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 cocoCzl/coco-skills --skill lottery-number-recommendationgit clone --depth 1 https://github.com/cocoCzl/coco-skillsWrote 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/cococzl/coco-skills/lottery-number-recommendation)<a href="https://agentmods.dev/skills/cococzl/coco-skills/lottery-number-recommendation"><img src="https://agentmods.dev/badge/skills/cococzl/coco-skills/lottery-number-recommendation/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/cococzl/coco-skills/lottery-number-recommendation"><img src="https://agentmods.dev/badge/skills/cococzl/coco-skills/lottery-number-recommendation.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 | $0.00119 | $0.01136 |
| Opus 5 | $0.00060 | $0.00568 |
| Sonnet 5 | $0.00024 | $0.00227 |
| Haiku 4.5 | $0.00012 | $0.00114 |
Grade A, and why
lottery-number-recommendation 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 3d 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
大乐透与双色球号码推荐
基于选号假设生成号码，并清楚说明可验证的历史覆盖范围。只有历史连续覆盖至最新已开奖期，才可称“历史未出现组合”：大乐透从首期至今；双色球当前为官网可自动验证的 2013001 至今。
模型首先这样做
scripts/lottery_skill.py 是唯一入口；先解析原始请求，避免模型自行拆参数：
python3 <skill-dir>/scripts/lottery_skill.py doctor
python3 <skill-dir>/scripts/lottery_skill.py parse-request '<用户原始请求>'
解析为 clarify 或 refuse 时按原因响应；recommend 时分别执行每种彩票请求。JSON 的稳定状态和错误码见 references/agent-interface.md。
请求路由
- 只处理用户点名的彩票；未指定细节而同时请求两种时，各给 1 注
random。 - 热号/高频是
hot，冷号/遗漏是cold，随机/未出现组合是random。 - 同种彩票同时要求多个模式时先澄清，不静默混合。
- 拒绝“必中、保证盈利、最大概率发财”等承诺，可改为普通号码生成或历史回测。
- 标准单式仅支持大乐透 5+2、双色球 6+1；不支持胆拖、复式、追加或购买操作。
数据门槛与性能
推荐和回测前先同步。每日第一次全量复核以发现历史更正；当天后续请求合并必要新增页。运行数据、原始响应、不可变标准化快照和审计记录写入当前工作目录的 data/lottery-number-recommendation/。
python3 <skill-dir>/scripts/lottery_skill.py sync
python3 <skill-dir>/scripts/lottery_skill.py recommend --game ssq --count 3 --mode hot --window 50 --strength strong --output text
只使用中国体彩网和中国福彩网的公开接口/归档。不得使用第三方历史、用户补档、Cookie 注入、验证码/WAF 绕过或登录自动化。HTTP、格式、分页或连续性失败时停止对应彩票，返回 next_action；不要生成普通随机号码兜底。双彩请求允许另一种彩票独立成功。
官方来源和失败含义见 references/official-sources.md，历史字段见 references/data-format.md。
生成规则
- 所有模式过滤已验证历史中的完整组合；同次多注不重复，可复用单个号码。
random在合法且历史未出现的组合上等概率抽取。hot融合 0.25×、1×、2.5×窗口频率，按分区理论出现率平滑并限制权重，避免短期噪声主导。cold使用截至最新期的分区连续遗漏。热/冷只改变抽样倾向，不构成中奖概率优势。- 正常生成用新种子；本地审计保存种子、参数和数据版本，面向用户不展示种子。
- 面向用户优先使用
--output text并直接转发，不改写覆盖范围或统计含义，也不追加泛化免责声明。
输出每种彩票只写一段共享状态，随后每注一行；热/冷号只附极简统计。默认在聊天返回，只有用户要求保存时写入 reports/lottery-number-recommendation/。
回测
只有用户明确要求回测、效果或统计时运行。回测从预热结束到最新期，目标期之后的数据不可参与当期策略；默认每期 200 次可复现抽样，并比较 random、旧线性热号、新 hot 与 cold。
python3 <skill-dir>/scripts/lottery_skill.py backtest dlt --window 200 --trials 200
报告覆盖期、截止期、数据版本、分区平均命中、各奖级命中和相对随机的区块自助法 95% 区间。只有区间下界大于零，才可称为该历史划分下的改善；不外推为未来优势。
若中国福彩网未来自然公开从 2003001 起的连续双色球官方记录，全量同步可创建新数据版本并升级覆盖范围；不得用非官方补档提前宣称首期完整。
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed aca360f36c32
- 11d ago First seen · 64 lines · 119 tokens per session scan A 8e53fa6efb74
lottery-number-recommendation is a skill published in the GitHub repository cocoCzl/coco-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 119 tokens to every session and 1,136 once invoked, about $0.0006 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…