shimo4228/zenn-content
Bilingual (JA/EN) essay corpus on AI agent design, coding-agent workflows, and authorship under AI-mediated diffusion — the essay surface of a five-line research ecosystem. CC0; intrinsic priority claim via Software Heritage SWHID (CITATION
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit shimo4228/zenn-content/.claude ./rig-zenn-content # 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 shimo4228/zenn-content/.claude/skills/article-stocktake .claude/skills/article-stocktake $ npx degit shimo4228/zenn-content/.claude/skills/note-publishing .claude/skills/note-publishing $ npx degit shimo4228/zenn-content/.claude/skills/publish-article .claude/skills/publish-article $ npx degit shimo4228/zenn-content/.claude/skills/quality-gate .claude/skills/quality-gate $ npx degit shimo4228/zenn-content/.claude/skills/session-theme-mining .claude/skills/session-theme-mining $ npx degit shimo4228/zenn-content/.claude/skills/substack-publishing .claude/skills/substack-publishing $ npx degit shimo4228/zenn-content/.claude/skills/writing-ecosystem .claude/skills/writing-ecosystem $ npx degit shimo4228/zenn-content/.claude/skills/zenn-format .claude/skills/zenn-format
$ curl -fsSL --create-dirs -o .claude/agents/devto-translator.md https://raw.githubusercontent.com/shimo4228/zenn-content/main/.claude/agents/devto-translator.md $ curl -fsSL --create-dirs -o .claude/agents/editor.md https://raw.githubusercontent.com/shimo4228/zenn-content/main/.claude/agents/editor.md $ curl -fsSL --create-dirs -o .claude/agents/essay-reviewer.md https://raw.githubusercontent.com/shimo4228/zenn-content/main/.claude/agents/essay-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/fact-checker.md https://raw.githubusercontent.com/shimo4228/zenn-content/main/.claude/agents/fact-checker.md $ curl -fsSL --create-dirs -o .claude/agents/prose-clarity-reviewer.md https://raw.githubusercontent.com/shimo4228/zenn-content/main/.claude/agents/prose-clarity-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/theme-reviewer.md https://raw.githubusercontent.com/shimo4228/zenn-content/main/.claude/agents/theme-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/title-reviewer.md https://raw.githubusercontent.com/shimo4228/zenn-content/main/.claude/agents/title-reviewer.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 (8)
article-stocktakenote-publishingpublish-articlequality-gatesession-theme-miningsubstack-publishingwriting-ecosystemzenn-format
Subagents (7)
| devto-translator model: opus | JP記事をprose-translationでEN化し、Dev.to固有のtags・links・cover・schedule.jsonへ変換してEN稿を生成するproject agent。Use when — Zenn原稿の英訳とDev.to crosspost準備を行うとき。NOT for — 投稿・予約、quality-gate、翻訳方法論、Zenn公開、既存Dev.to記事の更新。 |
| editor model: fable | Strict article editor for practical publishing channels. Judges whether the argument moves — narrative flow, one discovery per section, claim-before-evidence order, explanation quality, AI slop, audie |
| essay-reviewer model: fable | Strict essay editor for essay publishing channels; which channel routes here is defined by the project's rules channel table, not by article type. Reviews essays that mix social theory, organizational |
| fact-checker model: sonnet | Fact verification specialist for articles. Extracts verifiable factual claims, verifies them against web sources and against the local records named in the dispatch prompt (code, paths, outputs, evide |
| prose-clarity-reviewer model: opus | First-contact reader clarity reviewer for human-primary articles, essays, blog posts, and newsletters. Reads once as the audience declared by the project's publication channel contract and flags first |
| theme-reviewer model: fable | 人間向け記事・エッセイの執筆前テーマレビュアー。選択済みの問い一文と素材を fresh context で読み、非自明性・一次アクセス・読者接続・外部言説との差分を点検して findings と深化の問いだけを返す。Use when the piece claims novelty against external discourse and the author asks for it (opt |
| title-reviewer model: opus | 凍結した人間向け原稿のタイトルレビュアー。headline-craft の候補と現行タイトルを fresh context で読み、中心命題との軸一致・誠実さ・具体性・好奇心の回収・前提への問い・直近の題との見分け・channel 制約を点検して findings だけを返す。Use after 著者の内容 GO と headline-craft の候補生成、quality-gate の前、/ti |
Similar rigs
RapierCraftStudios/ForgeDock
ForgeDock — autonomous AI dev pipeline for Claude Code. GitHub as agent memory: issue in, PR out.
Minimalist 724 tok ·
illusionaireal/oh-my-patent
🏛️ The patent plugin for AI coding agents — turn technical ideas into patent disclosures with Claude Code, Codex, and OpenCode.
Pragmatist 2.4k tok ·
Sunnydalelow/ai-content-automation
AI-powered content automation for marketing teams using Claude Code. 14 slash commands, 8 agent personas, templates, workflows, and brand guidelines.
Orchestrator 926 tok ·
kremserw/KWproject_template
Reusable, self-instantiating knowledge-work project template for Claude Code (agents, skills, hooks, KB conventions + /setup-project first-run bootstrap)
Orchestrator 3.2k tok ·