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.

48

Quality

51%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/salesforce-automation/SKILL.md

The canonical home for this skill is salesforce-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-5

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

The content is well-structured and provides concrete tool names, parameters, pitfalls, and executable SOQL examples, but it is a single monolithic file with duplicated reference material and lacks validation checkpoints in its destructive/batch record workflows. Several sections are redundant or stub-like.

Suggestions

Add explicit validation/verification checkpoints to destructive and batch workflows (e.g. after update/complete/transfer, re-fetch the record to confirm the change) to clear the workflow_clarity cap.

Move the Quick Reference table and SOQL pattern examples into a separate references/ file and link to it one level deep, keeping SKILL.md as a concise overview.

Remove the empty 'When to Use' stub and de-duplicate the pitfalls that restate the 'Key parameters' required-field notes.

DimensionReasoningScore

Conciseness

The body is mostly lean tool/param/pitfall lists, but the stub 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview.') is pure padding, and the Quick Reference table duplicates the workflow sections, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened.'

3 / 5

Actionability

Concrete tool names, exact parameter bullets, and copy-paste-ready SOQL examples provide real guidance, but the workflow sections list tools with [Optional] tags and param bullets rather than executable call payloads, so they describe rather than instruct — matching 'some concrete guidance but incomplete.'

3 / 5

Workflow Clarity

Setup is sequenced with an explicit ACTIVE-status checkpoint, but the record-mutation workflows (update lead, complete task, mass transfer ownership) involve destructive/batch operations yet have no validation or verification step, triggering the cap of 3.

3 / 5

Progressive Disclosure

The file is well-organized with clear section headers, but it is a ~190-line monolith with no references/ scripts/ or assets/ bundle; the large inlined Quick Reference table and SOQL patterns belong in separate reference files, fitting 'some structure but content that should be separate is inline.'

3 / 5

Total

12

/

20

Passed

Description

53%Weight 40%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 clearly identifies the domain and tooling and enumerates the CRM objects covered, but relies on the vague verb 'Automate' and omits any 'Use when...' trigger guidance. It is specific enough to be distinct but incomplete on the 'when' axis.

Suggestions

Replace the generic verb 'Automate Salesforce tasks' with concrete actions per object, e.g. 'Create, search, update, and list leads, contacts, accounts, and opportunities; run SOQL queries.'

Add an explicit trigger clause such as 'Use when the user wants to manage Salesforce CRM records or run SOQL queries via Rube MCP.'

Include a synonym or two users naturally say (e.g. 'CRM records', 'deals/pipeline') to broaden trigger coverage.

DimensionReasoningScore

Specificity

The phrase 'leads, contacts, accounts, opportunities, SOQL queries' names the concrete domains, but the single verb 'Automate Salesforce tasks' leaves the per-object actions (create/search/update) unspecified, matching the 'names domain and 1-2 concrete actions but not comprehensive' anchor rather than the multi-action 4.

3 / 5

Completeness

The 'what' is clear ('Automate Salesforce tasks via Rube MCP (Composio): leads, contacts, accounts, opportunities, SOQL queries') but there is no 'when' clause — 'Always search tools first' is a behavior instruction, not a trigger, so the missing-trigger cap of 3 applies.

3 / 5

Trigger Term Quality

'leads, contacts, accounts, opportunities, SOQL queries' are real Salesforce terms users say, but synonyms (CRM, deals, pipeline) and the 'Use when...' phrasing are absent, fitting 'some relevant keywords but missing common variations.'

3 / 5

Distinctiveness Conflict Risk

'Salesforce tasks via Rube MCP (Composio)' is a clearly distinct niche with minimal overlap risk, but the absence of explicit trigger phrasing keeps it just below the 'clear niche with distinct triggers' 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

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.