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.
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads Wellcrafted's source and README on GitHub and asks DeepWiki questions about the TanStack/query repo. Both are vendor-maintained, but DeepWiki is an AI summary of a public repo that can include contributor-authored text, so the agent retrieves it by choice, which makes this low rather than no.
EpicenterHQ/epicenter
04f87cb
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.