CtrlK
BlogDocsLog inGet started
Tessl Logo

services-layer

Apply Whispering service-boundary patterns for UI-free capabilities, explicit inputs, Result fallibility, Live objects, lifecycle factories, and platform variants. Use when creating or refactoring services, contracts, provider dispatch, or the `$lib/services` barrel.

77

Quality

97%

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

100%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.

An exemplary architecture-guidance skill body: lean and jargon-appropriate prose, concrete code and exact file paths, an explicit final-check validation checklist, and well-signaled one-level-deep references that exist and deliver on their promises. No dimension shows meaningful weakness.

DimensionReasoningScore

Conciseness

The body is dense, rule-first prose with zero padding: no explanation of what services or Results are, just repo-specific rules like 'no runtime reads of Svelte stores, `settings`, `deviceConfig`'. Every section carries non-obvious, codebase-specific decisions, matching the lean anchor where every token earns its place; there is no over-explanation to justify a 4.

5 / 5

Actionability

Guidance is concrete and executable: a complete `DownloadService` type with the exact Result shape, the actual `services` barrel to extend, exact import specifiers (`#platform/text`, `#platform/tauri`), named files (`$lib/operations/transcribe.ts`), and current real examples ('local shortcut `register` / `unregister` returning `void`'). Combined with the fully-implemented `DownloadServiceLive` code in its reference, the common cases are covered copy-paste-ready; nothing is pseudocode or vague, so the minor-gaps anchor of 4 does not fit.

5 / 5

Workflow Clarity

The body is organized as a coherent traversal — boundary, fallibility, object-vs-factory, platform selection, barrel — ending in an explicit 'Final Check' checklist that serves as a validation checkpoint for the work. This matches the anchor's 'checklists for complex processes'; no destructive or batch operations are involved, so no validation cap applies, and each decision point is unambiguous.

5 / 5

Progressive Disclosure

The ~125-line body keeps principles inline and pushes worked examples to two clearly signaled, one-level-deep references — 'Read [service implementation patterns](references/service-implementation-pattern.md)' and '[service organization and platform variants](references/service-organization-platforms.md)' — both of which exist in the bundle, match their descriptions, and contain no further nesting. Content split and navigation match the clear-overview anchor.

5 / 5

Total

20

/

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, concise, explicitly states what the skill applies and when to use it, with repo-specific triggers that minimize conflict risk. The only weakness is keyword coverage — jargon-heavy terms crowd out a few natural synonyms a user might say.

Suggestions

Add one or two natural synonyms to the trigger clause, e.g. 'service layer' or 'platform seams', so users phrasing the need conversationally still match.

Soften jargon-only trigger terms like 'Result fallibility' and 'Live objects' with a plainer equivalent (e.g. 'Result-returning APIs, Live service objects') to widen the natural-term surface.

DimensionReasoningScore

Specificity

The description enumerates six concrete capability areas — 'UI-free capabilities, explicit inputs, Result fallibility, Live objects, lifecycle factories, and platform variants' — which comprehensively cover the skill's scope, matching the anchor for multiple specific concrete items. It is not score 4 because coverage is comprehensive rather than having minor gaps; not below because every listed item is a concrete, checkable pattern rather than generic domain talk.

5 / 5

Completeness

It explicitly answers both questions: the 'what' is 'Apply Whispering service-boundary patterns for UI-free capabilities, explicit inputs, ...' and the 'when' is a concrete trigger clause 'Use when creating or refactoring services, contracts, provider dispatch, or the `$lib/services` barrel'. This matches the anchor for clear, explicit what-and-when with concrete trigger phrases; the neighboring anchor 4 would require a weaker or less specific 'when'.

5 / 5

Trigger Term Quality

The 'Use when' clause supplies good natural triggers — 'creating or refactoring services, contracts, provider dispatch, or the `$lib/services` barrel' — terms a contributor would plausibly say. It falls short of 5 because common variations like 'service layer', 'platform seam', or 'dependency injection' are absent, and jargon terms like 'Result fallibility' and 'Live objects' are less user-natural; it is clearly above 3 because several relevant natural keywords are present, not just 'some'.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche — repo-specific service-boundary enforcement anchored to `$lib/services` and `#platform/*` — with triggers unlikely to fire for sibling skills like error-handling or define-errors. It is a distinct, well-bounded trigger set matching the minimal-conflict anchor, not merely 'mostly distinct'.

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
EpicenterHQ/epicenter
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.