~ / rigs / tzuyi0817 / dotagent

tzuyi0817/dotagent

AI coding agent settings that record personal preferences.

↗ GitHub ★ 0 no license updated 12d ago project Claude CodeCodex
stack: Shell
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~736 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details
Quality 15/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit tzuyi0817/dotagent/agents ./rig-dotagent/agents
$ npx degit tzuyi0817/dotagent/skills ./rig-dotagent/skills

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 tzuyi0817/dotagent/skills/address-review .claude/skills/address-review
$ npx degit tzuyi0817/dotagent/skills/build-prototype .claude/skills/build-prototype
$ npx degit tzuyi0817/dotagent/skills/coding-standards .claude/skills/coding-standards
$ npx degit tzuyi0817/dotagent/skills/complete-issue .claude/skills/complete-issue
$ npx degit tzuyi0817/dotagent/skills/diagnose-bug .claude/skills/diagnose-bug
$ npx degit tzuyi0817/dotagent/skills/e2e-testing .claude/skills/e2e-testing
$ npx degit tzuyi0817/dotagent/skills/frontend-code-review .claude/skills/frontend-code-review
$ npx degit tzuyi0817/dotagent/skills/grill-plan .claude/skills/grill-plan
$ npx degit tzuyi0817/dotagent/skills/pr-body .claude/skills/pr-body
$ npx degit tzuyi0817/dotagent/skills/review-pr .claude/skills/review-pr
$ npx degit tzuyi0817/dotagent/skills/unit-testing .claude/skills/unit-testing
$ npx degit tzuyi0817/dotagent/skills/vue2-refactor-composable .claude/skills/vue2-refactor-composable
$ npx degit tzuyi0817/dotagent/skills/vue3-setup .claude/skills/vue3-setup
$ npx degit tzuyi0817/dotagent/skills/writing-for-agents .claude/skills/writing-for-agents
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/tzuyi0817/dotagent/main/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/tzuyi0817/dotagent/main/agents/e2e-runner.md
$ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/tzuyi0817/dotagent/main/agents/refactor-cleaner.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

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

Skills (14)

Subagents (3)

code-reviewer
model: sonnet
程式碼審查專家。主動審查程式碼品質、安全性與可維護性。在撰寫或修改程式碼後應立即使用。所有程式碼變更皆必須使用。
e2e-runner
model: sonnet
端對端測試專家,優先使用 Vercel Agent Browser,備援使用 Playwright。主動建立、維護與執行 E2E 測試。管理測試流程、隔離不穩定測試、上傳產出物(截圖、影片、追蹤紀錄),確保關鍵使用者流程正確運作。
refactor-cleaner
model: sonnet
死碼清理與程式碼整合專家。主動用於移除未使用的程式碼、重複項目與重構。執行分析工具(knip、depcheck、ts-prune)識別死碼並安全移除。

Plugins (4)

everything-claude-code@everything-claude-codeexample-skills@anthropic-agent-skillstypescript-lsp@claude-plugins-officialswift-lsp@claude-plugins-official

Similar rigs

copied ✓