 out tokens
With context: $0.2986 · 1m 17s · 16 turns · 53 in / 4,107 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Unknown
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.