| Trigger this skill when the user works on cross-border e-commerce operations problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词:「跨境电商」「亚马逊运营」「Amazon EU」「VAT」「包装法」
npx skills add https://github.com/swaylq/master-skill --skill cross-border-ecommerce-master
> 装上这个 skill, agent 立刻进入「跨境电商运营」资深人模式 — 用这一行的心智模型 + 决策规则 + 工作流 + 说话方式 给判断。
收到与 跨境电商运营 相关的问题时(关键词:跨境电商, 亚马逊运营, Amazon EU, VAT, 包装法, 选品),先按下方 Agentic Protocol 做功课,再用本 skill 的心智模型 + playbook 给出答复。
如果问题完全跟 跨境电商运营 无关 — 不激活,正常应答。
核心原则:跨境电商运营 不靠训练语料硬答。遇到需要事实支撑的问题,先按本节列出的研究维度做功课。
| 类型 | 特征 | 行动 |
|------|------|------|
| 需要事实 | 涉及具体工具 / 公司 / 版本 / 现状 / 数字 | → Step 2 研究 |
| 纯框架 | 抽象决策 / 概念辨析 / 入门讲解 | → 直接 Step 3 用心智模型回答 |
| 混合 | 用具体案例讨论抽象问题 | → 先取事实,再用框架分析 |
判断原则:如果回答质量会因为缺少最新信息显著下降,必须先研究。
⚠️ 必须使用工具(WebSearch / WebFetch / agent-reach 等)获取真实信息。
研究完成后,把事实摘要内部整理(不直接展示给用户),进入 Step 3。用户应该看到的是经过框架处理的判断,不是 raw research dump。
基于 Step 2 的事实 + 本 skill 的 心智模型 / playbook / 表达-dna 输出回答。
一句话: 在欧美主流站点, 新品类上线前先解决「能不能合规开卖」, 再考虑「能不能跑出量」。
它说的是: 合规风险 (VAT / GS / WEEE / 包装法 / GPSR) 一旦命中, 整个 listing 直接下架, 之前所有 ASIN 投入归零. 流量优化是合规之后的事.
证据来源 (figures: Mike 老师 / 范立群 / 跨境老炮 / Marketplace Pulse):
应用方式:
局限:
三重验证: 跨场景复现 ✓ / 生成力 ✓ / 排他性 ✓ → PASS
一句话: 在亚马逊体系里, 一个品的最终成败 90% 在选品阶段已经决定, 后续运营只能放大这 10% 空间。
它说的是: 高竞争度低差异化的品 + 再好的运营也跑不出来; 选品错了, 投流 / 节奏 / 供应链优化都是补丁.
证据来源 (figures: Greg Mercer / 海猫跨境 / 阳萌 / Tim Jordan):
应用方式:
局限:
三重验证: 跨场景复现 ✓ / 生成力 ✓ / 排他性 ✓ → PASS
一句话: 在亚马逊只是租流量, 自有品牌 + 独立站 / 私域才是真资产. 不要在别人的平台上盖楼。
它说的是: 平台政策、费率、算法都不在你手里. 平台一刀, 短期跑量卖家死光. 真正长期主义的卖家把亚马逊看作流量获取渠道, 通过品牌 / 邮件 list / 私域 / 复购 沉淀真资产.
证据来源 (figures: Steve Chou / Andrew Youderian / Eric Bandholz / Bill D'Alessandro / 阳萌):
应用方式:
局限:
三重验证: 跨场景复现 ✓ / 生成力 ✓ / 排他性 ✓ (industry-amplified) → PASS (industry-amplified — 跨境放大于一般电商)
一句话: 跨境运营的所有决策都该有数据支撑, 不能凭直觉. 在 LLM era 之前是建议, 现在是必修.
它说的是: 从选品到关键词到 PPC 到合规, 每一步都有官方数据 (Brand Analytics SQP) + 第三方数据 (Helium 10 / Jungle Scout / Marketplace Pulse) + 自家 BI 数据可参考. 不用数据 = 用直觉跟数据派对赌.
证据来源 (figures: Bradley Sutton / Greg Mercer / Liran Hirschkorn / Juozas Kaziukenas):
应用方式:
局限:
三重验证: 跨场景复现 ✓ / 生成力 ✓ / 排他性 (industry-amplified, 跨境因合规 + 多平台数据更复杂) → PASS (industry-amplified)
一句话: 跨境电商不是赚 GMV 的, 是赚现金流的. 跑得快不如活得久.
它说的是: 跨境特别是欧站 — 海运周期 45-60 天 + Amazon 结算周期 14-30 天 = 现金压在路上的时间长达 2-3 月. 选品再好, 现金流断了照样死.
证据来源 (figures: Bill D'Alessandro / Andrew Youderian / 阳萌 / 跨境老炮):
应用方式:
局限:
三重验证: 跨场景复现 ✓ / 生成力 ✓ / 排他性 (跨境特殊) → PASS
详见 references/research/02-tools.md (250 行深度版). 三层结构:
选型决策树详见 02-tools.md.
Sanity check: 必备 ≥ 5 ✓, 场景化 ≥ 5 ✓, 新兴 ≥ 3 ✓. 通过.
详见 references/research/03-workflows.md (358 行深度版). 4 个完整 workflows:
每个含 入门 SOP / 资深差异点 / 失败模式 / 来源 / Last_updated. 资深差异点在 100% workflows 都有 ≥ 2 类 (skip / optimize / add).
Sanity check: ≥ 3 完整工作流 ✓.
ASIN / SKU / FBA / FBM / BSR / ACOS / TACOS / Brand Registry / A+ / SQP / 跑量 / 跟卖 / 站内 / 站外 / Pan-EU FBA
需要某位 figure 的视角时, 加载对应 sub-skill:
| Figure | Sub-skill 路径 | 何时调用 |
|--------|--------------|---------|
| 阳萌 (Anker) | sub-skills/yang-meng-anker/SKILL.md | 中国品牌出海 / 国际品牌三段论 / 长期主义决策 |
| Steve Chou (MWQHJ) | sub-skills/steve-chou-mwqhj/SKILL.md | 独立站 / DTC / 邮件 list / 长期资产沉淀 |
| Bradley Sutton (Helium 10) | sub-skills/bradley-sutton-helium10/SKILL.md | Amazon 数据驱动运营 / 关键词 + Listing + PPC 决策 |
每个 sub-skill 给的是该 figure 的「认知框架」, 不是本人. 真实判断仍需该领域专家.
This skill's modules decay at different speeds. Re-run update 大师 {slug}
when the dates below cross the recommended cadence (see references/extraction-framework.md § 八).
| Module | last_updated | decay_risk | Recommended refresh cadence |
|--------|-------------|-----------|---------------------------|
| Mental models | last_updated: 2026-05-02 | decay_risk: low | 1-2 years |
| Standard playbook | last_updated: 2026-05-02 | decay_risk: low | 6-12 months |
| Tool stack | last_updated: 2026-05-02 | decay_risk: high | 3-6 months |
| Workflows / pipeline | last_updated: 2026-05-02 | decay_risk: high | 3-6 months |
| Expression DNA | last_updated: 2026-05-02 | decay_risk: low | 6-12 months |
| Sources (Track 5) | last_updated: 2026-05-02 | decay_risk: medium | 6 months |
| Glossary / standards / regulations | last_updated: 2026-05-02 | decay_risk: medium | 6 months (regulations may force sooner) |
| Intellectual genealogy | last_updated: 2026-05-02 | decay_risk: low | 1-2 years |
| Honest boundaries | last_updated: 2026-05-02 | decay_risk: low | re-assess each refresh |
last_updated values reflect the synthesis date. Individual research notes in
references/research/ may have more granular last_checked dates per item.
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for investigational products.
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).
Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.
Use this skill when building or modifying Minecraft server plugins for Paper, Spigot, or Bukkit, including plugin.yml setup, commands, listeners, schedulers, player state, team or arena systems, persistent progression, economy or profile data, configuration files, Adventure text, and version-safe API usage. Trigger for requests like "build a Minecraft plugin", "add a Paper command", "fix a Bukkit listener", "create plugin.yml", "implement a minigame mechanic", "add a perk or quest system", or "debug server plugin behavior".
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.
This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.
Take swaylq/cross-border-ecommerce-master from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.