CtrlK
BlogDocsLog inGet started
Tessl Logo

salesforce-automation

Automate Salesforce tasks via Rube MCP (Composio): leads, contacts, accounts, opportunities, SOQL queries. Always search tools first for current schemas.

53

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/salesforce-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%Scale 1-5

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 reasonable catalog of Salesforce operations via Rube MCP with clear tool names, required parameters, and useful SOQL examples. However, it reads more like an API reference than an actionable workflow guide—most steps are marked [Optional] with no real decision logic, and there's significant duplication between workflow sections and the quick reference table. It lacks validation steps after operations and concrete tool invocation examples.

Suggestions

Replace [Optional] tags with actual decision guidance (e.g., 'If user provides search criteria, use SALESFORCE_SEARCH_LEADS first; if creating from scratch, skip to SALESFORCE_CREATE_LEAD')

Add at least one concrete end-to-end example showing actual tool invocation with parameters and expected response handling

Add validation/verification steps after create and update operations (e.g., 'Confirm creation by checking the returned ID' or 'Verify update with a follow-up search')

Remove the quick reference table or the detailed workflow sections to eliminate duplication—keep whichever format better serves the use case

DimensionReasoningScore

Conciseness

The skill is moderately efficient but contains repetitive patterns across workflows (each section follows the same template with [Optional] tags that add little value). The quick reference table duplicates information already covered in the workflow sections. The 'When to Use' footer is vacuous. Some pitfalls are repeated (e.g., ID formats mentioned in both Leads and Known Pitfalls sections).

3 / 5

Actionability

The skill lists tool names and parameters clearly, and provides concrete SOQL examples. However, it lacks executable examples showing actual tool invocations with full parameter structures. Every tool in the workflows is marked [Optional], which provides no real guidance on when to use which tool. The setup steps are concrete but the core workflows are more like reference catalogs than actionable instructions.

3 / 5

Workflow Clarity

The setup section has a clear 4-step sequence with a validation checkpoint (confirm ACTIVE status). However, the core workflows lack true sequencing—they're lists of optional tools rather than guided workflows. There are no validation/verification steps after operations (e.g., confirming a lead was created successfully, verifying SOQL results). For batch operations like MASS_TRANSFER_OWNERSHIP, there's no validation or error recovery guidance.

3 / 5

Progressive Disclosure

The content is structured with clear sections and headers, which aids navigation. However, at ~180 lines with significant repetition, some content (like the full quick reference table or detailed SOQL patterns) could be split into separate reference files. There are no bundle files or external references, and the skill is long enough that it would benefit from them. The instruction to 'always call RUBE_SEARCH_TOOLS first to get current tool schemas' partially mitigates the need for detailed inline documentation.

3 / 5

Total

12

/

20

Passed

Description

70%Scale 1-5

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 reasonably specific about the Salesforce domain and the tooling (Rube MCP/Composio), with good trigger terms for Salesforce-related queries. Its main weakness is the absence of an explicit 'Use when...' clause, which limits Claude's ability to know precisely when to select this skill. The behavioral instruction about searching tools first is a nice operational detail but doesn't substitute for trigger guidance.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Salesforce CRM tasks, managing leads/contacts/accounts/opportunities, or running SOQL queries.'

Include common synonyms and related terms like 'CRM', 'sales pipeline', 'deal management', or 'Salesforce API' to improve trigger matching.

DimensionReasoningScore

Specificity

Lists several specific Salesforce objects (leads, contacts, accounts, opportunities) and mentions SOQL queries, but doesn't detail specific actions like 'create', 'update', 'delete' for each object. The instruction to 'search tools first for current schemas' adds a concrete behavioral directive.

4 / 5

Completeness

Has a clear 'what' (automate Salesforce tasks via Rube MCP with specific object types), but lacks an explicit 'when' clause. There's no 'Use when...' guidance telling Claude when to select this skill over others.

3 / 5

Trigger Term Quality

Includes strong trigger terms like 'Salesforce', 'leads', 'contacts', 'accounts', 'opportunities', 'SOQL queries', and 'Rube MCP (Composio)'. Missing some natural user phrases like 'CRM', 'sales pipeline', 'deal tracking', or 'Salesforce automation'.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive with the specific combination of Salesforce, Rube MCP, Composio, and named Salesforce objects. Very unlikely to conflict with other skills given the narrow technology stack and platform specificity.

5 / 5

Total

16

/

20

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.