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 ggen0488-cyber/worldcup-2026-predictor-skill --skill worldcup-2026-predictorgit clone --depth 1 https://github.com/ggen0488-cyber/worldcup-2026-predictor-skillWrote 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/ggen0488-cyber/worldcup-2026-predictor-skill/worldcup-2026-predictor)<a href="https://agentmods.dev/skills/ggen0488-cyber/worldcup-2026-predictor-skill/worldcup-2026-predictor"><img src="https://agentmods.dev/badge/skills/ggen0488-cyber/worldcup-2026-predictor-skill/worldcup-2026-predictor/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/ggen0488-cyber/worldcup-2026-predictor-skill/worldcup-2026-predictor"><img src="https://agentmods.dev/badge/skills/ggen0488-cyber/worldcup-2026-predictor-skill/worldcup-2026-predictor.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 | $0.00184 | $0.02531 |
| Opus 5 | $0.00092 | $0.01265 |
| Sonnet 5 | $0.00037 | $0.00506 |
| Haiku 4.5 | $0.00018 | $0.00253 |
Grade A, and why
worldcup-2026-predictor 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
2026 世界杯预测 ⚽🔮
对 2026 美加墨世界杯做离线概率预测:单场比分、小组晋级、夺冠概率、淘汰赛路径。 默认使用理性模型(Elo → 波动修正泊松比分 → 蒙特卡洛);用户明确要求时才叠加玄学趣味模式。
本 skill 非 FIFA 官方项目,不与 FIFA 存在隶属、认可或赞助关系。输出只用于概率分析和娱乐,不构成官方赛程、赛果或确定性判断。
使用脚本
从当前 skill 根目录运行脚本,不要假设固定安装路径。下例用 $SKILL_DIR 表示 worldcup-2026-predictor 目录:
理性预测(默认)
python3 "$SKILL_DIR/scripts/predict.py" match 阿根廷 巴西 --seed 7
python3 "$SKILL_DIR/scripts/predict.py" match 阿根廷 巴西 --knockout --seed 7
python3 "$SKILL_DIR/scripts/predict.py" group C --sims 5000
python3 "$SKILL_DIR/scripts/predict.py" champion --sims 10000 --seed 7
python3 "$SKILL_DIR/scripts/predict.py" route 阿根廷 --sims 5000 --seed 7
python3 "$SKILL_DIR/scripts/predict.py" bracket --seed 7
python3 "$SKILL_DIR/scripts/predict.py" match 阿根廷 巴西 --json
- 球队名支持代码(
ARG)、英文(Argentina)或中文(阿根廷)。 - 如果是小组赛/联赛/积分赛,保留胜/平/负三种结果并预测比分;如果是淘汰赛,使用
--knockout,输出晋级倾向、常规时间比分和点球决胜路径。 group输出晋级 32 强概率,已纳入 8 个最佳第三名。route输出某队完整晋级路线概率、每轮到达概率和常见潜在对手。champion/group可调--sims;--seed用于复现;单场加--neutral可去掉东道主加成。- 所有理性命令支持
--json,用于让 Agent 稳定生成 HTML 报告,不需要解析中文文本。 - 足球偶然性已默认进入模型:泊松比分抽样 + 单场状态冲击 + 胜平负概率收缩,不需要额外参数。
bracket输出一次抽样的每轮淘汰赛路径,当前使用简化蛇形种子对阵,非 FIFA 官方槽位映射。- 预测脚本不联网抓数据;若存在
data/live/teams.json、data/live/results.json或data/live/intelligence.json,会优先读取这些由 Agent 保存的快照。
玄学模式(需用户主动开启)
python3 "$SKILL_DIR/scripts/divination.py" 阿根廷 巴西
python3 "$SKILL_DIR/scripts/divination.py" 阿根廷 巴西 --factor
python3 "$SKILL_DIR/scripts/divination.py" 阿根廷 巴西 --json
三种玩法(按用户意图选):纯玄学 / 科学+玄学并列 / 玄学加权(把 --factor 叠加到泊松胜率,得"开过光的概率")。详见 references/divination.md。
玄学脚本可读取 data/live/divination_context.json 中由 Agent 保存的起卦背景,例如比赛时间、地点、问题、颜色象意和资料来源;这些资料只用于确定起卦语境,不证明玄学可靠。
工作流程
- 判定用户要单场、小组、夺冠榜、淘汰赛路径,或是否明确要求玄学。
- 理性预测前由 Agent 主动查找官方或可靠来源,收集当前小组、赛程、已完赛比分、可用评级和比赛阶段;不要把数据源硬编码进脚本。如果用户只给出“谁 vs 谁”,先搜索确认这是小组/积分赛、淘汰赛、友谊赛还是其他赛制,再选择命令。若搜索后仍无法确认赛制,必须先问用户。
- 将理性基础数据保存为本地快照:
data/live/teams.json使用references/teams.json的结构,必须包含完整 48 队、A-L 12 组且每组 4 队;data/live/results.json使用data/results.json的结构,并在_meta记录来源 URL、采集时间和说明。 - 如果是当前理性单场预测,继续从多个方面收集两队赛前情报:伤停/停赛、预计首发、近期状态、赛程体能、场地天气、战术对位、比赛动机、赔率或评级变化。按
references/intelligence.md保存data/live/intelligence.json,并保留来源、采集时间、置信度、冲突说明和赛制/阶段。 - 调用脚本,脚本会优先读取
data/live/快照;若没有 live 快照,则回退到样例数据。intelligence.json是可选快照:团队级elo_delta会影响所有理性模拟,指定对阵的goal_delta当前只影响match A B单场命令。 - 如果用户明确要求玄学,Agent 可以收集比赛日期、开球时间、举办城市、场地、双方颜色/象征和用户问题,按
references/divination.md保存data/live/divination_context.json;不要把伤停、阵容、赔率等理性情报当作玄学可靠性的证据。 - 保留脚本的中文概率表格和“预测原因”说明,或优先使用
--json的结构化结果生成 HTML;单场预测要概括关键情报依据和不确定点。如果用户强调足球偶然性,说明模型默认已考虑冷门路径。 - 按
references/html_report.md由 Agent 直接生成自包含 HTML 报告,保存到reports/,并自动用默认浏览器打开;不要调用额外 HTML 生成脚本。HTML 必须显示“为什么这样预测”的原因区。若包含玄学预测,还必须清楚展示本卦、变卦、变爻、五行/生肖/命理依据、气运因子和断语原因。 - 涉及整届模拟时优先用
--sims 10000;需要快速反馈可降到2000;需要复现时加--seed。
What ships with it
10 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.
- data/results.json 421 B
- references/divination.md 4.5 KB
- references/hexagrams.json 8.0 KB
- references/html_report.md 6.6 KB
- references/intelligence.md 3.6 KB
- references/model.md 5.9 KB
- references/output_format.md 5.3 KB
- references/teams.json 6.8 KB
- scripts/divination.py 14 KB runs code
- scripts/predict.py 37 KB runs code
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.
- 12d ago First seen · 84 lines · 184 tokens per session scan A 24fa5b9cc9b7
worldcup-2026-predictor is a skill published in the GitHub repository ggen0488-cyber/worldcup-2026-predictor-skill (23 stars, last pushed 2mo ago), licensed MIT. It adds 184 tokens to every session and 2,531 once invoked, about $0.0009 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…