salesforce-automation

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

1.71x

Quality

—

Does it follow best practices?

Impact

96%

1.71x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is well-structured and free of concept bloat, with a strong sequenced Setup workflow and a useful quick-reference table, but it is held back by duplicated content, missing executable call examples, absent verification steps on mutating operations, and no reference-file split for a skill of this length.

Suggestions

Remove the duplication between the per-workflow tool lists/pitfalls and the consolidated 'Quick Reference'/'Known Pitfalls' sections — keep one or the other to tighten conciseness.

Add at least one fully-parameterized executable example per CRUD workflow (e.g. a SALESFORCE_CREATE_LEAD call with LastName/Company values) and drop the uniformly-applied '[Optional]' tags, which obscure which tool is the actual entry point.

Add a verification checkpoint after mutating/batch operations (e.g. re-query the created record's Id, or confirm SOQL 'done' before paging) to lift workflow clarity, and split the quick-reference table and detailed pitfalls into reference files to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body largely avoids explaining concepts Claude already knows, but the per-workflow tool lists and pitfalls are duplicated by the consolidated 'Quick Reference' table and 'Known Pitfalls' section, so it 'could be tightened' rather than earning the lean/copy-paste-ready level.	2 / 3
Actionability	Concrete tool slugs, key parameters, and executable SOQL examples are given, but the CRUD workflows stop at tool-name lists with no full executable call example (no parameter values filled in), and every tool is confusingly tagged '[Optional]', leaving guidance 'incomplete' per the score-2 anchor.	2 / 3
Workflow Clarity	The Setup section is a well-sequenced process with a validation checkpoint ('Confirm connection status shows ACTIVE'), but the data-mutating workflows (create/update/mass-transfer) lack verification steps, and the guidelines cap workflow_clarity at 2 when batch/destructive operations omit validation.	2 / 3
Progressive Disclosure	The body is well-organized into clear sections, but for a ~190-line skill it is monolithic with no internal reference files, so 'content that should be separate is inline' rather than split via well-signaled one-level-deep references.	2 / 3
	Total	8 / 12 Passed

Description

72%

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 specific to the Salesforce CRM niche with strong natural trigger terms, but it omits an explicit 'Use when...' trigger clause, which caps completeness and leaves the 'when to use' guidance implicit.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to create, update, search, or query Salesforce leads, contacts, accounts, opportunities, or run SOQL.'

Replace the generic verb 'Automate Salesforce tasks' with concrete actions (create, update, search, query) to lift specificity from 'names domain' to 'lists multiple specific concrete actions'.

Move 'Always search tools first for current schemas' into the body — it is Claude-facing instruction, not a capability or trigger, and dilutes the description.

Dimension	Reasoning	Score
Specificity	It names the Salesforce domain and lists concrete entities ('leads, contacts, accounts, opportunities, SOQL queries'), but the only verbs are generic ('Automate Salesforce tasks', 'search tools first') rather than enumerated concrete actions, matching the 'names domain and some actions but not comprehensive' anchor.	2 / 3
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	Natural user terms are well covered — 'Salesforce', 'leads', 'contacts', 'accounts', 'opportunities', and 'SOQL queries' are exactly what a user would say, matching the 'good coverage of natural terms' anchor; 'Rube MCP (Composio)' is implementation detail, not a trigger.	3 / 3
Distinctiveness Conflict Risk	'Automate Salesforce tasks' is a clear niche with distinct Salesforce-specific triggers, making it unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Commit: 366e45b

Reviewed: about 23 hours ago

Table of Contents

Discovery Implementation Validation

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.