Results for “model debugging”

Run inference on Fireworks AI — direct, through the Leanmcp AI Gateway proxy (aigateway.leanmcp.com) for observability, or via LiteLLM / the OpenAI SDK / raw HTTP. Covers the endpoint-and-key matrix for each route, serverless vs dedicated deployments and their cold starts, browsing and filtering the model catalogue, reasoning models that return content:null with the answer in reasoning_content, function calling, concurrency and load testing, and runner scripts where many models share one protocol with a --use-proxy toggle. Use this skill whenever the user mentions Fireworks, FIREWORKS_API_KEY, api.fireworks.ai, fireworks_ai/ model ids, accounts/fireworks/models/..., a Fireworks deployment id, the Leanmcp gateway or LEANMCP_API_KEY, app.leanmcp.com observability, or gpt-oss / kimi / glm / qwen / deepseek served on Fireworks; wants to route LLM calls through a proxy for logging or cost tracking; is debugging empty responses, 404s, scope errors, cold starts, or "the gateway isn't working"; wants to pick a Fireworks model with tool calling; or wants to sweep several models over one benchmark. Reach for it even on vague asks like "why is this model returning nothing" or "set up inference for these models" when Fireworks is in play.

The English summary is being prepared. Showing the original description.

Add or verify model support in SGLang's Rust processor so chat requests produce the same prompt text and token IDs as Python. Use reference-generated test cases to find differences in tools, reasoning settings, conversation history, and errors.

• Adding model support to sglang-processor
• Porting model rendering from sgl-router
• Rechecking prompt behavior after a Dynamo update

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

The English summary is being prepared. Showing the original description.

Bridge Codex to web-based AI model products by packaging local task context, scrub-checking it, sending it through an approved browser surface to ChatGPT Pro, Claude, Grok, Gemini, or another web model, waiting for the answer, and returning the model response to the user or Codex. Also guide DevSpace-like MCP Connector Mode when the user wants ChatGPT Pro or another MCP-capable web host to access approved local workspaces without relying on Codex browser automation. Use when the user asks for GPT Pro, ChatGPT Pro, Claude web, Grok, Gemini web, web model bridge, external model consult, ask another model, second opinion, use a web AI model, browserless agent access to GPT Pro, MCP connector, DevSpace-like workflow, or send local repo context to a browser-based model for planning, review, debugging, architecture discussion, or implementation guidance.

The English summary is being prepared. Showing the original description.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

The English summary is being prepared. Showing the original description.

Regenerate an iOS app's debug bridge, the code connecting it to debugging tools, using current gstack templates. Update Swift support files and typed state accessors after gstack upgrades or ViewModel and property additions.

• Updating the debug bridge after a gstack upgrade
• Adding accessor coverage for new ViewModels
• Regenerating accessors for added state properties

Build and troubleshoot C#/.NET MCP servers that expose tools and information to AI agents. Guidance targets the official 2.x SDK and covers transport setup, authentication, interactive features, basic clients, and migration issues caused by changed defaults.

• Build a C#/.NET MCP server
• Add tools, prompts, and resources
• Diagnose STDIO and HTTP connection errors

Define custom entities and relationships in cognee, a memory system for AI applications. This skill guides model design, identity matching, searchable fields, and troubleshooting when entities are duplicated or relationships are missing.

• Designing custom entities and relationships
• Preventing duplicate entities across imports
• Investigating missing search results or relationships

Investigate 403 and 500 errors in Google Cloud Gemini Enterprise Agent Platform. Examine logs, registered destinations, agent identities, and authorization policies to produce a diagnostic report with evidence, recommended fixes, and verification steps.

• Investigating 403 errors when an agent calls an external API
• Diagnosing Agent Runtime 500 errors involving Model Armor
• Checking registration and permissions for failing MCP connections

Apply a specific set of Rails conventions to design, implementation, and code review. It keeps business logic in models, represents state changes as records, limits dependencies, and uses Minitest with fixtures, or predefined test data.

• Designing Rails models and database changes
• Representing state changes with separate records
• Reviewing code for consistent Rails conventions

This skill covers structural econometric models. Use when the user is building, estimating, or debugging structural models — including BLP demand estimation, dynamic discrete choice, auction models, or any workflow involving moment conditions, nested fixed-point algorithms, or MPEC formulations. Triggers on "structural model", "moment conditions", "NFXP", "MPEC", "BLP", "random coefficients", "dynamic discrete choice", "CCP", "Rust model", "auction estimation", "GMM objective", "inner loop", "contraction mapping", or convergence/starting value problems in optimization-based estimation.

The English summary is being prepared. Showing the original description.

Use this skill when authoring reusable, idempotent MATLAB scripts that build System Composer architecture models via the architecture-modeling API — `systemcomposer.createModel`, `addComponent`, `addPort`, `setInterface`, `connect(srcPort, dstPort)`, interface dictionaries (.sldd) with `addInterface`/`addElement`, profiles/stereotypes with `Profile.createProfile` and `addStereotype`, or `systemcomposer.allocation.createAllocationSet`. Also trigger when debugging these APIs (connections that don't appear, interfaces that don't resolve, profile save errors, `createAllocationSet` signature-mismatch errors). Do NOT trigger for ad-hoc structural edits to an already-built model (adding one SubSystem, rewiring a port) — use `building-simulink-models` with `model_edit` for that.

The English summary is being prepared. Showing the original description.

