CtrlK
BlogDocsLog inGet started
Tessl Logo

query-layer

Query/RPC layer with TanStack Query, defineKeys, service composition, runtime DI. Use for createQuery, createMutation, queries/mutations, reactive data management.

70

Quality

85%

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

85%

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

The body is highly actionable with executable code and clear decision guidance, and it practices good progressive disclosure through conditional one-level-deep references. The main improvement area is conciseness, where some rules and the decision table restate guidance already covered in adjacent prose.

Suggestions

Consolidate guidance that currently appears in 'Adapter Boundary', 'Reactive And Imperative Use', and 'Key Rules' to remove restated rules and let the 'When to Use Each' table be the single decision source.

Reduce overlap between the reactive/imperative prose and the 'When to Use Each' table so the table stands as the authoritative quick reference rather than repeating nearby content.

DimensionReasoningScore

Conciseness

The body is largely lean with tables and real code and no beginner-concept padding, but some guidance is restated across 'Adapter Boundary', 'Reactive And Imperative Use', and 'Key Rules', and the 'When to Use Each' table partially duplicates the preceding prose, fitting the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

Provides fully executable TypeScript and Svelte code blocks with real imports and typed parameters, specific API surfaces (`.options`, `.fetch()`, `.ensure()`), and a decision table mapping concrete situations to patterns, matching the 'fully executable, copy-paste ready' anchor.

3 / 3

Workflow Clarity

As a non-destructive patterns guide, it offers explicit, unambiguous decision sequencing via the 'When to Use Each' table and clear reactive-vs-imperative branching; no risky batch/destructive operations require validation checkpoints, so the unambiguous flow earns the top anchor.

3 / 3

Progressive Disclosure

SKILL.md serves as an overview with three real, one-level-deep reference files (verified present) each linked via explicit conditional triggers ('If working with X, read ...'), plus pointers to the RPC README and sibling skills, matching the 'clear overview with well-signaled one-level-deep references' anchor.

3 / 3

Total

11

/

12

Passed

Description

85%

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 is specific and complete, explicitly stating both what the skill does and when to use it with named API triggers. Its main weakness is trigger-term breadth, leaning on internal API names rather than the full range of natural phrasings a user might say.

Suggestions

Broaden trigger terms to include natural user phrasings such as 'data fetching', 'caching', 'cache invalidation', and 'optimistic updates' alongside the current API names.

Consider trimming the dense jargon cluster ('defineKeys, service composition, runtime DI') slightly so the most common triggers (createQuery/createMutation, queries/mutations) stand out for matching.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities and named APIs: 'createQuery, createMutation, queries/mutations, reactive data management' plus 'defineKeys, service composition, runtime DI', matching the 'Lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('Query/RPC layer with TanStack Query, defineKeys, service composition, runtime DI') and when ('Use for createQuery, createMutation, queries/mutations, reactive data management'), matching the 'clearly answers both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

Relevant keywords exist ('createQuery', 'createMutation', 'queries/mutations', 'reactive data management') but coverage leans on internal API jargon and misses common natural variations like 'data fetching', 'caching', or 'cache invalidation', fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The Query/RPC-layer niche anchored to TanStack Query, defineKeys, and RPC constructs is a clear, distinct domain unlikely to trigger the wrong skill; only 'reactive data management' is mildly generic, but not enough to drop it.

3 / 3

Total

11

/

12

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.

Validation16 / 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.