- 📁 examples/
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Supports both basic forecasting and advanced covariate forecasting (XReg) with dynamic and static exogenous variables. Automatically checks system RAM/GPU before loading the model, validates dataset fit before processing, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model and handle your specific dataset.
Add a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including Cache-DiT acceleration and parallelism support (TP, SP/USP, CFG-Parallel, HSDP). Use when integrating a new diffusion model, porting a diffusers pipeline or a custom model repo to vllm-omni, creating a new DiT transformer adapter, adding diffusion model support, or enabling multi-GPU parallelism and cache acceleration for an existing model.
- 📁 evals/
- 📁 references/
- 📄 SKILL.md
Core guide for using the Tinker API — installation, model selection, SDK basics, types, CLI, and hyperparameters. Use this skill whenever the user asks about getting started with Tinker, choosing a model, using the SDK, API types, CLI commands, or tuning hyperparameters. This is the foundational skill — trigger it for any general Tinker question.
Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation. --- # Auto Arena Skill End-to-end automated model comparison using the OpenJudge `AutoArenaPipeline`: 1. **Generate queries** — LLM creates diverse test queries from task description 2. **Collect responses** — query all target endpoints concurrently 3. **Generate rubrics** — LLM produces evaluation criteria from task + sample queries 4. **Pairwise evaluation** — judge model compares every model pair (with position-bias swap) 5. **Analyze & rank** — compute win rates, win matrix, and rankings 6. **Report & charts** — Markdown report + win-rate bar chart + optional matrix heatmap ## Prerequisites ```bash # Install OpenJudge pip install py-openjudge # Extra dependency for auto_arena (chart generation) pip install matplotlib ``` ## Gather from user before running | Info | Required? | Notes | |------|-----------|-------| | Task description | Yes | What the models/agents should do (set in config YAML) | | Target endpoints | Yes | At least 2 OpenAI-compatible endpoints to compare | | Judge endpoint | Yes | Strong model for pairwise evaluation (e.g. `gpt-4`, `qwen-max`) | | API keys | Yes | Env vars: `OPENAI_API_KEY`, `DASHSCOPE_API_KEY`, etc. | | Number of queries | No | Default: `20` | | Seed queries | No | Example queries to guide generation style | | System prompts | No | Per-endpoint system prompts | | Output directory | No | Default: `./evaluation_results` | | Report language | No | `"zh"` (default) or `"en"` | ## Quick start ### CLI `
Build a ForgeCAD model while actively hunting for API friction — missing helpers, awkward patterns, bad defaults, verbose boilerplate. Use when asked to dogfood, stress-test the API, or build a model with the goal of improving ForgeCAD.
- 📁 agents/
- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Inspect external prediction model implementations and adapt them to EasyTSF task contracts. Use when the user provides model code, class definitions, forward logic, or config fragments and wants Codex to classify the target task as `sequence_prediction`, `graph_prediction`, or `grid_prediction`, determine the current repository fit, and produce either a direct adaptation plan or a repository extension plan.
从零构建机构级三表模型（IS/BS/CF）— 完整公式联动、季度/半年/年频自适应、IFRS/US GAAP/中国准则。 触发词：三表模型、financial model、3-statement、建模、从零建模、收入预测。 ❌ 填写已有模板请用 financial-analysis:3-statements --- # 3-Statement Model — IPO / Equity Research Quality (v4.8 · Public Edition) --- ## 🚀 Quick Start — New Users **This skill builds:** A complete institutional-grade 3-statement financial model (IS / BS / CF) in Excel, with full formula linkage, zero hardcoded forecast cells, and 9-step QC validation. **Prerequisites — install before starting:** ```bash pip install openpyxl yfinance pandas pip install notebooklm # optional — only needed if you have a NotebookLM notebook ``` **How to trigger:** Just say `"建个三表模型"` / `"build a 3-statement model for [Company]"` and the skill guides you step by step. **What to prepare:** - Company ticker (e.g. `BABA`, `0700.HK`, `600519.SS`) - A data source — see recommendations below - ~1–2 hours across 5 sessions (each session is independent — pause and resume anytime) **⚠️ Data Source Guide — Read Before Starting** | Option | Setup | Token Cost | Recommended? | |--------|-------|-----------|--------------| | **NotebookLM notebook** (annual reports / prospectus pre-loaded) | One-time OAuth auth setup | Very low — NLM handles the PDF; Claude only receives answers | ✅ Best path | | **Excel upload** (historical IS/BS/CF already structured) + short PDF excerpts | None | Low | ✅ Good | | **Direct PDF upload** (full annual report, prospectus) | None | 🔴 Very high — a single A-share annual report can be 200+ pages | ⚠️ Pro users: avoid | | **Web only** (Sina / Yahoo Finance fallback) | None | Low | ✅ Fallback | **Strongly recommended for new users: set up NotebookLM first.** The one-time auth flow takes ~5 minutes and saves significant token consumption for every future model: ```bash pip install notebooklm # Run once interactively — browser will open for Google OAuth python3 -c " import asyncio from notebooklm import NotebookLMClient async def auth(): async with await NotebookLMClient.
Add or update a model in the harness model registry. Use when the user wants to add a new AI model, update model pricing, or change default models for a harness.
Add a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including Cache-DiT acceleration and parallelism support (TP, SP/USP, CFG-Parallel, HSDP). Use when integrating a new diffusion model, porting a diffusers pipeline or a custom model repo to vllm-omni, creating a new DiT transformer adapter, adding diffusion model support, or enabling multi-GPU parallelism and cache acceleration for an existing model.
Creates entity model documents with Mermaid.js ER diagrams and attribute tables defining entities, relationships, data types, and validation rules. Use when the user asks to "create an entity model", "design a data model", "draw an ERD", "define database schema", "model entities", or mentions entity-relationship diagram, ER diagram, database design, or data modeling. --- # Entity Model ## Instructions Create or update the entity model at `docs/entity_model.md` based on `docs/requirements.md`. The document contains an ER diagram and attribute tables. ## DO NOT - Add attributes/columns to the Mermaid diagram - Write prose descriptions like "Key attributes: name, email..." - Create a "Relationships" table - Skip the attribute tables ## Document Structure ```markdown # Entity Model ## Entity Relationship Diagram ```mermaid erDiagram ROOM_TYPE ||--o{ ROOM : "categorizes" GUEST ||--o{ RESERVATION : "makes" ``` ### ENTITY_NAME One sentence describing the entity. | Attribute | Description | Data Type | Length/Precision | Validation Rules | |-----------|-------------|-----------|------------------|-----------------------| | id | ... | Long | 19 | Primary Key, Sequence | | ... | ... | ... | ... | ... | ## Required Format for Each Entity
Guides ACT-R cognitive model construction: chunk types, production rules, subsymbolic parameters, and model validation
This skill should be used when the user asks about "AI security", "ML pipeline attacks", "prompt injection", "model deserialization", "unsafe model loading", "Jupyter injection", "LLM security", or needs to identify AI/ML-specific vulnerabilities in codebases that use machine learning frameworks.
