612 skills · sorted by relevance
Reviews FastAPI code for routing patterns, dependency injection, validation, and async handlers. Use when reviewing FastAPI apps, checking APIRouter setup, Depends() usage, or response models.
The English summary is being prepared. Showing the original description.
Discoverability shim for the Retail-Agentic-Commerce backend feature Codex skill. Use when writing or modifying Python backend code, routes, services, models, tests, or protocol logic.
The English summary is being prepared. Showing the original description.
Systems programming from memory management through networking. Covers memory models (stack vs heap, manual allocation, garbage collection, ownership/borrowing), concurrency (threads, mutexes, channels, async/await, actor model, data races vs race conditions), operating system concepts (processes, virtual memory, page tables, system calls, file descriptors, signals), compilation (lexing, parsing, code generation, linking, static vs dynamic libraries), networking fundamentals (TCP/IP, sockets, HTTP, DNS, TLS), and the hardware-software boundary (caches, cache lines, false sharing, memory-mapped I/O). Use when working with low-level code, diagnosing system-level bugs, understanding performance characteristics, or bridging between high-level languages and machine behavior.
The English summary is being prepared. Showing the original description.
Get external agent review and feedback. Routes Anthropic models through Claude Agent SDK (uses local subscription) and other models through OpenRouter API. Use for code review, architecture feedback, or any external consultation.
The English summary is being prepared. Showing the original description.
Odoo engineering workflows for addon development, codebase exploration, debugging, architecture/refactor review, manifest/docs sync, and routing to migration work. Use when the user mentions Odoo, addons, modules, manifests, models, XML views, security CSVs, record rules, Odoo shell, OWL/QWeb/assets, or when an Odoo codebase is detected.
The English summary is being prepared. Showing the original description.
Review Odoo addon code for correctness, security, performance, migrations, tests, and official Odoo coding guidelines. Use when reviewing Odoo modules, diffs, pull requests, or changed files involving models, fields, XML views, data, controllers, reports, OWL/assets, manifests, access rules, record rules, or OCA migrations.
The English summary is being prepared. Showing the original description.
Fit hidden Markov models using the Baum-Welch (EM) algorithm with model selection, Viterbi decoding for state sequences, and forward-backward probabilities. Use when observations are generated by unobservable latent states, you need to segment a time series into latent regimes (market regimes, speech phonemes, biological sequences), compute sequence probabilities, decode the most likely hidden state path, or compare models with different numbers of hidden states.
The English summary is being prepared. Showing the original description.
Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp. Includes Qwen 3.5 serve scripts (9B dense + F16, 35B MoE) with asymmetric KV cache and thinking mode. Secondary to Ollama; use when needing direct model control or LoRA hot-loading. Triggers on 'llama.cpp', 'GGUF', 'LoRA adapter', 'benchmark inference', 'llama-server'.
The English summary is being prepared. Showing the original description.
Write a durable feature spec before touching code. Reads the codebase map, reads related models/migrations to ask technical questions (not generic ones), then produces a structured spec doc in docs/specs/. Designed to pipeline with /implementation --issue N. Use before any feature implementation.
The English summary is being prepared. Showing the original description.
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browser_use, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle hooks, MCP server setup, or monitoring/observability with Laminar or OpenLIT. Also trigger for questions about browser-use installation, prompting strategies, or sensitive data handling. Do NOT use this for Cloud API/SDK usage or pricing — use the cloud skill instead. Do NOT use this for directly automating a browser via CLI commands — use the browser-use skill instead.
The English summary is being prepared. Showing the original description.
Work with text embeddings — choosing models, pooling, similarity measures, evaluation, and multilingual considerations. Use when building semantic search, clustering, or any similarity-based feature.
The English summary is being prepared. Showing the original description.
Fast serverless inference on Fireworks AI — open models, fine-tuning, and function-calling optimized endpoints.
The English summary is being prepared. Showing the original description.
Fine-tune large language models — data curation, SFT, parameter-efficient methods (LoRA), evaluation, and avoiding common training failures. Use when a base model needs task-specific behavior or domain knowledge.
The English summary is being prepared. Showing the original description.
Build financial models — revenue forecasts, unit economics, scenario analysis, and investor-grade spreadsheets.
The English summary is being prepared. Showing the original description.
Teach models new tasks from a handful of examples — prompting strategies, example selection, and in-context learning mechanics.
The English summary is being prepared. Showing the original description.
Generate and edit images with diffusion models: prompting, seeds, CFG, img2img, inpainting, conditioning, and API integration. Use when adding AI image generation to apps or workflows.
The English summary is being prepared. Showing the original description.
Distill large models into smaller ones — teacher-student training, data generation, loss design, and quality validation. Use when you need big-model behavior at small-model cost.
The English summary is being prepared. Showing the original description.
Align language models with human preferences using Direct Preference Optimization — no reward model, no RL loop.
The English summary is being prepared. Showing the original description.
Program language models instead of prompting them — DSPy signatures, modules, and optimizers that tune prompts automatically.
The English summary is being prepared. Showing the original description.
Analytics engineering with dbt — models, tests, and modular SQL pipelines — use when building or maintaining dbt projects.
The English summary is being prepared. Showing the original description.
Build SaaS customer support — tiered support models, SLAs, macros, escalation, and support-driven product feedback.
The English summary is being prepared. Showing the original description.
Build with Cohere's enterprise AI — Command models, Embed embeddings, and Rerank for retrieval pipelines.
The English summary is being prepared. Showing the original description.
Clinical prediction models and risk scores — development, validation, calibration, and bedside use.
The English summary is being prepared. Showing the original description.
Elicit step-by-step reasoning from language models to boost accuracy on math, logic, and multi-step problems.
The English summary is being prepared. Showing the original description.