- 用户目标单一且明确 - 只缺某一类结果，例如补件清单、规则口径、复核意见 - 不需要重复汇总中间环节
Scanned 9/7/2026
Install to Claude Code
Skills Directorynpx -y skills add aifinlab/FinClaw --skill references --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of References?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/aifinlab-references-finclaw)More formats (shields.io, HTML) on the badges page.
# Workflow 与单项技能的区别
## 更适合单项技能的情况
- 用户目标单一且明确
- 只缺某一类结果，例如补件清单、规则口径、复核意见
- 不需要重复汇总中间环节
## 更适合 workflow skill 的情况
- 案件复杂，横跨多个分析环节
- 用户希望一次性得到综合结果
- 已有部分中间结果，需要统一收束
- 需要明确下一步路径而不是只要某一块输出Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.
