Development

Генерация полных Python pytest тестов для REST API эндпоинтов с валидацией схемы. Использовать при создании тестов для новых эндпоинтов, добавлении покрытия для CRUD операций или валидации соответствия API с OpenAPI схемами.

Управление переводами REST API ключей (rest_*) для MikoPBX. Автоматически находит отсутствующие русские ключи в RestApi.php и синхронизирует их с исходным кодом. Использовать при проверке переводов API, после добавления новых endpoints или перед релизом.

Auto-activate CCS CLI delegation for deterministic tasks. Parses user input, auto-selects optimal profile (glm/kimi/custom) from ~/.ccs/config.json, enhances prompts with context, executes via `ccs {profile} -p "task"` or `ccs {profile}:continue`, and reports results. Triggers on "use ccs [task]" patterns, typo/test/refactor keywords. Excludes complex architecture, security-critical code, performance optimization, breaking changes.

Performs focused, depth-first investigation of specific reverse engineering questions through iterative analysis and database improvement. Answers questions like "What does this function do?", "Does this use crypto?", "What's the C2 address?", "Fix types in this function". Makes incremental improvements (renaming, retyping, commenting) to aid understanding. Returns evidence-based answers with new investigation threads. Use after binary-triage for investigating specific suspicious areas or when user asks focused questions about binary behavior.

Solve CTF reverse engineering challenges using systematic analysis to find flags, keys, or passwords. Use for crackmes, binary bombs, key validators, obfuscated code, algorithm recovery, or any challenge requiring program comprehension to extract hidden information.

Performs initial binary triage by surveying memory layout, strings, imports/exports, and functions to quickly understand what a binary does and identify suspicious behavior. Use when first examining a binary, when user asks to triage/survey/analyze a program, or wants an overview before deeper reverse engineering.

MANDATORY: When writing Go tests, you MUST use 'When...it should...' format for ALL test names. When writing any Go code, you MUST remind user to run 'make lint-fix' and 'make verify'. These are non-negotiable HyperShift requirements.

Apply HyperShift conventional commit formatting rules. Use when generating commit messages or creating commits.

Provides systematic debugging approaches for HyperShift hosted-cluster issues. Auto-applies when debugging cluster problems, investigating stuck deletions, or troubleshooting control plane issues.

Apply Go best practices, idioms, and conventions from golang.org/doc/effective_go. Use when writing, reviewing, or refactoring Go code to ensure idiomatic, clean, and efficient implementations.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.