redhoram/claude-landing-template
Reusable Claude Code agent framework for landing pages & simple apps — visual-loop /craft + /polish: designer, builder, qa.
field: Developer tools workflow: Frontend & designPlanning & specsTesting & TDDSecurity reviewCI/CD & deploy
stack: Python
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 redhoram/claude-landing-template/.claude ./rig-claude-landing-template # 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 redhoram/claude-landing-template/.claude/skills/antislop-human .claude/skills/antislop-human $ npx degit redhoram/claude-landing-template/.claude/skills/antislop-layoutmobile .claude/skills/antislop-layoutmobile $ npx degit redhoram/claude-landing-template/.claude/skills/antislop-ui .claude/skills/antislop-ui $ npx degit redhoram/claude-landing-template/.claude/skills/antislop .claude/skills/antislop $ npx degit redhoram/claude-landing-template/.claude/skills/conversion-copy .claude/skills/conversion-copy $ npx degit redhoram/claude-landing-template/.claude/skills/humanizer .claude/skills/humanizer $ npx degit redhoram/claude-landing-template/.claude/skills/premium-design .claude/skills/premium-design $ npx degit redhoram/claude-landing-template/.claude/skills/seo-content-strategist .claude/skills/seo-content-strategist $ npx degit redhoram/claude-landing-template/.claude/skills/ux-research .claude/skills/ux-research $ npx degit redhoram/claude-landing-template/.claude/skills/web-quality .claude/skills/web-quality
$ curl -fsSL --create-dirs -o .claude/agents/composer.md https://raw.githubusercontent.com/redhoram/claude-landing-template/main/.claude/agents/composer.md $ curl -fsSL --create-dirs -o .claude/agents/copywriter.md https://raw.githubusercontent.com/redhoram/claude-landing-template/main/.claude/agents/copywriter.md $ curl -fsSL --create-dirs -o .claude/agents/curator.md https://raw.githubusercontent.com/redhoram/claude-landing-template/main/.claude/agents/curator.md $ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/redhoram/claude-landing-template/main/.claude/agents/developer.md $ curl -fsSL --create-dirs -o .claude/agents/inspector.md https://raw.githubusercontent.com/redhoram/claude-landing-template/main/.claude/agents/inspector.md $ curl -fsSL --create-dirs -o .claude/agents/optimizer.md https://raw.githubusercontent.com/redhoram/claude-landing-template/main/.claude/agents/optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/redhoram/claude-landing-template/main/.claude/agents/qa.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 (10)
antislop-humanantislop-layoutmobileantislop-uiantislopconversion-copyhumanizerpremium-designseo-content-strategistux-researchweb-quality
Subagents (7)
| composer model: opus | Produces a design spec for a page/section before coding. The core of this framework, use for anything with a UI surface. |
| copywriter model: opus | Turns the page/section request into a message strategy + exact copy BEFORE any design work. Runs first in /craft, the copy decides the layout, not the other way around. |
| curator model: opus | Sets the project's brand system once (visual reference, palette with contrast rules, typography, section rhythm, motion, icons, voice) and writes it to .craft/brand.md. Runs first in /craft only when |
| developer model: opus | Implements the design spec into clean code. Use once .craft/design.md exists. |
| inspector model: opus | Gives the final verdict on a finished /craft run (SHIP, REVISE, or HOLD) by judging the build against the brief, the brand, and the copy's promise, using the QA report, the screenshots, and the main s |
| optimizer model: sonnet | Plans SEO for one page before any copy is written (primary keyword and search intent, heading outline, title, meta description, JSON-LD, internal links, image alt text) into .craft/seo.md, or audits a |
| qa model: sonnet | Visual and UX quality check after the build (a11y, responsive, cleanliness, performance, SEO), including headless screenshots it looks at itself. Use after the build in /craft; the inspector gives the |
Slash commands (4)
/brand/craft/polish/seo-audit
Similar rigs
redhoram/claude-pipeline-template
Reusable Claude Code agent framework for complex CRUD apps — /ship pipeline: planner, designer, coder, tester, reviewer.
Orchestrator 3.9k tok · · Q10
miqdadbadjuber/anti-slop
Rules for an AI coding agent to filter out generic AI-generated UI designs, text, and code.
Pragmatist 258 tok · · Q0
xazaj/sdlc-playbook
Decision playbooks for coding agents — 给 coding agent 的开发全链路决策手册。每个 SDLC 阶段一份选型矩阵:该装什么、用哪套设计系统、走 SDD 还是 TDD。
Pragmatist 1.5k tok · · Q0
vannt-dev/governed-agent-sdlc
Ship with agents. Keep humans in control. Cross-platform governance toolkit for AI coding agents.
Fort Knox 632 tok · · Q24