Token导航 LogoToken导航TokenDH.com
开发敏感数据github未标认证来源可访问clear审计提醒

nathan-standards内森标准

Agent Skill

nathan-standards 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

489

周安装

21

GitHub Stars

4

下载量

171
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:nathan-standards(内森标准)
来源仓库:https://github.com/89jobrien/steve
仓库路径:skills/nathan-standards
安装命令:
npx skills add https://github.com/89jobrien/steve --skill nathan-standards
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/89jobrien/steve --skill nathan-standards

简介

用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,支持多宿主环境集成。

  • 帮助 Agent 围绕仓库状态、代码变更或协作事项进行整理,提升开发流程透明度。
  • 通过 npx 安装,需确认权限范围和维护状态,注意潜在的文件读写或命令执行风险。
  • 建议结合来源仓库和原始 README 进一步核验功能细节与使用场景。
  • nathan-standards 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Nathan Development Standards

Standards and patterns for developing within the Nathan project - an n8n-Jira agent automation system.

When to Use

Invoke this skill when:

  • Creating or modifying n8n workflow JSON files
  • Writing Python code for the Nathan helpers or templating modules
  • Designing webhook command contracts
  • Building workflow registry configurations
  • Implementing spec-driven features via agent-os

Project Architecture

Nathan follows a layered architecture:

External Service (Jira) <-- n8n Workflows <-- Python Agent Service
                             (credentials)      (webhook calls)

Core Principle: n8n owns all external credentials. Python services call n8n webhooks with shared secret authentication.

n8n Workflow Standards

For detailed workflow patterns, load references/n8n-workflow-patterns.md.

Standard Workflow Structure

Every webhook workflow must follow this pattern:

Webhook --> Validate Secret --> Operation --> Respond to Webhook
               |                   |              |
               v                   v              v
           Unauthorized       Error Response   Success Response
           Response (401)     (500)            (200)

Required Node Pattern

{
  "id": "validate-secret",
  "name": "Validate Secret",
  "type": "n8n-nodes-base.if",
  "typeVersion": 2,
  "parameters": {
    "conditions": {
      "conditions": [{
        "leftValue": "={{ $json.headers['x-n8n-secret'] }}",
        "rightValue": "={{ $env.N8N_WEBHOOK_SECRET }}",
        "operator": { "type": "string", "operation": "equals" }
      }]
    }
  }
}

Response Format

All responses must follow this shape:

{ "success": true, "data": {...}, "status_code": 200, "error": null }
{ "success": false, "data": {}, "status_code": 500, "error": "message" }

JQL Expression Escaping

In n8n expressions within JSON, escape properly:

WrongCorrect
.map(x => "${x}").map(x => '"' + x + '"')
.join('\n').join('\\n')
.replaceAll('\n', ' ').replaceAll('\\n', ' ')

Python Standards

For detailed patterns, load references/python-patterns.md.

Module Structure

nathan/
  helpers/           # Shared utilities (workflow registry, etc.)
  workflows/         # n8n workflow JSON + registry.yaml per category
  templating/        # YAML-to-JSON template engine
  scripts/           # Standalone runnable scripts

Code Style

# Required imports pattern
from __future__ import annotations
from typing import Any
from pathlib import Path
import logging

logger = logging.getLogger(__name__)

# Type hints required, use T | None not Optional[T]
async def trigger_workflow(url: str, params: dict[str, Any]) -> dict[str, Any]:
    ...

Registry Pattern

# registry.yaml
version: "1.0.0"
description: "Registry description"

commands:
  command_name:
    endpoint: /webhook/endpoint-path
    method: POST
    required_params:
      - param1
    optional_params:
      - param2
    description: What this command does
    example:
      param1: "value"

Spec-Driven Development

Use agent-os commands for feature development:

  1. /shape-spec - Initialize and shape specification
  2. /write-spec - Write detailed spec document
  3. /create-tasks - Generate task list from spec
  4. /orchestrate-tasks - Delegate to subagents

Specs live in agent-os/specs/[spec-name]/ with:

  • spec.md - Feature specification
  • tasks.md - Implementation tasks with checkboxes
  • orchestration.yml - Subagent delegation config

Quick Reference

Common Commands

uv sync                              # Install dependencies
uv run pytest                        # Run tests
uv run pytest path/to/test.py -v     # Single test file
uvx ruff check .                     # Lint
uvx ruff format .                    # Format
docker compose -f docker-compose.n8n.yml up -d  # Start n8n

Environment Variables

VariablePurpose
N8N_WEBHOOK_SECRETShared secret for webhook auth
N8N_API_KEYn8n Public API key
JIRA_DOMAINJira Cloud domain
JIRA_EMAILJira account email
JIRA_API_TOKENJira API token

File Naming Conventions

TypeConventionExample
Workflow JSONkebab-case.jsonjira-get-ticket.json
Python modulessnake_case.pyn8n_workflow_registry.py
Test filestest_*.pytest_parser.py
Registryregistry.yamlper workflow category

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

29.59%
按下载量换算51

OpenCode

22.09%
按下载量换算38

Antigravity

19.08%
按下载量换算33

windsurf

12.17%
按下载量换算21

Codex

9.32%
按下载量换算16

Gemini CLI

3.49%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills