~ / rigs / selmakcby / claude-agents-skills

selmakcby/claude-agents-skills

Multi-Agent Claude Code setup — 4 uzman ajan (planner · ui-agent · builder · reviewer) + skills + Next.js demo projesi. YouTube Bölüm 1 video materyalleri.

↗ GitHub ★ 136 MIT updated 6mo ago collection Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.5k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit selmakcby/claude-agents-skills/my-project-demo/.claude ./rig-claude-agents-skills  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit selmakcby/claude-agents-skills/my-project-demo/.claude/skills/api-design .claude/skills/api-design
$ npx degit selmakcby/claude-agents-skills/my-project-demo/.claude/skills/code-review .claude/skills/code-review
$ npx degit selmakcby/claude-agents-skills/my-project-demo/.claude/skills/plan .claude/skills/plan
$ npx degit selmakcby/claude-agents-skills/my-project-demo/.claude/skills/security-review .claude/skills/security-review
$ npx degit selmakcby/claude-agents-skills/my-project-demo/.claude/skills/ui-ux-pro-max .claude/skills/ui-ux-pro-max
$ npx degit selmakcby/claude-agents-skills/skills/tdd .claude/skills/tdd
$ curl -fsSL --create-dirs -o .claude/agents/builder.md https://raw.githubusercontent.com/selmakcby/claude-agents-skills/main/my-project-demo/.claude/agents/builder.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/selmakcby/claude-agents-skills/main/my-project-demo/.claude/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/selmakcby/claude-agents-skills/main/my-project-demo/.claude/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/ui-agent.md https://raw.githubusercontent.com/selmakcby/claude-agents-skills/main/my-project-demo/.claude/agents/ui-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/builder.md https://raw.githubusercontent.com/selmakcby/claude-agents-skills/main/agents/builder.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/selmakcby/claude-agents-skills/main/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/selmakcby/claude-agents-skills/main/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/ui-agent.md https://raw.githubusercontent.com/selmakcby/claude-agents-skills/main/agents/ui-agent.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (6)

Subagents (8)

builder
model: opus
Backend implementation specialist. Use for API routes, database schemas, business logic, webhooks, and server-side code. Follows test-first (TDD) practices and returns a summary of what was built.
planner
model: opus
Use PROACTIVELY when the user requests a new feature, refactor, or architectural change. Produces step-by-step implementation plans before any code is written. Never writes code itself.
reviewer
model: sonnet
Use PROACTIVELY immediately after builder produces code. Double-role agent — checks BOTH code quality AND security before commit. Blocks merge on CRITICAL findings.
ui-agent
model: opus
Use after planner has produced a plan. Makes UI/UX decisions — layout, components, design tokens, accessibility. Produces a component brief the builder can implement from without asking questions.
builder
model: sonnet
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.
planner
model: opus
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.
reviewer
model: sonnet
Use PROACTIVELY immediately after builder produces code. Double-role agent that checks BOTH code quality AND security before commit. Blocks merge on CRITICAL issues.
ui-agent
model: sonnet
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.

Similar rigs

copied ✓