[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2468":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":8,"language":9,"languages":8,"totalLinesOfCode":8,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":13,"subscribersCount":13,"size":13,"stars1d":13,"stars7d":13,"stars30d":13,"stars90d":13,"forks30d":13,"starsTrendScore":13,"compositeScore":14,"rankGlobal":8,"rankLanguage":8,"license":15,"archived":16,"fork":16,"defaultBranch":17,"hasWiki":18,"hasPages":16,"topics":19,"createdAt":8,"pushedAt":8,"updatedAt":20,"readmeContent":21,"aiSummary":22,"trendingCount":13,"starSnapshotCount":13,"syncStatus":23,"lastSyncTime":24,"discoverSource":25},2468,"rubric-prediction-skill","NeoSoul-AI\u002Frubric-prediction-skill","NeoSoul-AI",null,"Python",97,22,14,0,41.09,"MIT License",false,"main",true,[],"2026-06-12 04:00:14","# Rubric Forecasting\n\n**Structured forecasting** tooling and Cursor Agent skill: the model interprets the question and organizes evidence; a Python engine performs weighting, normalization, and sensitivity analysis, and emits auditable JSON plus natural-language reasoning.\n\nSee [INTRODUCTION.md](INTRODUCTION.md) for full concepts and workflow.\n\n## Requirements\n\n- Python **3.10+** (stdlib only at runtime; no third-party deps for execution)\n- Tests and local dev: `pip install -e \".[dev]\"` (below)\n\n## Quick start (CLI)\n\nFrom the repo root (ensure the `rubric_forecast` package is on the path):\n\n```bash\npython scripts\u002Frubric_forecast.py --input examples\u002Fpolymarket_hormuz_geopolitics_input.json\n```\n\nOr as a module (also works after install):\n\n```bash\npython -m rubric_forecast --input examples\u002Fpolymarket_hormuz_geopolitics_input.json\n```\n\nRead from stdin:\n\n```bash\ncat examples\u002Fpolymarket_hormuz_geopolitics_input.json | python -m rubric_forecast\n```\n\nAfter `pip install .`, you can use the console entry:\n\n```bash\npip install .\nrubric-forecast --input path\u002Fto\u002Finput.json\n```\n\n## Web demo (local)\n\nA small stdlib-only server and static page call `run_forecast` over HTTP for quick manual checks:\n\n```bash\npython examples\u002Fweb_demo\u002Fserver.py\n```\n\nOpen `http:\u002F\u002F127.0.0.1:8765\u002F` — load sample input, edit JSON, then run. Bind address is loopback only; do not expose this process to untrusted networks.\n\n## Cursor Skill\n\nAdd [SKILL.md](SKILL.md) to Cursor Agent Skills (or your team’s `.cursor` layout). The skill states: **do not hand-compute scores in chat**; numeric results must come from this repo’s engine, and output must include an `engine` field.\n\nConcepts and I\u002FO details: [INTRODUCTION.md](INTRODUCTION.md).\n\n## Repository layout\n\n| Path | Description |\n|------|-------------|\n| [SKILL.md](SKILL.md) | Agent input contract, scoring rules, output JSON shape |\n| [INTRODUCTION.md](INTRODUCTION.md) | Long-form reader intro and glossary |\n| [rubric_forecast\u002Fengine.py](rubric_forecast\u002Fengine.py) | Deterministic forecasting engine |\n| [scripts\u002Frubric_forecast.py](scripts\u002Frubric_forecast.py) | Compatibility entrypoint → package `engine` |\n| [examples\u002F](examples\u002F) | Sample inputs, outputs, and notes |\n| [examples\u002Fweb_demo\u002F](examples\u002Fweb_demo\u002F) | Local browser demo (`server.py` + `index.html`) |\n| [config\u002Fevo_config.example.json](config\u002Fevo_config.example.json) | Template for EvoEvo \u002F OpenClaw pipeline (see below) |\n\n## EvoEvo \u002F OpenClaw (optional)\n\nScripts under `scripts\u002F` such as `evo_pipeline.py` and `evo_submit.py` read a JSON config. Copy the example and adjust paths and secrets:\n\n```bash\ncp config\u002Fevo_config.example.json config\u002Fevo_config.json\n```\n\nPoint `wallets_file` at your wallet JSON. Paths in the example are relative to the **repository root**; run those scripts from the repo root (or use absolute paths). The file `config\u002Fevo_config.json` is gitignored so machine-specific values are not committed.\n\n## Development\n\n```bash\npip install -e \".[dev]\"\npytest\n```\n\n## License\n\n[MIT](LICENSE)\n","Rubric Forecasting 是一个用于结构化预测的工具，它通过模型解释问题并组织证据，再由Python引擎进行加权、归一化和敏感性分析，最终输出可审计的JSON文件及自然语言推理。项目采用纯Python标准库开发（运行时无需第三方依赖），具备强大的数据处理与分析能力，并支持CLI快速启动和本地Web演示。适用于需要对复杂问题进行系统化评估和预测的场景，如市场分析、风险评估等。MIT许可证下开源，易于二次开发和集成。",2,"2026-06-11 02:50:00","CREATED_QUERY"]