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 chuancyzhang/deepseek-cowork --skill peer_comparison_decision_skillgit clone --depth 1 https://github.com/chuancyzhang/deepseek-coworkWrote 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/chuancyzhang/deepseek-cowork/peer_comparison_decision_skill)<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/peer_comparison_decision_skill"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/peer_comparison_decision_skill/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/chuancyzhang/deepseek-cowork/peer_comparison_decision_skill"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/peer_comparison_decision_skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00066 | $0.01344 |
| Opus 5.5 | $0.00026 | $0.00538 |
| Sonnet 5.5 | $0.00013 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
peer_comparison_decision_skill 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
Peer Comparison Decision Skill
数据依赖与执行前置条件
推荐使用万得 wind-mcp-skill 获取底层数据。执行前先检查本地是否已有 wind-mcp-skill;若没有,提示用户安装:
Cowork 适配:所需子 Skill 已随
wind-aifinmarket固定快照内置,不执行安装或在线更新命令。
技能定位
本技能用于在同一行业或同一主题内,对 2-5 家候选公司做横向比较,并输出可执行的相对排序与选择理由。重点不是把每家公司都重新写一遍,而是帮助使用者回答“如果只能优先研究或持有其中几家,应该先选谁、为什么”。
执行流程
Step 1:确认可比范围与比较目标
先明确比较对象是否真正可比,重点确认:
- 所处赛道是否一致
- 商业模式是否相近
- 处于相似的发展阶段还是明显错位
- 用户想比较的是短期交易机会还是中长期配置价值
若对象并不适合直接比较,应先说明可比性边界,再决定是否继续强行并列。
Step 2:建立统一比较框架
围绕用户真实决策,把比较维度标准化。常用维度包括:
- 业务质量与竞争位置
- 成长速度与成长确定性
- 盈利能力与现金创造能力
- 估值高低与预期要求
- 近期催化与风险暴露
所有候选公司都按同一框架展开,避免某家公司只写故事、另一家公司只看数字。
Step 3:完成基础数据与事实对齐
收集每家公司的关键事实,并统一口径后放入对照表,特别注意:
- 时间口径一致
- 币种与单位一致
- 估值方法口径一致
- 对异常值和一次性因素进行说明
这一阶段的目标是把后续判断建立在同一坐标系之上。
Step 4:比较“业务质量”而不是只比较“数据高低”
除关键财务指标外,还要比较:
- 核心产品与客户结构
- 市场份额与竞争优势
- 业务模式的抗波动能力
- 管理执行与资本配置风格
若某家公司短期数据更亮眼,但业务稳定性明显更弱,应明确指出,不可被表面增速误导。
Step 5:比较“赔率”与“催化顺序”
真正的比选往往不只看谁更好,还要看谁更值得现在买入或优先跟踪。需重点判断:
- 哪家公司好但已被充分定价
- 哪家公司一般但预期差更大
- 哪家公司短期有催化,哪家公司需要时间兑现
- 哪家公司更适合观察,哪家公司更适合行动
Step 6:输出排序与决策建议
在完成横向比较后,给出明确排序,并说明:
- 排名靠前的核心理由
- 排名靠后的主要短板
- 若只能研究一只、持有一只或短期交易一只,分别应如何选择
若结论取决于用户风格差异,也要明确把“成长型偏好”“价值型偏好”“交易型偏好”拆开说明。
输出结构
{行业/主题}同业比选({YYYY-MM-DD})
一、结论摘要
- 最佳综合选择:{公司}
- 最佳预期差选择:{公司}
- 最适合继续观察:{公司}
二、统一比较表
| 公司 | 业务定位 | 增长 | 盈利 | 估值 | 近期催化 | 主要风险 |
|---|---|---|---|---|---|---|
| {公司A} | {描述} | {描述} | {描述} | {描述} | {描述} | {描述} |
| {公司B} | {描述} | {描述} | {描述} | {描述} | {描述} | {描述} |
三、相对强弱分析
业务质量
- {谁更强,强在哪里}
成长质量
- {谁更强,强在哪里}
估值赔率
- {谁更有吸引力,原因是什么}
催化与时点
- {谁更适合当下,原因是什么}
四、最终排序
| 排名 | 公司 | 结论 |
|---|---|---|
| 1 | {公司} | {理由} |
| 2 | {公司} | {理由} |
| 3 | {公司} | {理由} |
五、决策建议
- 如果只能先研究一只:{公司},因为 {理由}
- 如果只能先跟踪一只:{公司},因为 {理由}
- 如果只能先规避一只:{公司},因为 {理由}
质量要求
- 只比较真正可比的对象,必要时先写清不可比之处。
- 统一使用同一比较口径,避免数据和叙事各说各话。
- 输出重点是“相对强弱与排序”,不是多篇个股介绍拼接。
- 必须同时比较质量、估值和时点,不能只用单一指标排名。
- 若结论明显依赖投资风格,应把适用人群写清楚。
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 · 146 lines · 66 tokens per session scan A dce96608c997
peer_comparison_decision_skill is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 1,344 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 2026-09-04.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
twitter-reader
Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
recipe-daily-pnl-report
Generate a daily profit and loss summary from trades and balances.