golden-principles
Scans and enforces organizational golden principles within a repository.
Install
mkdir -p .claude/skills/golden-principles && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14603" && unzip -o skill.zip -d .claude/skills/golden-principles && rm skill.zipInstalls to .claude/skills/golden-principles
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Scan repository for golden principle violations with agent-readable remediation. Enforces GP-001 through GP-008 from .agents/governance/golden-principles.md. Use when auditing compliance, preparing PRs, or running garbage collection scans.Key capabilities
- →Scan the repository for violations of golden principles GP-001 through GP-008.
- →Produce remediation instructions for identified violations.
- →Scope scans to the entire repository, specific directories, or PR diffs.
- →Run specific rules only, such as `script-language` or `skill-frontmatter`.
- →Output results in JSON format for tooling integration.
How it works
The skill executes a Python script to scan specified targets for violations of predefined golden principles and generates remediation advice.
Inputs & outputs
When to use golden-principles
- →Auditing principle compliance
- →Preparing code for PR submission
- →Garbage collection scans
About golden-principles
Performs mechanical scans of the codebase to identify violations of predefined golden principles and provides actionable remediation paths.
Scan repository for golden principle violations with agent-readable remediation. Enforces GP-001 through GP-008 from .agents/governance/golden-principles.md. Use when auditing compliance, preparing PRs, or running garbage collection scans.
When not to use it
- →When checking code-level invariants only like file size or naming.
- →When grading domains across architectural layers.
- →When producing quality trend reports.
Limitations
- →The skill enforces GP-001 through GP-008 as defined in `.agents/governance/golden-principles.md`.
- →The skill requires a Python script to run the scan.
- →The skill can be suppressed for specific rules via file header comments.
How it compares
This workflow mechanically enforces specific golden principles and provides agent-readable remediation, unlike general linting or quality grading tools.
Compared to similar skills
golden-principles side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| golden-principles (this skill) | 0 | 4mo | Review | Intermediate |
| pair-capability-verify-adoption | 0 | 8mo | No flags | Intermediate |
| harness-boundary | 0 | 6mo | No flags | Advanced |
| adversarial-review | 0 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by rjmurillo
View all by rjmurillo →You might also like
pair-capability-verify-adoption
foomakers
Checks code and configuration against project adoption files for a given scope. Detection-only: returns conformity/non-conformity list per area without resolving issues. Caller decides resolution. Invocable independently or composed by /pair-process-review and /pair-process-implement.
harness-boundary
zkp442910864
Harness 工程边界约束与变更评估。Use when: 评估代码变更影响范围、确认安全边界、检查工程规范合规性、审查变更风险等级。
adversarial-review
dahatake
>
beforemerge-fullstack-architecture-review
adrian-coronel
Code review rules for DRY/SOLID layered architecture in fullstack TypeScript applications. Covers dependency direction, service/repository patterns, factory injection, domain entities, security hardening, performance optimization, and code quality patterns. Use this skill when reviewing, writing, or
agent-v3-security-architect
ruvnet
Agent skill for v3-security-architect - invoke with $agent-v3-security-architect
ai-spec-review
jyjeanne
Review a markdown specification across business logic, architecture, performance, security, testing, DevOps/CI/CD, dependencies, standards, UX, documentation, code quality, and maintainability. Generates a structured review, risk register, test plan, implementation tasks, and dimension scores (0–10)