byerlikaya

60 mods across 1 repository, 22 stars between them.

byerlikaya

01

byerlikaya/claude-starter-kit

Plugin Claude Code

Barış Yerlikaya's Claude Code plugins — starting with the Agentic Working Kit.

22 4d ago A tokens not measured original MIT

backend-expert-csk

02

byerlikaya/claude-starter-kit

Agent

Senior .NET backend expert. Applies the project's backend-pattern skill (devarch-module = MediatR CQRS / IResult / AOP by default; a project may declare its own). Use proactively — owns server behaviour: endpoints, handlers, validators, controllers, business rules, integrations. Any request about it is yours whatever…

22 4d ago A 78 tokens original MIT

commit-agent-csk

03

byerlikaya/claude-starter-kit

Agent

Commit message specialist (thin trigger). Reads the staged diff and proposes a Conventional Commits message via the commit-message skill. Writes no source; commits only with user approval.

22 4d ago A 42 tokens original MIT

database-expert-csk

04

byerlikaya/claude-starter-kit

Agent

PostgreSQL + EF Core + Redis data-layer expert. Applies the db-migration skill. Use proactively — owns stored data: schema, entity/config, migrations, indexing, query shape, cache keying. Any request about it is yours whatever its size or wording.

22 4d ago A 64 tokens original MIT

devops-expert-csk

05

byerlikaya/claude-starter-kit

Agent

Ops/DevOps expert. Use proactively for CI pipelines, safe deployment/release to servers, and production incident response and blameless postmortems. Deploy is DESTRUCTIVE and OUTWARD-FACING — no unapproved release to prod (§4.4).

22 4d ago C 61 tokens original MIT

frontend-expert-csk

06

byerlikaya/claude-starter-kit

Agent

Stack-agnostic frontend expert — web (React/Next/Vue/Svelte/Angular), mobile (React Native/Flutter), desktop. The "how" lives in the frontend skill (mobile: frontend-rn-expo). Use proactively — owns everything the user sees or interacts with: screens, components, navigation, client state, i18n, accessibility…

22 4d ago A 130 tokens original MIT

byerlikaya/claude-starter-kit

Agent

Performance auditor. Use proactively when a change touches a hot path, a query/loop, a render path, a large payload, or when something is reported slow. Produces measured findings via performance; writes no fix.

22 4d ago A 52 tokens original MIT

planner-csk

08

byerlikaya/claude-starter-kit

Agent

Planning specialist. Use proactively before implementing a feature whose scope or acceptance criteria are unclear: task breakdown + acceptance criteria + dependency order, via the spec-planning skill. Plans; does not write code.

22 4d ago A 48 tokens original MIT

privacy-agent-csk

09

byerlikaya/claude-starter-kit

Agent

Privacy auditor for the regimes the project declares (KVKK/GDPR by default). Use proactively when personal data, legal basis/consent, data minimisation, retention, transparency, data-subject rights, or cross-border transfer are touched. Findings + fixes via privacy-compliance; writes no code.

22 4d ago A 70 tokens original MIT

review-agent-csk

10

byerlikaya/claude-starter-kit

Agent

Code review specialist. Use immediately after writing or modifying a nontrivial diff: audits whether it improves the system's code health, against the four principles (simplicity, surgical change, readability, altitude). Findings via code-review-csk; writes no code.

22 4d ago A 60 tokens original MIT

security-expert-csk

11

byerlikaya/claude-starter-kit

Agent

Security review expert. Use proactively whenever auth/authz, anonymous/token flows, secret leakage, injection, weak crypto, IDOR, rate limits, or tamper surface are touched. Findings + fixes via security-scan (plus sonarqube-check where used); writes no code.

22 4d ago A 67 tokens original MIT

session-manager-csk

12

byerlikaya/claude-starter-kit

Agent

Session/context health auditor. At every task close, evaluates context fill and appends the one-line status + recommendation to the END of the reply. Evaluates only; writes no code.

22 4d ago A 43 tokens original MIT

test-expert-csk

13

byerlikaya/claude-starter-kit

Agent

Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".

22 4d ago A 41 tokens original MIT

doctor-csk

16

byerlikaya/claude-starter-kit

Command

Health-check the installed kit — hooks executable, core.hooksPath set, gates wired, discipline loaded.

22 4d ago A 25 tokens original MIT

gates-csk

17

byerlikaya/claude-starter-kit

Command

Gate report — what the tool-level gates actually did, and which rules nothing has tripped.

22 4d ago A 24 tokens original MIT

skill-csk

22

byerlikaya/claude-starter-kit

Command

Author or change a kit component (skill / agent / command) against the template and its gates.

22 4d ago A 24 tokens original MIT

a11y

24

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.

22 4d ago A 43 tokens original MIT