CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

query-layer

Compose Result-returning services into TanStack Query with Wellcrafted's resultQueries and resultMutations, one invalidation rule per QueryClient, and composition by spread. Use when editing createQuery, createMutation, resultQueries, resultMutations, resultQueryOptions, resultMutationOptions, runQuery, runMutation, a QueryClient or MutationCache, cache keys, invalidation, or optimistic updates.

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, highly actionable instruction skill: executable examples for every pattern, clear scope-placement rules, and a coherent grounding-to-naming flow, with essentially no filler. The only deductions are a version-pinned detail outside a deprecated section and the absence of explicit validation checkpoints.

DimensionReasoningScore

Conciseness

The body is dense and project-specific — every section states non-obvious rules ("So do not call `invalidateQueries` after a write in a component or a mutation callback", "writes refer to reads, never the reverse") with no padding and no explanation of concepts Claude already knows. It misses the 5 anchor because time-sensitive version information ("as installed (0.47)") appears outside any old-patterns/deprecated section, which the guidelines say should penalize conciseness.

4 / 5

Actionability

Guidance is copy-paste ready and covers the common cases: the two-map resultQueries/resultMutations declaration, hook usage ("createQuery(() => billingQueries.overview())"), the full MutationCache invalidation rule, the mutationOptions spread with setQueryData, and the imperative runMutation example with error handling. It exceeds the 4 anchor because examples are executable (not pseudocode) and span all of the skill's named patterns.

5 / 5

Workflow Clarity

The sections form a coherent, ordered decision path — ground against installed sources, compose in two maps, install one invalidation rule per client, place behavior by scope via spread, run imperatively — with a grounding checkpoint ("confirm the deciding detail in the installed `@tanstack/query-core` source"). It stops short of 5 because no explicit validation/feedback-loop steps exist, and sits above 3 because the sequence and decision points are clear and no risky operation lacks guidance.

4 / 5

Progressive Disclosure

No bundle files exist, and the single ~157-line body is organized into seven well-labeled sections with clearly signaled one-level-deep pointers (the wellcrafted/query GitHub source, DeepWiki, and related skills services-layer/svelte/error-handling). It fits the 4 anchor of good structure with minor gaps — the length slightly exceeds the ideal single-file overview, and a rationale-heavy passage (the plan-change-preview POST example) could live in a reference — but nothing is buried or nested.

4 / 5

Total

17

/

20

Passed

Description

83%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 with an explicit third-person what-statement and an explicit, symbol-level 'Use when' trigger clause covering almost the entire API surface. Its only weaknesses are a few missing natural term variations and slight overlap risk on generic TanStack vocabulary.

DimensionReasoningScore

Specificity

Names concrete actions — "Compose Result-returning services into TanStack Query", "one invalidation rule per QueryClient, and composition by spread" — alongside the specific tools (resultQueries, resultMutations). It falls short of the 5 anchor because the what-sentence omits parts of the skill's coverage (imperative runs, error handling) that only appear in the trigger list; it is above 3 because several specific actions are listed, not just 1-2.

4 / 5

Completeness

It explicitly answers both questions: what ("Compose Result-returning services into TanStack Query with Wellcrafted's resultQueries and resultMutations, one invalidation rule per QueryClient, and composition by spread") and when ("Use when editing createQuery, ... cache keys, invalidation, or optimistic updates") with concrete trigger phrases, matching the 5 anchor exactly; 4 would require the when-clause to be less explicit, which it is not.

5 / 5

Trigger Term Quality

The "Use when editing" clause enumerates nearly the full API surface users would naturally name: createQuery, createMutation, resultQueries, resultMutations, resultQueryOptions, resultMutationOptions, runQuery, runMutation, a QueryClient or MutationCache, cache keys, invalidation, optimistic updates. A few natural variations are missing (e.g. "queryKey"/"query keys" instead of "cache keys", "stale"), which fits the 4 anchor of good coverage with a few terms missing rather than the comprehensive-synonym coverage of 5.

4 / 5

Distinctiveness Conflict Risk

Wellcrafted-specific symbols (resultQueries, resultMutations, runQuery) form a clear niche unlikely to fire the wrong skill, but broadly shared TanStack terms like "invalidation", "optimistic updates", and "cache keys" create minor overlap with a general TanStack Query skill. This fits "mostly distinct; minor overlap risk with closely related skills" rather than the minimal-conflict 5 anchor.

4 / 5

Total

17

/

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

Path

.agents/skills/query-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.