byerlikaya/claude-starter-kit

Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.

22Stars on the repository
68Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

a11y

01

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Frontend accessibility audit (WCAG): semantic HTML, keyboard access, focus management, contrast, ARIA, screen readers. Use when building or changing UI, or before shipping a user-facing screen.

not rated 22 today A 43 tokens original MIT

adr

02

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.

not rated 22 today A SkillSpector: warn 27 tokens original MIT

api-design

03

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

API contract design: resource naming, error model, versioning, pagination, backward compatibility, OpenAPI. A predictable interface that evolves without breaking consumers.

not rated 22 today A SkillSpector: warn 33 tokens original MIT

automode-policy

04

byerlikaya/claude-starter-kit

Skill Claude Code

Auto-mode classifier config: inspect what the classifier that now answers permission prompts is configured with, and catch the silent case where a custom autoMode block drops the built-in block rules.

not rated 22 today B 41 tokens original MIT

brainstorm

05

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Divergent discovery BEFORE planning: turn a fuzzy ask into 2–4 scoped options + named unknowns, pick a direction, hand to spec-planning. Bounded; converges to explicit choices, never guesses.

not rated 22 today A 49 tokens original MIT

ci-pipeline

06

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

CI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.

not rated 22 today A 30 tokens original MIT

code-review-csk

07

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Code review discipline: severity-ranked, reasoned feedback on whether a change improves the system's overall code health. review-agent-csk applies it. Use when reviewing a change set, and when acting on a review someone else wrote.

not rated 22 today A SkillSpector: warn 52 tokens original MIT

commit-message

08

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Conventional Commits: reads the staged diff and proposes type(scope): summary, with body/footer when needed. One logical change = one commit. commit-agent-csk applies it.

not rated 22 today A SkillSpector: warn 40 tokens original MIT

confidence-check

09

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Readiness gate BEFORE writing implementation code: does this already exist, does it fit the project's architecture, is the API claim actually checked, is there a working reference, is the root cause known.

not rated 22 today A 43 tokens original MIT

db-migration

10

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Apply schema migrations safely: detect the tool, classify the change by risk, gate destructive ones behind approval, back up in prod, preview-apply-verify, roll back on failure. Use when a schema change is about to be applied to any environment.

not rated 22 today A SkillSpector: warn 56 tokens original MIT

dependency-audit

11

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Dependency risk assessment, read-only: known CVEs, deprecated packages, licence compliance, maintenance status, lockfile integrity, and a justification for every new dependency. Acting on it is dependency-upgrade.

not rated 22 today A SkillSpector: warn 45 tokens original MIT

dependency-upgrade

12

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Bring dependencies current without breaking the build: find what is vulnerable, deprecated or behind, classify each target version by risk, apply what is safe, verify, and roll back what is not.

not rated 22 today A SkillSpector: warn 43 tokens original MIT

deploy

13

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Ship a build reversibly — to a host you manage or a platform that manages it. Pick the topology first, keep the previous version reachable, gate on health, roll back without rebuilding. Use when shipping anywhere users can reach.

not rated 22 today A ✓ AI review 50 tokens original MIT

devarch-module

14

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

DevArchitecture backend pattern: MediatR CQRS handler/command/query, IResult/IDataResult, Autofac AOP chain, FluentValidation, i18n. backend-expert-csk applies it.

not rated 22 today A SkillSpector: warn 47 tokens original MIT

docs-writer

15

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Keeps documentation in sync with the code: README, usage and related docs when a public API or behavior changes. Leaves no dead or misleading docs behind.

not rated 22 today A 36 tokens original MIT

eval-grader

16

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Measure output quality, don't vibe it: score a generative task with a two-layer grader — deterministic code metrics + per-dimension LLM-as-judge — over a fixed task set, as signed deltas vs a pinned baseline. Grades cost alongside correctness (pass-slow).

not rated 22 today A 62 tokens original MIT

frontend-design

17

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Visual and UX design quality for interfaces: hierarchy, spacing rhythm, typographic scale, a restrained color system, layout composition, and polished states. The taste layer above frontend architecture and a11y.

not rated 22 today A 44 tokens original MIT

frontend-rn-expo

18

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

OPTIONAL, stack-specific: React Native + Expo (prebuild). Mobile RN projects only; the generic principles live in the frontend skill.

not rated 22 today A 37 tokens original MIT

frontend

19

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Stack-agnostic frontend discipline (web · mobile · desktop): component structure, state, data fetching, loading/empty/error states, i18n, accessibility, performance. frontend-expert-csk applies it on every stack.

not rated 22 today A 48 tokens original MIT

handoff

20

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Session handover: when context fills, a phase closes, or the topic changes, write an action-oriented handover to docs/SESSIONSTATE.md, then recommend /clear.

not rated 22 today A SkillSpector: warn 39 tokens original MIT

i18n-integrity

21

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Translation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. Runs when user-facing text changes.

not rated 22 today A SkillSpector: warn 35 tokens original MIT

incident-runbook

22

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Production incident response: diagnose → mitigate → resolve, then a blameless postmortem and a repeatable runbook. Stop the impact first, root cause second. Use when production is degraded or broken, and again for the postmortem afterwards.

not rated 22 today A 56 tokens original MIT

iterate

23

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Refine-to-Done loop: repeat until tests green + review clean + nothing deferred; bounded. Not the harness /loop.

not rated 22 today A 28 tokens original MIT

mcp-builder

24

byerlikaya/claude-starter-kit

Skill Claude CodeCodex

Build a Model Context Protocol (MCP) server so an AI client can call your tools/resources: design tool schemas, pick a transport, handle errors, and test it. For exposing an API, database, or service to Claude and other clients.

not rated 22 today A 54 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: