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 OpenMinis/MinisSkills --skill fucai3d-latestgit clone --depth 1 https://github.com/OpenMinis/MinisSkillsWrote 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/openminis/minisskills/fucai3d-latest)<a href="https://agentmods.dev/skills/openminis/minisskills/fucai3d-latest"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/fucai3d-latest/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/openminis/minisskills/fucai3d-latest"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/fucai3d-latest.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 | $0.00114 | $0.00989 |
| Opus 5 | $0.00057 | $0.00495 |
| Sonnet 5 | $0.00023 | $0.00198 |
| Haiku 4.5 | $0.00011 | $0.00099 |
Grade A, and why
fucai3d-latest 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 11d 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
Latest China Welfare Lottery 3D Draw Results
When the user wants to query the most recent China Welfare Lottery 3D draw results:
- Prefer using the browser tool to visit
https://www.baidu.com - Search for
Fucai 3D - Prefer reading the "Official Welfare Lottery 3D - Draw Results" card at the top of the Baidu results page
- First extract the information currently shown by default:
- Issue number
- Draw date
- Winning numbers
- If the user asks to "update results", "fill in missed draws", "check the recent draws", or suspects that the numbers are wrong:
- Do not rely only on the result shown by default in the current card
- First check the issue/date selector above the winning numbers, such as a switchable entry like
Issue 2026086, 2026-04-06... - Switch through the most recent issues one by one to verify them, checking at least the current issue and the previous 1 to 3 issues
- If "historical draw results" text appears directly below the Baidu card or in the body of the search results, such as
Issue 2026086: 382 / Issue 2026085: 118 / Issue 2026084: 456, use that issue-by-issue list as the basis for backfilling and correcting data
- Only fall back to the China Welfare Lottery website or other authoritative sources when issue-by-issue verification cannot be completed from the Baidu results page, and clearly state the data source
After obtaining the result, perform these additional entertainment functions:
- Use
/var/minis/shared/fucai3d/recommender.py update ISSUE DATE DIGITSto write this draw result to the history file/var/minis/shared/fucai3d/history.json - If any issue numbers are missing, backfill the missing issues as well; if any incorrect numbers already exist in the history, correct the local history using the latest verified results
- Use
/var/minis/shared/fucai3d/recommender.py bundle 5to generate:- 5 sets of basic entertainment recommendations
- 3 sets of cold-number preference recommendations
- 3 sets of hot-number mixed recommendations
- Frequencies of 0 to 9 in the recent window
- Hot-number and cold-number summary
- Clearly state that these suggested numbers are only "toy recommendations" generated from historical exclusion rules and simple frequency preferences, and do not represent any real predictive ability
Keep the output as concise as possible. Default format:
- Issue number: Issue XXXXXXX
- Draw date: YYYY-MM-DD
- Winning numbers: X X X
- History: updated / already exists / corrected
- If backfilled: backfilled Issue XXXXXXX, Issue XXXXXXX...
- Entertainment recommendations: A B C / D E F / ...
- Cold-number preference: A B C / D E F / ...
- Hot-number mix: A B C / D E F / ...
- Hot numbers in the last 30 issues: x, x, x...
- Cold numbers in the last 30 issues: x, x, x...
- Note: Based only on historical records for simple exclusion and frequency statistics; does not constitute predictive advice
Recommendation logic notes (no need to explain too much to the user):
- Prefer avoiding exact three-digit combinations that have appeared recently
- Avoid recent identical sum values as much as possible
- Avoid recent repeated patterns in adjacent digit pairs as much as possible
- Use the recent window to calculate hot and cold number frequencies
- If the history is too sparse or the constraints are too strict, fall back to random completion
If the Baidu results page cannot directly provide the winning numbers:
- Try clicking the first result to continue reading
- Prefer finding and parsing historical draw list text in the Baidu result body
- If that still fails, check the China Welfare Lottery website or other authoritative sources
- Clearly state the data source
If the retrieved information may not be from the latest issue, clearly state "based on current search results."
What ships with it
2 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.
- 11d ago First seen · 66 lines · 114 tokens per session scan A e89e90e48454
fucai3d-latest is a skill published in the GitHub repository OpenMinis/MinisSkills (407 stars, last pushed 6d ago), licensed MIT. It adds 114 tokens to every session and 989 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 2026-08-30.
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…