salesforce-automation
Automate Salesforce tasks via Rube MCP (Composio): leads, contacts, accounts, opportunities, SOQL queries. Always search tools first for current schemas.
Install with Tessl CLI
npx tessl i github:davepoon/buildwithclaude --skill salesforce-automation59
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
89%
61%Trade Show Lead Import Automation
Salesforce connection setup and lead creation workflow
RUBE_SEARCH_TOOLS first
0%
100%
RUBE_MANAGE_CONNECTIONS call
0%
100%
ACTIVE status check
0%
100%
Auth link handling
0%
100%
SALESFORCE_CREATE_LEAD tool
0%
100%
LastName field required
100%
100%
Company field required
100%
100%
Correct ID format note
0%
0%
Search before create option
25%
37%
Rube MCP endpoint
0%
100%
Pitfalls documented
100%
100%
Without context: $0.6500 · 2m 50s · 33 turns · 36 in / 9,776 out tokens
With context: $0.4572 · 2m 9s · 20 turns · 275 in / 6,520 out tokens
100%
8%Salesforce Reporting Query Library
SOQL query correctness and pagination handling
SOQL not SQL syntax
100%
100%
API names in pipeline query
100%
100%
Relationship traversal syntax
100%
100%
API names in contacts query
100%
100%
Date literal in recent_leads
100%
100%
Custom object __c suffix
100%
100%
Custom field __c suffix
100%
100%
Correct query tool used
20%
100%
Pagination with nextRecordsUrl
100%
100%
Checks 'done' field
100%
100%
Without context: $0.4850 · 1m 48s · 26 turns · 32 in / 6,862 out tokens
With context: $0.5919 · 2m 6s · 28 turns · 282 in / 7,927 out tokens
100%
50%Sales Pipeline Automation Script
Opportunity creation and pipeline management workflow
RUBE_SEARCH_TOOLS first
0%
100%
RUBE_MANAGE_CONNECTIONS call
0%
100%
ACTIVE status verified
0%
100%
SALESFORCE_CREATE_OPPORTUNITY tool
0%
100%
Name field included
100%
100%
StageName field included
100%
100%
CloseDate field included
100%
100%
Stage names exact match
100%
100%
Search/list before create
25%
100%
Pitfalls documented
60%
100%
Without context: $0.4937 · 2m 18s · 31 turns · 32 in / 7,904 out tokens
With context: $0.5632 · 2m 24s · 22 turns · 28 in / 8,318 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.