CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

services-layer

Apply Epicenter's service-boundary patterns for UI-free capabilities, explicit inputs, Result fallibility, lifecycle factories, and a capability package that picks its browser or desktop implementation when the page runs. Use when creating or refactoring an app's services or their contract, provider or connection dispatch, or a desktop service over the shell, the credentials file, or the account.

Quality

89%

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

86%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 dense, well-organized pattern skill: every section carries project-specific rules anchored to real code, bundle references are real and well-signaled, and the Final Check checklist closes the loop. Minor deductions for a duplicated error-handling pointer and the lack of an explicit sequence (appropriate for a decision-rule skill, but it keeps workflow clarity below the top anchor).

Suggestions

In 'Model Fallibility Honestly', consolidate the two pointers to the error-handling skill into one sentence to save tokens.

Consider a one-line ordering note (read app.ts -> apply boundary rules -> run Final Check) to make the implicit workflow explicit for refactoring tasks.

DimensionReasoningScore

Conciseness

The body is lean and almost entirely project-specific (no explanations of concepts Claude already knows), but the 'Model Fallibility Honestly' section points to the error-handling skill twice ('Adapt throwing platform or library calls with the error-handling skill' and again 'Use error-handling for variant shape, message rules, adaptation, and propagation'). That minor duplication places it at the efficient-with-small-trims anchor rather than flawless token economy.

4 / 5

Actionability

Guidance is highly concrete: real function names and commands ('createMicrophoneDevice', 'customEndpoints()', 'isTauri()', 'connection_key_set'/'connection_key_move', 'account_fetch', 'connection_fetch', 'shellFetch', naming the data folder root as 'Data') plus codebase-grounded examples covering the common cases. For an instruction-only pattern skill this is fully actionable guidance.

5 / 5

Workflow Clarity

There is a clear read-first step ('Read the app's app.ts and the capability package's entry before changing a service') and an explicit 'Final Check' validation checklist covering every rule. However, the body is organized as decision rules rather than a sequenced process, so it sits between the clear-sequence anchor and the checklist-with-feedback-loops anchor.

4 / 5

Progressive Disclosure

The body is a genuine overview and both references are real files, one level deep, each clearly signaled with a read-condition ('Read [service organization and platform variants](references/service-organization-platforms.md) when adding or moving a service'; 'See [service implementation patterns](references/service-implementation-pattern.md)'). The split matches the content: organization/platform dispatch in one file, implementation patterns in the other.

5 / 5

Total

18

/

20

Passed

Description

88%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: it states concrete capabilities in third person, gives an explicit 'Use when' clause with specific triggers, and stays tightly scoped to its domain. The only weaknesses are a few missing natural trigger variations and slight overlap with a sibling skill's platform-dispatch topic.

DimensionReasoningScore

Specificity

The description lists multiple concrete pattern areas — 'UI-free capabilities, explicit inputs, Result fallibility, lifecycle factories, and a capability package that picks its browser or desktop implementation when the page runs' — comprehensively covering the skill's scope. It matches the anchor for multiple specific concrete actions rather than the anchor-4 case of minor gaps in coverage.

5 / 5

Completeness

Both parts are explicit: the what ('Apply Epicenter's service-boundary patterns for...') and the when ('Use when creating or refactoring an app's services or their contract, provider or connection dispatch, or a desktop service over the shell, the credentials file, or the account') with concrete trigger phrases. This matches the top anchor exactly.

5 / 5

Trigger Term Quality

Natural trigger terms are present ('creating or refactoring an app's services', 'provider or connection dispatch', 'desktop service', 'the shell, the credentials file, or the account'), giving good keyword coverage. A few natural variations a user might say (e.g. 'service layer', 'connection key', 'platform variant') are missing, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche (Epicenter service-boundary patterns) with specific triggers, so conflict risk is low. However, 'a capability package that picks its browser or desktop implementation when the page runs' overlaps the platform-seams sibling skill's territory, giving minor overlap risk with a closely related skill.

4 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

EpicenterHQ/epicenter

Path

.agents/skills/services-layer/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.