salesforce-automation
Automate Salesforce tasks via Rube MCP (Composio): leads, contacts, accounts, opportunities, SOQL queries. Always search tools first for current schemas.
72
58%
Does it follow best practices?
Impact
96%
1.71xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/salesforce-automation/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is strong in specificity and distinctiveness, clearly identifying Salesforce-specific entities and the integration mechanism. However, it lacks an explicit 'Use when...' clause which caps completeness, and the trigger terms could be broader to capture more natural user language like 'CRM' or 'sales pipeline'.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Salesforce, CRM tasks, managing sales data, or querying Salesforce records.'
Include common user-facing synonyms like 'CRM', 'sales pipeline', 'deal tracking', 'customer records' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete entities and actions: leads, contacts, accounts, opportunities, SOQL queries, and includes the operational guidance to search tools first for current schemas. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (automate Salesforce tasks involving leads, contacts, accounts, opportunities, SOQL queries), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes good domain-specific terms like 'Salesforce', 'leads', 'contacts', 'accounts', 'opportunities', 'SOQL queries', but misses common user variations like 'CRM', 'sales pipeline', 'deal tracking', or 'Salesforce automation'. The mention of 'Rube MCP (Composio)' is technical jargon users wouldn't naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific Salesforce domain, named integration (Rube MCP/Composio), and specific entity types. Unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid catalog of Salesforce operations via Rube MCP with useful tool names, required parameters, and SOQL examples. Its main weaknesses are the lack of concrete MCP tool call examples showing actual invocation patterns, missing validation/error-recovery steps in data-modifying workflows, and some redundancy between the workflow sections and the quick reference table. The content would benefit from being more prescriptive about when and how to chain tools together.
Suggestions
Add concrete examples of actual MCP tool calls (e.g., show a complete RUBE_SEARCH_TOOLS invocation and its response, then a SALESFORCE_CREATE_LEAD call with specific parameters) to improve actionability.
Add validation/verification steps after create and update operations (e.g., 'After creating a lead, verify by searching for it or checking the returned ID') to improve workflow clarity for destructive/modifying operations.
Remove or consolidate the quick reference table with the core workflows to reduce redundancy—or move it to a separate REFERENCE.md file for progressive disclosure.
Add decision logic or a brief flowchart for choosing between tools (e.g., when to use SALESFORCE_QUERY vs SALESFORCE_RUN_SOQL_QUERY, or when to search vs list) instead of marking everything [Optional].
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some redundancy—the quick reference table largely duplicates information already presented in the core workflows sections. The pitfalls sections repeat some points (e.g., ID formats mentioned twice). Some workflow descriptions could be tighter, but it generally avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and SOQL examples which are helpful. However, it lacks executable code examples showing actual MCP tool calls with concrete input/output, and the tool sequences are all marked [Optional] without clear guidance on when to use which combination. The SOQL examples are concrete and useful, but the MCP interaction patterns are underspecified. | 2 / 3 |
Workflow Clarity | The setup section has a clear 4-step sequence with a validation checkpoint (confirm ACTIVE status). However, the core workflows list tools as optional sequences without clear decision logic or validation steps. There are no feedback loops for error recovery—e.g., what to do if a create operation fails, or how to verify a record was created successfully. For operations that modify CRM data, this is a notable gap. | 2 / 3 |
Progressive Disclosure | The content is organized into logical sections with headers, and the quick reference table aids navigation. However, with no bundle files, all content is in one monolithic file (~150+ lines). The SOQL patterns, pitfalls, and quick reference table could be split into separate reference files. The external link to Composio docs is helpful but the internal organization could benefit from splitting. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
c911a92
- Reviewed
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.