分析报告结构
SkillDatabases & dataWrite decision-oriented analysis reports. Answers first, evidence-backed, open items kept close to conclusions. Provides three structure templates: executive summary, KPI reporting, and in-depth analysis. Trigger scenarios: writing analysis reports, preparing presentation materials, outputting insig
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the 分析报告结构 skill
What this skill tells your AI
The instructions your AI receives, as published by rongxinzy/rongxinai in SKILLs/zhiyuan-expert-manager/presets/data-analyst/skills/analytics-report/SKILL.md and read by ahel’s review.
目标
把分析结果组织成决策者可行动的报告:先给答案,再给证据,最后给不确定性。
核心原则
- 答案先行:开篇即结论,不在开头堆方法
- 证据就近:每个数字紧跟来源、口径与期间
- 假设显式:区分已验证结论、合理推断与未验证假设
- 数字可读:业务口径(
899k (+8% 周环比)),原始数值附上下文(占总量比、对比基线、历史区间)
报告模板
执行摘要(管理层)
**Primary Insight**: [最重要发现 + 量化影响]
**Key Evidence**: [2-3 个支撑数据点]
**Confidence**: [高/中/低 + 理由]
**Recommended Action**: [做什么、预期收益、时间线]
**Open Questions**: [哪些待验证]
KPI 汇报(周报/月报)
**Status**: [达成 / 有风险 / 落后]
**Current vs Target**: [当前值 vs 目标值(+/-X%,进度口径)]
**Driver**: [驱动表现的主因]
**Implication**: [团队该做什么]
深度分析(技术读者)
- 结论与建议
- 方法与口径(可复现:SQL/Python 逻辑)
- 证据与分析过程
- 敏感性与局限性
- 附录(明细数据、图表)
可视化规范
- 图表服务于分析问题:趋势用折线、构成用堆叠、分布用直方/箱线、对比用条形
- 一图一结论:标题即结论,读者 5 秒内可读
- 配色克制、灰阶可读、标签不重叠
- 使用
code-to-chart生成图表并自检:形式与对比匹配、数据与结论一致
交付规范
- 报告文件落盘后用
declare_artifact声明(role: deliverable) - HTML 报告自包含可离线打开;Markdown 报告结构清晰
- 结尾列出未决问题与提升置信度的下一步
Signals
- GitHub stars
- 151
- Forks
- 3
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
analytics-report- Source
- github.com/rongxinzy/rongxinai