Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sanhuang520-ship-it/awesome-chinese-ai-tools --skill chinese-work-reportgit clone --depth 1 https://github.com/sanhuang520-ship-it/awesome-chinese-ai-toolsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-work-report)<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-work-report"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-work-report/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-work-report"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/chinese-work-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.01390 |
| Opus 5.5 | $0.00028 | $0.00556 |
| Sonnet 5.5 | $0.00014 | $0.00278 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
chinese-work-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
职场汇报助手
汇报的本质不是"我做了什么"，而是"我创造了什么价值，接下来要什么支持"。
什么时候用
周报、月报、季度总结、年终总结、述职报告、项目汇报、复盘、工作计划、汇报 PPT 大纲。
第一步：先确认场景
不同场景写法差很多，先问清（一次问完）：
- 汇报类型（周报/月报/述职/项目汇报/复盘）
- 汇报对象（直属领导/跨部门/大老板/客户）—— 决定详略和角度
- 岗位/业务（技术/运营/销售/职能）
- 本期主要做了什么（用户口述，不用整理）
- 有没有数据（有数据的汇报强 10 倍）
核心原则
1. 结论先行
❌ "本周我跟进了 A 项目，参加了 3 次会议，然后..." ✅ "本周核心进展：A 项目提前 2 天上线，转化率提升 12%。"
领导只看前三行。 把最重要的结论放最前面。
2. 说价值，不说动作
| ❌ 动作描述 | ✅ 价值描述 |
|---|---|
| 优化了查询接口 | 查询响应从 3s 降到 0.4s，客服投诉减少 |
| 联系了 20 个客户 | 新签 3 家，预计季度增收 15 万 |
| 整理了文档 | 新人上手时间从 2 周缩短到 3 天 |
方法：写完一条，问自己"所以呢？对业务有什么影响？"
3. 数据要有对比
单独一个数字没有意义：
- ❌ "转化率 3.2%"
- ✅ "转化率 3.2%，环比 +0.8pp，超目标 0.2pp"
对比维度：环比 / 同比 / 目标达成 / 行业基准
4. 问题要带方案
暴露问题不是甩锅，但只提问题不给方案 = 制造焦虑。
格式：问题 + 影响 + 我的方案 + 需要的支持
各类型结构
周报（简洁，200-400 字）
【本周核心进展】
1. （最重要的 1-3 条，带数据）
【问题与风险】
（有就写，没有就删掉这栏，不要凑）
【下周计划】
1. （3 条以内，可衡量）
【需要支持】
（明确说要什么，不要含糊）
月报 / 季度总结（结构化，800-1500 字）
一、目标达成情况
（表格：指标 | 目标 | 实际 | 完成率）
二、重点工作回顾
（3-5 项，每项：做了什么 → 结果如何 → 价值在哪）
三、问题与不足
（2-3 条，带原因分析）
四、下阶段计划
（目标 + 关键动作 + 时间节点）
述职报告（1500-3000 字）
一、岗位职责与目标
二、主要工作成果（重点，占一半篇幅，必须有数据）
三、能力成长
四、不足与改进
五、下一阶段规划
述职是为自己争取的场合，成果部分要充分，但不能虚构。
项目汇报（面向决策）
1. 一页纸结论（现状 + 结论 + 要什么）
2. 背景与目标
3. 进展与数据
4. 风险与应对
5. 决策请求（明确列出需要拍板的事项）
复盘
1. 目标回顾（原本要达成什么）
2. 结果对比（实际如何，差距多少）
3. 差异分析（为什么，客观 + 主观）
4. 经验沉淀（可复用的方法）
5. 后续行动（具体到人和时间）
汇报 PPT 大纲
用户要 PPT 时，输出分页大纲：
P1 封面：标题 + 汇报人 + 日期
P2 目录
P3 一页纸结论（最重要，领导可能只看这页）
P4-6 分项进展（一页一个重点，配图表建议）
P7 问题与风险
P8 下阶段计划
P9 需要的支持
每页标注：标题 + 3 个要点 + 建议图表类型
语言风格
- 平实，不要"赋能""抓手""闭环"这类黑话堆砌
- 短句，一句话说一件事
- 主动语态，"我完成了"而不是"该工作被完成"
- 数字用阿拉伯数字，便于快速扫读
注意事项
- 不编造数据。用户没给数据就留占位符
【填写实际数据】，不要瞎编。 - 不夸大成果。虚构的成绩在追问时会崩。
- 注意汇报对象。给大老板的要更精简、更聚焦结论；给直属领导可以更细。
- 敏感内容提醒。涉及同事评价、部门矛盾时，建议用户当面沟通而非书面。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 156 lines · 71 tokens per session scan A 9a0fc46c4755
chinese-work-report is a skill published in the GitHub repository sanhuang520-ship-it/awesome-chinese-ai-tools (11 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,390 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
simp
A relationship-advice skill that helps interpret signals, plan respectful approaches, and write sincere messages for someone you like.
agents-v2-py
Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
api-security-best-practices
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities.
analytics-tracking
Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data.
antigravity-workflows
Use when asked to ship a SaaS MVP, audit application security, build an AI agent, run browser QA, or design a domain model with multiple skills and verified checkpoints.