selmakcby

14 mods across 3 repositories, 324 stars between them.

llm-wiki

01

selmakcby/knowledge-pipeline

Skill Claude CodeCodex

LLM tarafından sürekli inşa edilen ve güncellenen kalıcı, birikimli bir bilgi arşivi (persistent wiki) deseni. Standart RAG'ın aksine her sorguda bilgi yeniden keşfedilmez — ajan yeni kaynakları okur, mevcut wiki'ye entegre eder, varlık/kavram sayfalarını günceller, çelişkileri işaretler, çapraz-referansları korur.…

not rated 172 +2 1mo ago A 0 tokens

builder

02

selmakcby/claude-agents-skills

Agent Claude Code

Use after planner and ui-agent have produced their briefs. Writes the actual application code, follows TDD (test-first). Handles implementation — not planning or design.

not rated 143 +2 6mo ago A 34 tokens original MIT

planner

03

selmakcby/claude-agents-skills

Agent Claude Code

Use PROACTIVELY when the user asks to implement a new feature, refactor code, or make architectural changes. Creates step-by-step implementation plans before any code is written.

not rated 143 +2 6mo ago A 38 tokens original MIT

reviewer

04

selmakcby/claude-agents-skills

Agent Claude Code

Use PROACTIVELY immediately after builder produces code. Double-role agent that checks BOTH code quality AND security before commit. Blocks merge on CRITICAL issues.

not rated 143 +2 6mo ago A 34 tokens original MIT

ui-agent

05

selmakcby/claude-agents-skills

Agent Claude Code

Use when the user needs UI/UX design decisions, component architecture, layout, typography, color system, or visual hierarchy. Produces design notes the builder agent can implement from.

not rated 143 +2 6mo ago A 39 tokens original MIT

api-design

06

selmakcby/claude-agents-skills

Skill Claude Code

Backend API design specialist. Use when building REST/GraphQL APIs, designing endpoints, data models, or backend architecture. Covers RESTful principles, HTTP semantics, error handling, versioning, and OWASP-aligned security.

not rated 143 +2 6mo ago A 48 tokens original MIT

code-review

07

selmakcby/claude-agents-skills

Skill Claude Code

Senior code review specialist. Use PROACTIVELY after writing or modifying code. Reviews for quality, correctness, performance, and best practices. Assigns severity levels to findings (CRITICAL / HIGH / MEDIUM / LOW).

not rated 143 +2 6mo ago A 48 tokens original MIT

plan

08

selmakcby/claude-agents-skills

Skill Claude Code

Implementation planning specialist. Use when the user requests a feature, refactor, or architectural change. Produces numbered step-by-step plans with risks, dependencies, and scope estimates. Never writes code.

not rated 143 +2 6mo ago A 41 tokens original MIT

security-review

09

selmakcby/claude-agents-skills

Skill Claude Code

AI-powered security vulnerability detection. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, payments, or sensitive data. Flags OWASP Top 10 issues with diff-aware scanning.

not rated 143 +2 6mo ago A 45 tokens original MIT

ui-ux-pro-max

10

selmakcby/claude-agents-skills

Skill Claude Code

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types with reasoning rules, 99 UX guidelines, and 25 chart types across 10 technology stacks. Use when designing UI, choosing palettes, typography, or component architecture.

not rated 143 +2 6mo ago A 71 tokens original MIT

tdd

11

selmakcby/claude-agents-skills

Skill Claude CodeCodex

Test-Driven Development workflow. Use when writing new features, fixing bugs, or refactoring code. Enforces RED-GREEN-REFACTOR cycle with 80%+ coverage.

not rated 143 +2 6mo ago A 40 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: