reeschan/atelier
開発を 9 工程のワークフローテンプレートとして回す Claude Code スキル (旧 pbi-orchestration-jev)。複数ファイルの実装を PBI に分け、判定表と Jev でモデルを選んでサブエージェントに振り分け、検証コマンドで合否を決める / Claude Code skill that runs development as a nine-stage workflow template: splits multi-file work into PB
stack: Python
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code
$ npx degit reeschan/atelier/skills ./rig-atelier/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 reeschan/atelier/skills/atelier .claude/skills/atelier $ npx degit reeschan/atelier/skills/harness-log .claude/skills/harness-log $ npx degit reeschan/atelier/skills/pbi-orchestration-jev .claude/skills/pbi-orchestration-jev $ npx degit reeschan/atelier/skills/ui-video .claude/skills/ui-video
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 (4)
Similar rigs
Wexop/atelier
Procedural image studio driven by short Python scripts, built for LLMs (no generative AI)
Minimalist 842 tok · · Q0
ksprashu/agent-skill-forge
Curated, unified monorepo of high-performance skills for Google Antigravity, Claude Code, Gemini CLI, and agentic AI coding assistants.
Skill Collector 2.7k tok · · Q20
mhxie/Atelier
AI-native personal operating system
Orchestrator 4.8k tok · · Q18
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Minimalist 723 tok · · Q3