agentrigs
+ submit rig
~ / rigs / keez97 / claude-architecture-skills

keez97/claude-architecture-skills

7 Claude Code skills for software architecture review (Python, web, cloud, microservices). Includes A/B benchmarks against unskilled baseline, assertion-graded eval suite, and interactive dashboards.

↗ GitHub ★ 9 MIT updated 5mo ago collection Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~94 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 keez97/claude-architecture-skills/skills ./rig-claude-architecture-skills/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 keez97/claude-architecture-skills/skills/architecture-workflow .claude/skills/architecture-workflow
$ npx degit keez97/claude-architecture-skills/skills/cloud-infrastructure .claude/skills/cloud-infrastructure
$ npx degit keez97/claude-architecture-skills/skills/describe-design .claude/skills/describe-design
$ npx degit keez97/claude-architecture-skills/skills/microservices-architect .claude/skills/microservices-architect
$ npx degit keez97/claude-architecture-skills/skills/modern-web-app-architecture .claude/skills/modern-web-app-architecture
$ npx degit keez97/claude-architecture-skills/skills/python-architecture-review .claude/skills/python-architecture-review
$ npx degit keez97/claude-architecture-skills/skills/software-architecture .claude/skills/software-architecture

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 (7)

architecture-workflowcloud-infrastructuredescribe-designmicroservices-architectmodern-web-app-architecturepython-architecture-reviewsoftware-architecture

Similar rigs

Muratovnik/assay
Evidence-grounded methods for coding agents: skills and agent profiles for Claude Code, Codex, Cursor and Gemini CLI
★ 0 project Claude CodeCodexGemini CLI 14 skills 6d ago
Skill Collector 2.8k tok ·
tractorjuice/arc-kit
The Enterprise Architecture Governance Harness — strategy, architecture, delivery, and assurance using AI coding assistants
★ 2,252 project Claude CodeCodexGemini CLI 7 mcp 12 skills 1d ago
MCP Hoarder 27.5k tok ·
NAZCAMEDIA/claude-code-config
—
★ 1 setup Claude CodeCodex 23 skills 8mo ago
Skill Collector 7.4k tok ·
sabahattink/antigravity-fullstack-hq
Tool-agnostic, permission-first AI engineering configuration kit for Claude Code, Google Antigravity IDE, and OpenAI Codex.
★ 30 project Claude CodeCodexGemini CLI 28 skills 22d ago
Skill Collector 4.2k tok ·
copied ✓