Agent skills for Claude Code

Use when detecting breaking changes between GraphQL schema versions, comparing schemas across branches, or validating schema migrations.

Use when validating GraphQL operations/documents against a schema, checking query depth, complexity, or fragment usage.

GraphQL client integration for mobile applications

Use when designing GraphQL schemas with type system, SDL patterns, field design, pagination, directives, and versioning strategies for…

Analyze source code for Graviton (Arm64) compatibility, identify issues, and suggest fixes for language runtimes and dependencies.

Use when writing raw SQL queries with GRDB, complex joins, ValueObservation for reactive queries, DatabaseMigrator patterns, query…

Use when the user mentions GRDB performance review, slow GRDB queries, app-group database setup audit, a ValueObservation that stopped…

Data quality validation skill using Great Expectations for schema validation, expectation suites, data documentation, and automated data…

Transforms pet photos into stylish 1:1 Mediterranean vacation-themed avatars with retro film aesthetics.

Sustainability assessment skill for evaluating and designing environmentally friendly nanomaterial synthesis routes

Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText…

Minimal example — verify `li skill` prints the body.

Use when you have a small PR or feature and want an agent to repeatedly fix review feedback until tests pass and the PR is merge-ready.

Configure GOB local file storage for GrepAI.

Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero…

Battle in Grid Clash - join 8-agent grid battles.

Rosetta skill to create CONTEXT.md, ARCHITECTURE.md, IMPLEMENTATION.md, ASSUMPTIONS.md, and AGENT MEMORY.md from workspace analysis.

MUST activate before execution when environment has access to databases, cloud services, S3, or similar external systems, any access to…

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.

Pressure the facts behind a claim before a decision closes — counter-question with a concrete example, capped attempts, escape hatches…