sergei-aronsen

60 mods across 1 repository, 5 stars between them.

API Design

36

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

REST API design patterns — naming, status codes, OpenAPI/Swagger, versioning. Triggers on api/endpoint/openapi/swagger keywords.

5 15d ago A 32 tokens original MIT

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

Use when starting any new task to select the right GSD mode (fast/quick/plan-phase) and the right model tier (Haiku/Sonnet/Opus) for subagents — prevents 5-10× cost overpay on routine work.

5 15d ago A 57 tokens original MIT

Database

39

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

Database patterns — migrations, indexes, N+1 prevention, query optimization. Triggers on database/migration/query/sql/orm keywords.

5 15d ago A 29 tokens original MIT

Docker

40

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

Docker and container best practices — Dockerfile patterns, multi-stage builds, compose, security. Triggers on docker/container/dockerfile/compose keywords.

5 15d ago A 31 tokens original MIT

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

Use before declaring work complete on business-critical phases — simulate a Senior practitioner (auth specialist, payment engineer, DBA, security auditor) reviewing the change with their failure-mode bias.

5 15d ago A 40 tokens original MIT

gsd-mode-selector

42

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

Use when user requests work via natural language ("fix this", "add feature X") — selects appropriate GSD command (gsd-fast / gsd-quick / gsd-plan-phase) based on risk and scope, prevents using heavyweight pipeline for trivial work.

5 15d ago A 56 tokens original MIT

LLM Patterns

43

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

LLM integration patterns — RAG, embeddings, streaming, tool use. Triggers on rag/embeddings/vector/llm/prompt keywords.

5 15d ago A 34 tokens original MIT

product-thinking

45

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

Use BEFORE coding any new feature, MVP, pricing/billing change, launch, or pivot. Acts as a product validation gate for solo founders — validates target user, JTBD, pain intensity, current alternative, success metric, distribution channel, structural advantage vs competitors, unit economics with SaaS-graveyard gate…

5 15d ago A 166 tokens original MIT

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

Use after deploying a phase to production, when integrating new external services, or when user-facing behavior changes — instruments runtime errors (Sentry), user funnels (Posthog), and pre-ship smoke (Playwright).

5 15d ago A 48 tokens original MIT

reality-check

47

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

Use after /gsd-ship to verify product behaves correctly in production — runs Playwright e2e against deployed URL, checks Sentry for new errors, validates Posthog conversion funnel.

5 15d ago A 42 tokens original MIT

Repomix

48

sergei-aronsen/claude-code-toolkit

Skill Claude CodeCodex

Pack the whole repo (or a remote one) into one AI-friendly file via Repomix. Use for architectural reviews, cross-repo handoff, full-codebase audits — not for single-file lookups. Triggers on "pack repo", "feed codebase to AI", "снапшот", "analyze remote repo".

5 15d ago A 73 tokens original MIT