golden-principles — agentic-ai golden-principles, ai-agents, community, agentic-ai, ide skills, ai-assistant, anthropic-claude, claude-code, code-generation, code-review, Claude Code

v1.0.0
GitHub

关于此技能

Perfect for Code Analysis Agents needing automated golden principle compliance scans and remediation instructions. Multi-agent system for software development

# 核心主题

agentic-ai ai-agents ai-assistant anthropic-claude claude-code code-generation
rjmurillo rjmurillo
[15]
[4]
更新于: 3/31/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 9/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
9/11
Quality Score
60
Canonical Locale
en
Detected Body Locale
en

Perfect for Code Analysis Agents needing automated golden principle compliance scans and remediation instructions. Multi-agent system for software development

核心价值

Empowers agents to enforce mechanically enforced golden principles directly into the repository, utilizing Python scripts and JSON output for tooling, and providing remediation instructions for violations of rules such as script-language, skill-frontmatter, and yaml-logic.

适用 Agent 类型

Perfect for Code Analysis Agents needing automated golden principle compliance scans and remediation instructions.

↓ 赋予的主要能力 · golden-principles

Automating periodic garbage collection scans for repository compliance
Debugging golden principle violations in specific directories or files
Generating JSON reports for tooling and auditing purposes

! 使用限制与门槛

  • Requires Python 3 execution environment
  • Limited to scanning repositories for specific golden principle rules
  • Needs write access to the repository for remediation instructions

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致，便于搜索引擎理解页面内容。

? FAQ

golden-principles 是什么？

Perfect for Code Analysis Agents needing automated golden principle compliance scans and remediation instructions. Multi-agent system for software development

如何安装 golden-principles？

运行命令：npx killer-skills add rjmurillo/ai-agents/golden-principles。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

golden-principles 适用于哪些场景？

典型场景包括：Automating periodic garbage collection scans for repository compliance、Debugging golden principle violations in specific directories or files、Generating JSON reports for tooling and auditing purposes。

golden-principles 支持哪些 IDE 或 Agent？

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

golden-principles 有哪些限制？

Requires Python 3 execution environment；Limited to scanning repositories for specific golden principle rules；Needs write access to the repository for remediation instructions。

↓ 安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行：npx killer-skills add rjmurillo/ai-agents/golden-principles。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    golden-principles 已启用，可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考，但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论，再决定是否继续查看上游仓库说明。

Imported Repository Instructions

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

Supporting Evidence

golden-principles

安装 golden-principles，这是一款面向AI agent workflows and automation的 AI Agent Skill。支持 Claude Code、Cursor、Windsurf，一键安装。

SKILL.md
Readonly
Imported Repository Instructions
The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.
Supporting Evidence

Golden Principles

Scan the repository for violations of mechanically enforced golden principles. Produces remediation instructions that agents can act on directly.

Inspired by OpenAI Harness Engineering:

"We started encoding what we call 'golden principles' directly into the repository and built a recurring cleanup process."

Triggers

Trigger PhraseOperation
scan golden principlesFull principle compliance scan
check principle complianceScan with summary report
golden principle violationsScan and list violations
run garbage collectionDeep scan with fix-up recommendations
audit principlesScan specific rules only

When to Use

Use this skill when:

  • Preparing a PR for submission (catch violations early)
  • Running periodic garbage collection scans
  • Auditing a domain or directory for compliance
  • Adding new files to the repository

Use taste-lints instead when:

  • Checking code-level invariants only (file size, naming, complexity)
  • Running pre-commit checks on staged files

Use quality-grades instead when:

  • Grading domains across architectural layers
  • Producing quality trend reports

Process

  1. Run python3 .claude/skills/golden-principles/scripts/scan_principles.py with target
  2. Review AGENT_REMEDIATION blocks in output
  3. Apply suggested fixes
  4. Re-run to confirm compliance

Usage

bash
1# Scan entire repository
2python3 .claude/skills/golden-principles/scripts/scan_principles.py
3
4# Scan specific directory
5python3 .claude/skills/golden-principles/scripts/scan_principles.py --directory .claude/skills/
6
7# Run specific rules only
8python3 .claude/skills/golden-principles/scripts/scan_principles.py --rules script-language,skill-frontmatter
9
10# JSON output for tooling
11python3 .claude/skills/golden-principles/scripts/scan_principles.py --format json
12
13# Write results to file
14python3 .claude/skills/golden-principles/scripts/scan_principles.py --output scan-results.json --format json

Rules

RulePrincipleWhat it checks
script-languageGP-001No new .sh/.bash files
skill-frontmatterGP-003SKILL.md has required frontmatter fields
agent-definitionGP-004Agent .md files have required sections
yaml-logicGP-005No inline logic in workflow YAML
actions-pinnedGP-006GitHub Actions pinned to SHA

GP-002, GP-007, GP-008 are enforced by existing tools (git hooks, taste-lints).

Exit Codes

CodeMeaning
0No violations found
1Script error (bad arguments, file not found)
10Violations detected

Suppression

Add a comment in the file header to suppress a specific rule:

python
1# golden-principle: ignore script-language

Valid rules: script-language, skill-frontmatter, agent-definition, yaml-logic, actions-pinned

Verification

After execution:

  • Report lists scanned file count
  • Each violation includes principle ID and remediation
  • Exit code matches violation state
  • Output format matches --format flag

Cross-References

相关技能

寻找 golden-principles 的替代方案 (Alternative) 或可搭配使用的同类 community Skill？探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

React 框架

★ 138.4k
⑂ 0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

★ 98.6k
⑂ 0
开发者工具