All authors
Claude Skills by theopenco
github.com/theopenco19 skills0 installs18 views
- Add ModelAdd a model or provider mapping to the catalogue, or verify one that was already written — pricing, capability and reasoning metadata, scoped e2e, and playground options for image/video models. Use when the user asks to add a named model on a provider, create a provider mapping, add a provider, check model pricing, verify a model, or change packages/models/src/models.Votes: 0GitHub stars: 1,674
- MigrationsGenerate, review, edit, apply, or resolve conflicts for Drizzle database migrations in this repo. Use when changing packages/db/src/schema.ts, running pnpm migrations or pnpm migrate, touching packages/db/migrations, reviewing migration diffs, or handling migration merge conflicts.Votes: 0GitHub stars: 1,674
- DatabaseQuery and change the LLM Gateway Postgres schema with Drizzle — reads, raw SQL, analytics and usage queries, the log table versus the hourly aggregation tables, used_model ids, cost sums, cached queries, and new columns. Use when editing packages/db/src/schema.ts, writing Drizzle or raw SQL, building dashboards, stats, or usage reports, adding an organization column, or pushing and seeding the local database. For migration files use the migrations skill.Votes: 0GitHub stars: 1,674
- Core Web VitalsOptimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".Votes: 0GitHub stars: 1,672
- BlogWrite and validate an LLM Gateway marketing blog post in the repository's current house style, including structured frontmatter and a gpt-image-2 OpenGraph image. Use when the user says "blog", "blog post", "write a blog post", "draft a blog", "add a blog post", "publish a blog", or "write an article" for the marketing site. For shipped-feature release notes use the `changelog` skill instead.Votes: 0GitHub stars: 1,672
- ChangelogWrite a new LLM Gateway changelog entry. Use when the user says "changelog", "changelog entry", "write a changelog", "add a changelog", "announce this feature", or asks to document a shipped feature for the public changelog. Produces the dated markdown file under apps/ui/src/content/changelog plus a gpt-image-2 prompt for the OpenGraph image.Votes: 0GitHub stars: 1,672
- Knowledge BaseWrite a new LLM Gateway docs Knowledge base page under apps/docs/content/(product)/learn with light and dark dashboard screenshots. Use when the user asks for a knowledge base page, KB page, learn page, or documentation for a dashboard or playground page with screenshots.Votes: 0GitHub stars: 1,672
- Pull RequestCreate, update, illustrate, and hand off pull requests in this repo. Use when opening a PR, pushing a branch for review, writing or revising a PR title/description, embedding a screenshot or image in a PR body, triggering e2e CI on a PR, or whenever the user mentions "PR", "pull request", "open a PR", "update the PR", or "attach a screenshot to the PR".Votes: 0GitHub stars: 1,672
- Skill AuthoringCreate, update, and audit repository-local agent skills against the current LLM Gateway codebase. Use when adding or editing files under .agents/skills or .claude/skills, reviewing a skill for stale instructions, or checking that skill paths, commands, cross-references, and workflows actually exist.Votes: 0GitHub stars: 1,672
- VerifyBuild, launch, and drive the LLM Gateway stack in an isolated worktree environment to verify API, gateway, dashboard, playground, or screenshot changes. Use when locally reproducing a change, launching services on offset ports, taking seeded-data screenshots, or checking a workflow end to end.Votes: 0GitHub stars: 1,672
- Model BenchmarksRun and report repository model or provider-mapping benchmarks. Use when asked to benchmark a model, compare all mappings or regions, collect latency or throughput metrics, measure agentic coding or multi-turn tool-calling performance, run the smoke, standard, coding, load, capability, quality, or performance suites, or inspect an existing benchmark JSON result.Votes: 0GitHub stars: 1,672
- BillingOrganizations, plans, credits, and billing in LLM Gateway — org kinds, the Pro plan, DevPass and Chat entitlements, Stripe webhooks, end-user wallets, cost and token billing math, audit logs, and org-scoped emails and notifications. Use when changing apps/api/src/stripe.ts, subscription or credit logic, cost calculation, organization.kind or plan gating, DevPass status, audit_log actions, or any email or notification sent for an organization.Votes: 0GitHub stars: 1,672
- FrontendBuild and change LLM Gateway Next.js frontends — apps/ui, apps/playground, apps/code, apps/airside, and ee/admin — including API calls, data fetching, navigation, dashboard routes, dialogs and popovers, charts, number formatting, and user settings. Use when editing React components or pages in those apps, adding a dashboard page, calling the API from the UI, or formatting displayed values.Votes: 0GitHub stars: 1,672
- GatewayChange the LLM Gateway request path in apps/gateway — chat and other endpoints, routing and provider selection, error and finish-reason classification, streaming, request logging, Redis use, user-supplied content URLs, and graceful shutdown. Use when editing apps/gateway/src or packages/actions request shaping, adding an endpoint, fetching remote content, changing fallback or routing, or debugging missing logs, hung Redis commands, or shutdown errors.Votes: 0GitHub stars: 1,672
- InfrastructureProduction infrastructure and request-origin facts for LLM Gateway — GCP hosting, production hostnames and which app serves each, deploy ordering, client IP extraction, forwarded headers, and visitor country. Use when touching client IP or geolocation code, IP rate limits or allow-lists, X-Forwarded-For or X-Client-Ip, server-side calls on a visitor's behalf, deployment assumptions, or when reasoning about api.llmgateway.io versus internal.llmgateway.io.Votes: 0GitHub stars: 1,672
- Legal PagesEdit LLM Gateway legal documents — Terms of Use, Privacy Policy, sub-processors, and product-specific supplemental terms such as DevPass. Use when changing any legal page, company details, contact address, data retention wording, or plan rules stated in legal text.Votes: 0GitHub stars: 1,672
- Local StackRun an isolated per-worktree LLM Gateway stack — own Postgres, Redis, storage Redis, and app ports — and tear it down safely. Use before running unit tests, starting dev servers, reseeding, or running docker compose in a worktree; when choosing STACK_SUFFIX, port slots, or .envrc; when a port is taken, a local server behaves like another worktree's code, or a relocated frontend fails CORS or login.Votes: 0GitHub stars: 1,672
- TestingRun, write, and debug LLM Gateway unit and e2e tests — pnpm test:unit, pnpm test:e2e, TEST_MODELS scoping, the gateway test harness, seeded accounts and test tokens, pinning a provider with x-no-fallback, e2e proxies, and test fixtures or cleanup. Use when running or adding *.spec.ts or *.e2e.ts files, reproducing a provider failure locally, triggering CI e2e, or when tests fail only locally or intermittently.Votes: 0GitHub stars: 1,672
- Security AuditSecurity best practices, vulnerability review, and full security audits for LLM Gateway. Use when writing security-sensitive code (auth, sessions, API keys, provider keys, billing, webhooks, user-supplied URLs, admin routes, CORS, rendering user content), when asked for a security review, security report, vulnerability research, pen test, or security audit, and for the monthly audit routine that fixes confirmed findings in a PR.Votes: 0GitHub stars: 1,672