claudeskills.page

10 skills · 7 categories

Claude Code skills for GraphQL

GraphQL skills for schema design, resolvers without N+1 queries, pagination, authorization at the field level and API security limits on depth and cost.

Install all 10 Browse the list

Start with these

  1. 1

    GraphQL Schema Design

    Client-shaped schemas that resolve in bounded queries

    Claude designs GraphQL types from the queries clients actually send, chooses nullability that will not wipe a whole response on one failed field, and routes every relation through per-request DataLoaders so list queries stop fanning out into hundreds of SQL calls. It adds depth and cost limits, trusted documents, and schema diffs before anything is removed.

  2. 2

    Shopify Apps

    GraphQL-first Shopify apps that pass review

    Keeps Claude on the current Shopify platform: CLI-scaffolded apps configured in shopify.app.toml, GraphQL Admin calls with pinned versions and userErrors checks, bulk operations for big syncs, and webhooks verified against raw bytes and deduped by webhook id. It treats REST calls and Shopify Scripts as migration debt and never ships an app missing the three compliance webhooks.

  3. 3

    Review Feedback Resolution

    Every review thread closed with a commit or a reason

    Claude pulls every unresolved review thread through the GitHub GraphQL API and turns it into a checklist, reads all feedback before editing, and classifies each item as blocking, question, suggestion, nit or out of scope. Fixes land in focused commits with tests, each thread gets a reply with a commit SHA or evidence, settled threads are resolved, and the reviewer receives one summary with a re-request.

All 10 GraphQL skills

Grouped by category. Each card opens the full playbook, example prompts and install commands.

Engineering Workflow 1

No. 041

Review Feedback Resolution

Every review thread closed with a commit or a reason

Claude pulls every unresolved review thread through the GitHub GraphQL API and turns it into a checklist, reads all feedback before editing, and classifies each item as blocking, question, suggestion, nit or out of scope. Fixes land in focused commits with tests, each thread gets a reply with a commit SHA or evidence, settled threads are resolved, and the reviewer receives one summary with a re-request.

review-feedback-resolution 154 lines · 2 files

Frontend 1

No. 056

Micro-frontends

Split the frontend only when the org chart demands it

Makes Claude argue the split before building it. It runs a team-topology test, falls back to a boundary-enforced modular monolith when the test fails, and otherwise defaults to route-level apps behind a proxy, escalating to Module Federation only for a real same-page need. It then pins shared singletons, the route table, typed events, per-app budgets and manifest-based rollback.

micro-frontends 225 lines · 2 files

Backend & APIs 2

No. 086

GraphQL Schema Design

Client-shaped schemas that resolve in bounded queries

Claude designs GraphQL types from the queries clients actually send, chooses nullability that will not wipe a whole response on one failed field, and routes every relation through per-request DataLoaders so list queries stop fanning out into hundreds of SQL calls. It adds depth and cost limits, trusted documents, and schema diffs before anything is removed.

graphql-schema 188 lines
No. 092

Pagination and Filtering

Page one and page ten thousand cost the same

Claude builds list endpoints on keyset pagination with a unique tiebreaker instead of OFFSET, so deep pages stay fast and concurrent inserts never duplicate rows. It signs opaque cursors bound to the sort and filters, whitelists filter and sort syntax, creates an index for each allowed shape, replaces exact counts with estimates or capped counts, and proves it with EXPLAIN and a paging-under-writes test.

pagination-filtering 226 lines · 2 files

DevOps & SRE 1

★ No. 154

GitHub Actions

Faster CI, read-only tokens, zero stored cloud keys

Claude rewrites workflows so irrelevant changes skip CI, superseded runs cancel, and package and Docker caches make the warm path fast. Tokens default to read-only, deploys use OIDC with subject-restricted trust policies and protected environments, and untrusted PR text never reaches a shell. Results are linted with actionlint and zizmor and reported with before-and-after timings.

github-actions 227 lines · 2 files

Security 1

No. 268

API Security

Prove every endpoint denies the wrong user

Claude works through the OWASP API Security Top 10 with the checks that catch real breaches: queries scoped to the caller, strict input and output schemas against mass assignment and data leaks, default-deny function checks, page and body caps, and GraphQL cost limits. A bundled matrix script calls every endpoint as several users on staging and fails on any cross-account access.

api-security 176 lines · 2 files

Performance 1

No. 302

N+1 Queries

Query counts that stay flat as data grows

Claude counts queries per request before touching code, finds the repeated statement that differs only by ID, and traces it to the serializer, template or resolver that triggers it. It picks join loading for to-one relations, separate IN queries for collections, SQL aggregates for counts and DataLoader for resolvers, then adds a test that fails if the count grows again.

n-plus-one-queries 218 lines

Integrations 3

No. 419

Shopify Apps

GraphQL-first Shopify apps that pass review

Keeps Claude on the current Shopify platform: CLI-scaffolded apps configured in shopify.app.toml, GraphQL Admin calls with pinned versions and userErrors checks, bulk operations for big syncs, and webhooks verified against raw bytes and deduped by webhook id. It treats REST calls and Shopify Scripts as migration debt and never ships an app missing the three compliance webhooks.

shopify-apps 257 lines · 2 files
No. 406

GitHub API Automation

Bulk GitHub changes with dry runs and throttling

Claude scripts GitHub the careful way: it picks the least-privileged credential (GITHUB_TOKEN, fine-grained PAT, or GitHub App), prototypes with gh api, paginates every list, throttles writes under primary and secondary limits, and runs a dry run you approve before mutating anything. App webhooks are verified against the raw body and deduped by delivery ID.

github-api-automation 215 lines · 2 files
No. 409

Jira and Linear APIs

Ticket automation that never files the same bug twice

Claude automates issue trackers with production habits: an external key and mapping table so retries never create duplicate tickets, Jira's current JQL search endpoint with nextPageToken paging, Atlassian Document Format bodies, transitions looked up by ID, Linear GraphQL with complexity-aware queries, and HMAC-verified webhooks that ignore the integration's own writes.

issue-tracker-apis 227 lines · 2 files

Install

Every GraphQL skill in one command

Installs into ~/.claude/skills/. Add --project after -- to install into the current repository.

curl -fsSL https://claudeskills.page/install.sh | sh -s -- graphql-schema shopify-apps review-feedback-resolution micro-frontends api-security github-api-automation issue-tracker-apis github-actions pagination-filtering n-plus-one-queries

GraphQL skills FAQ

What is the best Claude Code skill for GraphQL?

Start with GraphQL Schema Design: Client-shaped schemas that resolve in bounded queries. Then add Shopify Apps and Review Feedback Resolution, which cover the next most common GraphQL requests.

How do I install all 10 GraphQL skills at once?

Pass every name to the installer in one command: curl -fsSL https://claudeskills.page/install.sh | sh -s -- graphql-schema shopify-apps review-feedback-resolution micro-frontends api-security github-api-automation issue-tracker-apis github-actions pagination-filtering n-plus-one-queries. Add --project to install them into the current repository's .claude/skills/ folder so your team gets them too.

Do these GraphQL skills work outside Claude Code?

Yes. Each skill uses only the portable Agent Skills frontmatter, so the same folder works on claude.ai, through the Claude API and in the Agent SDK. Skills that run bundled scripts need an environment with code execution.

Related technologies

esc