CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

salesforce-developer

Writes and debugs Apex code, builds Lightning Web Components, optimizes SOQL queries, implements triggers, batch jobs, platform events, and integrations on the Salesforce platform. Use when developing Salesforce applications, customizing CRM workflows, managing governor limits, bulk processing, or setting up Salesforce DX and CI/CD pipelines.

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-structured, highly actionable skill body with excellent progressive disclosure via a load-conditions reference table and complete executable code patterns. Its main weakness is token efficiency: the boilerplate LWC counter example and the duplicated anti-pattern trigger block re-teach things an expert model already knows and could be trimmed or moved to references.

Suggestions

Trim the conciseness gap: replace the ~35-line counter LWC example (component + meta.xml scaffolding Claude already knows) with a short pointer to references/lightning-web-components.md, keeping only any non-obvious wiring details inline.

Remove the full INCORRECT trigger code block; a one-line note ('never place SOQL/DML inside a loop — see bulkified pattern') preserves the constraint without the duplicate listing.

Add an explicit error-recovery feedback loop to the Core Workflow (e.g., 'if governor limits are exceeded, refactor to batch/queueable and re-validate') to raise workflow clarity to a full checkpoint-and-retry pattern.

DimensionReasoningScore

Conciseness

The body is mostly efficient — terse MUST DO/MUST NOT constraint lists and no concept-explanation padding — but spends ~35 lines on a trivial counter LWC with full meta.xml boilerplate that Claude already knows, plus a complete duplicate INCORRECT trigger block where a one-line note would suffice. That is more than 'minor instances of over-explanation' (anchor 4), fitting anchor 3.

3 / 5

Actionability

All five code examples (bulkified trigger handler, batch apex with partial-success update, @TestSetup test class, selective/relationship SOQL, LWC bundle with meta.xml) are complete, executable, and copy-paste ready, covering the most common Salesforce development cases — matching anchor 5. Nothing is pseudocode or incomplete.

5 / 5

Workflow Clarity

The six-step Core Workflow has a clear sequence with an explicit validation checkpoint ("Verify SOQL/DML counts, heap size, and CPU time stay within platform limits before proceeding") and a bulk-scenario test step, so the batch-operation cap does not apply. It falls short of anchor 5 only because there is no explicit error-recovery feedback loop (e.g., 'if limits are exceeded, refactor to batch/queueable').

4 / 5

Progressive Disclosure

The Reference Guide table signals each topic with a path and a 'Load When' condition; all five referenced files exist and are exactly one level deep; core patterns stay inline while bulk detail lives in references. This matches anchor 5 (clear overview, well-signaled one-level-deep references, easy navigation) rather than 4, since there are no organization gaps.

5 / 5

Total

17

/

20

Passed

Description

92%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.

A strong description: third-person voice, specific and comprehensive capability list, and an explicit 'Use when...' clause with concrete trigger contexts. The only gap is a few natural synonym/abbreviation terms (LWC, SOSL, Visualforce) that appear in the metadata triggers but not in the description itself.

DimensionReasoningScore

Specificity

"Writes and debugs Apex code, builds Lightning Web Components, optimizes SOQL queries, implements triggers, batch jobs, platform events, and integrations" lists multiple specific concrete actions with comprehensive coverage of the Salesforce development domain, matching the anchor-5 example's breadth. It is not 4 because there are no meaningful gaps in the capability coverage.

5 / 5

Completeness

It clearly answers both what ("Writes and debugs Apex code, builds Lightning Web Components, optimizes SOQL queries...") and when ("Use when developing Salesforce applications, customizing CRM workflows, managing governor limits, bulk processing, or setting up Salesforce DX and CI/CD pipelines") with concrete trigger phrases, matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Good natural keyword coverage — "Apex", "Lightning Web Components", "SOQL", "Salesforce DX", "governor limits", "CRM", "CI/CD" — but a few natural terms users say are missing from the description itself (the "LWC" abbreviation, "SOSL", "Visualforce"), matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Salesforce is a clear niche with distinct triggers (Apex, LWC, SOQL, governor limits, Salesforce DX); the description would not plausibly fire for a non-Salesforce skill. Minor generic words like "integrations" and "CI/CD" are anchored by the Salesforce context, so this fits anchor 5 rather than 4.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Jeffallan/claude-skills

Path

skills/salesforce-developer/SKILL.md

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.