salesforce

tessl i github:jdrhyne/agent-skills --skill salesforce

Query and manage Salesforce orgs via the official Salesforce MCP server or SF CLI.

Review Score

63%

Validation Score

12/16

Implementation Score

73%

Activation Score

33%

SKILL.md

Review

Evals

Generated

13 days ago

Warnings & errors only

Criteria	Score
description_trigger_hint	Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...')
metadata_version	'metadata' field is not a dictionary
license_field	'license' field is missing
body_output_format	No obvious output/return/format terms detected; consider specifying expected outputs

Overall Assessment

This skill provides strong actionable content with executable queries and commands, and good progressive disclosure structure. However, it's somewhat verbose with template placeholders and explanatory content that assumes less of Claude's knowledge. The setup workflow lacks validation steps to confirm successful org connection.

Suggestions

Remove explanatory definitions for standard concepts (ACV, ARR, TCV, record types) that Claude already understands - just list the API names
Add validation steps to the setup workflow: e.g., 'Verify connection: `sf org display --target-org my-prod` should show org details'
Trim the 'Key Concepts' section to just show the customization format without generic examples, or move to SALESFORCE_STRUCTURE.md

Dimension	Score	Reasoning
Conciseness	2/3	The skill includes some unnecessary explanatory content (e.g., explaining what ACV/ARR/TCV mean, generic record type descriptions) that Claude would already know. The template placeholders and tips sections add bulk that could be trimmed.
Actionability	3/3	Provides fully executable SOQL queries, concrete CLI commands, and copy-paste ready MCP tool invocations. The examples are specific and immediately usable.
Workflow Clarity	2/3	Setup steps are listed but lack validation checkpoints. No guidance on verifying org connection succeeded, no error handling for failed queries, and no feedback loop for troubleshooting authentication issues.
Progressive Disclosure	3/3	Well-structured with clear sections and appropriate references to external files (SALESFORCE_STRUCTURE.md, BUSINESS_LOGIC.md, COMMON_QUERIES.md). Navigation is clear and references are one level deep.

Overall Assessment

The description identifies the Salesforce domain and mentions specific tools (MCP server, SF CLI), which provides some clarity. However, it lacks concrete action examples, natural trigger terms users would say, and critically missing explicit 'Use when...' guidance that would help Claude select this skill appropriately.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user mentions Salesforce, SOQL queries, SF CLI, sfdx, or CRM data operations'
Expand specific capabilities beyond 'query and manage' to concrete actions like 'run SOQL queries, deploy metadata, manage users, retrieve org information'
Include common user terms and variations: 'Salesforce', 'SFDC', 'sfdx', 'SOQL', 'Apex', 'CRM'

Dimension	Score	Reasoning
Specificity	2/3	Names the domain (Salesforce) and mentions two tools (MCP server, SF CLI), but 'query and manage' are fairly generic actions without listing specific concrete capabilities like 'run SOQL queries, deploy metadata, manage users'.
Completeness	1/3	Describes what it does (query and manage Salesforce orgs) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.
Trigger Term Quality	2/3	Includes 'Salesforce', 'orgs', 'MCP server', and 'SF CLI' which are relevant keywords, but misses common user terms like 'SOQL', 'Apex', 'sfdx', 'CRM', or 'Salesforce data'.
Distinctiveness Conflict Risk	2/3	Salesforce-specific focus provides some distinctiveness, but 'query and manage' is vague enough that it could overlap with generic database or CRM skills without clearer boundaries.

Repository: github.com/jdrhyne/agent-skills
Last updated: 13 days ago
Created: 13 days ago

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.