Guides implementation and maintenance of Claude applications using language-specific references and official SDKs, the libraries used to call the API. Covers tool integration, streaming responses, model migration, cost reviews, prompt audits, and evaluation workflows.

• Adding Claude API calls to an application
• Building an agent that uses custom tools
• Migrating existing Claude integrations to another model

Send proofs, planning questions, or difficult debugging tasks to DeepSeek's reasoning model. Receive the final answer and model-provided reasoning text in separate fields, with token usage reported for reviewing responses and costs.

• Requesting a mathematical proof
• Planning work that requires several reasoning steps
• Investigating root causes of difficult bugs

Build Claude applications using guidance for the official Anthropic SDK. Choose an integration approach, implement streaming and tool use, and follow workflows for model migration, prompt audits, evaluation, and cost optimization.

• Build a summarization app with Claude API
• Choose how to run an agent with custom tools
• Migrate existing code to a newer Claude model

Build and troubleshoot TorchDrug 0.2.1 workflows for molecular property prediction, molecule generation, protein modeling, and knowledge graph reasoning. Connect datasets, models, training tasks, and evaluation while checking version compatibility and common implementation errors.

• Training and evaluating molecular property prediction models
• Building molecule generation workflows
• Learning representations of protein sequences and structures

Plan and troubleshoot large language and vision model training and inference. This guide uses hardware measurements to identify bottlenecks, address memory shortages and unstable training, and improve checkpointing, recovery, and performance across multiple GPUs and machines.

• Diagnosing slow training and GPU memory shortages
• Investigating loss spikes and invalid numerical values
• Debugging communication hangs across GPUs and machines

Odoo 19 development knowledge base with 18 specialized guides covering Actions (ir.actions.*, cron jobs, server actions), Controllers (HTTP routing, endpoints, auth types), Data files (XML/CSV records, shortcuts, noupdate), API Decorators (@api.depends, @api.constrains, @api.ondelete, @api.onchange, @api.model, @api.private), SQL Constraints (models.Constraint replacing _sql_constraints), Database Indexes (models.Index), Module development (manifest, wizards, reports), Field types (Char, Text, Monetary, relational fields), Manifest configuration (__manifest__.py, dependencies, asset bundles), Mixins (mail.thread, mail.activity.mixin, mail.alias.mixin, utm.mixin), ORM Model methods (search, CRUD, domain filters, recordsets, CamelCase model naming), Migration scripts (pre/post/end hooks, data migration), OWL frontend components (hooks, services, lifecycle), Performance optimization (N+1 prevention, batch ops, _read_group), QWeb Reports (PDF/HTML, paper formats, barcodes, t-out), Security/ACL (record rules, field permissions, privilege-based groups, @api.private), Testing (TransactionCase, HttpCase, mocking, query count assertions), Transactions (savepoints, UniqueViolation, serialization failures), Translations (i18n, PO files, translatable fields), XML Views (list/form/search, kanban card templates, xpath inheritance, QWeb templates). Use when writing, reviewing, or debugging any Odoo 19 Python or XML code, creating or modifying modules, fixing performance issues, or looking up Odoo 19 API patterns and best practices. Includes CSS/SCSS asset authoring and review for Odoo addons.

The English summary is being prepared. Showing the original description.

Delegates coding/research tasks to the Google Antigravity CLI (`agy`) for external-model execution (Gemini 3.x, Claude Sonnet/Opus 4.6, GPT-OSS). Replaces the broken `collaborating-with-gemini` skill. Use when: (1) External-model delegation via Antigravity, (2) Multi-model prototyping (switch model per call), (3) Backend/logic implementation, (4) Algorithm design and optimization, (5) Bug analysis and debugging, (6) API/database code generation, (7) Code review. Triggers: "delegate to agy", "use Antigravity", "external model", "agy", "Gemini 3.5", "Claude Sonnet 4.6", "GPT-OSS". IMPORTANT: Always request unified diff patches only. Supports multi-turn sessions via SESSION_ID.

The English summary is being prepared. Showing the original description.

Use when adding support for a new model architecture to imp, porting a model family, or debugging a model that loads but produces wrong output - "add support for <model>", "new arch", loader detection, chat template, tokenizer parity, RoPE variant, "outputs garbage", "prompt-blind", "digits scrambled", "NaN logits", "describes a different picture", "does it fit in VRAM". Do NOT use for kernel performance (sm120-cuda-expert) or quant-format questions (quant-formats).

The English summary is being prepared. Showing the original description.

Choose tools and workflows for 3D modeling, dimensioned CAD parts, scan processing, rendering, and fabrication. Capability tables and recipes help connect tasks from photographs or initial designs to printable parts, CNC toolpaths, or game assets.

• Plan a workflow from dimensioned CAD to 3D printing
• Model and export a game asset
• Reconstruct a 3D model from photographs

Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Includes PyTorch and TensorFlow logging examples for examining weight distributions, predictions, and performance bottlenecks during machine learning training.

• Comparing loss and accuracy across training runs
• Inspecting weight and gradient distributions
• Exploring embeddings in two or three dimensions

Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.

• Training a language model on example responses
• Training with preferred and rejected response pairs
• Debugging GRPO reward functions and batch settings

Guides adapting OpenPI robot models to custom datasets and serving them to produce actions from observations. Covers JAX and PyTorch training, checkpoint conversion, and troubleshooting for normalization statistics and GPU memory.

• Fine-tune OpenPI models on custom robot datasets
• Convert JAX checkpoints to PyTorch
• Serve policies for ALOHA, DROID, or LIBERO