Use when you have a pretrained deep learning model, a reserved test set with ground-truth annotations, and need to evaluate prediction quality or generate embeddings for…
Use when you have cloned or loaded a deep-learning architecture extension (e.g., chemprop-IR) and need to verify that its feature extraction component can be instantiated and…
Guidelines for deep learning development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion model work.
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules.
Use when refactoring into deep modules, choosing seams, classifying dependencies, deciding adapter strategy, or planning tests around a refactor.
Trust-recovery deep quality-assurance pass. A six-subagent forensic review specialized for AI-failure-pattern classes, run over a defined PR window plus the files those PRs…
4-layer recall procedure (durable → semantic → PostgreSQL → daily notes) before claiming "no context".
Deep directory traversal, dependency analysis, env var discovery, and architecture summarization. Returns partial JSON for the parent scanner to assemble.
Builds a rigorous test strategy with multiple test-suite variants and critical review. Use when the user asks what to test, wants adversarial coverage, or needs a stronger test…
Use when user requests deep analysis, thorough thinking, or detailed breakdown of a problem. Triggered by phrases like: 帮我深入思考, 请仔细分析, 帮我详细拆解, 请梳理一下思路, 仔细考虑, 深入理解, 详细分析, or…
Comprehensive deep reasoning framework that guides systematic, thorough thinking for complex tasks. Automatically applies for multi-step problems, ambiguous requirements,…
Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or…
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop…
Use only when a developer explicitly asks to clean, prune, tidy, or organize DeepChat SDD documentation after implementation and validation.
Use when growing an already-playable Godot game along a depth axis (systemic / content / run-meta) without regressing proven behavior.
Surface architectural deepening opportunities — find shallow modules and refactor them into deep ones using precise vocabulary (module, seam, adapter, depth, leverage, locality).
Use when discussing or working with DeepEval (the python AI evaluation framework)
Test LLM applications with DeepEval, pytest-style unit tests for LLM outputs using G-Eval, answer relevancy, faithfulness, hallucination and custom metrics, with CI quality gates…
Configure Deepgram CI/CD integration for automated testing and deployment. Use when setting up continuous integration pipelines, automated testing, or deployment workflows for…
Collect Deepgram debug evidence for support and troubleshooting. Use when preparing support tickets, investigating issues, or collecting diagnostic information for Deepgram…
Deploy Deepgram integrations to production environments. Use when deploying to cloud platforms, configuring containers, or setting up Deepgram in Docker/Kubernetes/serverless.
Execute Deepgram incident response procedures for production issues. Use when handling Deepgram outages, debugging production failures, or responding to service degradation.
Configure Deepgram local development workflow with testing and mocks. Use when setting up development environment, configuring test fixtures, or establishing rapid iteration…
Transcribes audio using the Deepgram Nova-2 API with diarization, punctuation, and smart formatting. Supports streaming via WebSocket and batch via REST with pre-recorded endpoint…
Execute Deepgram production deployment checklist. Use when preparing for production launch, auditing production readiness, or verifying deployment configurations.
Implement Deepgram rate limiting and backoff strategies. Use when handling API quotas, implementing request throttling, or dealing with 429 rate limit errors.
Implement Deepgram reference architecture for scalable transcription systems. Use when designing transcription pipelines, building production architectures, or planning Deepgram…
Phone app and webpage launch payload guidance; transport routing and platform-specific targets stay inside the tools.
Use when reading, reviewing, inspecting, or reasoning about hosted Deepnote notebooks, blocks, inputs, SQL, Python, or notebook outputs through the Deepnote app tools.
NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference…
Essential procedural knowledge and constraints for writing, debugging, and understanding the `at` programming language.
Development workflow for features, bugs, refactoring. Auto-activates for multi-file implementations. — from engineering/code-quality
Development workflow for features, bugs, refactoring. Auto-activates for multi-file implementations. — from engineering/workflow-orchestration
Investigates bugs with evidence and analyzes root causes. Use for defects, incidents, flakes, and “why did this break?” work.
Builds a lawful, evidence-led criminal defence theory and action plan. Use when preparing a case strategy, testing prosecution allegations, planning motions or trial work, or…
Production-grade defensive Bash scripting for server automation, monitoring, and DevOps tasks. Emphasizes safety, error handling, idempotency, and logging.
A defesa do Município e do gestor perante o tribunal de contas competente — o TCE ou, onde houver, o Tribunal de Contas dos Municípios — com a trava que vale mais que qualquer…
Expert knowledge for DeFi/MEV bot development including critical pitfalls, backtesting realities, AMM mechanics, MEV extraction strategies, and production failure modes
Tests whether given facts actually satisfy the legal threshold for deficiency in service, defect in goods, or unfair trade practice, working element by element rather than…
Manifest builder. Plan work, scope tasks, spec out requirements, break down complex tasks before implementation.
Generates folder structures, module contracts, middleware pipelines, and frontend/backend boundaries for TypeScript full-stack applications.
Capture deployment characteristics for both production and development — hosting, IaC, CI/CD, secrets, observability, local dev environment, containerization, hot reload, and seed…
Encode test, lint, build, and docs routines as named Python sessions so humans and agents run the same workflow every time.
Use when starting an initiative or when the request names a vague quality ("make it scalable / fast / secure / robust") with no bar — derive and RANK the architecture…
Use as the mandatory front door for ALL planning, brainstorming, design, and "let's build/add/change/plan X" work — including prompts that claim the problem statement is already…
Defines standard TypeScript interfaces for Appwrite Collections. Use when creating new models for Tours, Users, or Bookings to ensure full type safety.
Root-cause flaky or failing E2E tests from a specific CI run by downloading and analyzing the Playwright HTML report (traces, screenshots, errors).
Automatically gather flaky E2E tests from recent CI runs on the main branch and from recent PRs by wwwillchen/keppo-bot/dyad-assistant, then deflake them.
Search the user's past AI coding sessions. Use when they say things like 'didn't we fix this before', 'what did we decide about X', or before re-debugging an error that may…
Search the user's past AI coding sessions with the deja CLI. Use when they say things like 'didn't we fix this before', 'what did we decide about X', or before re-debugging an…
Prüft Dekompilierung zur Interoperabilität, API-Reverse-Engineering, Vertragsverbote und EU/US-Unterschiede im Softwarerecht De Eu Us.
Generate a pre-flight delegation spec for any agent task -- context packages for memory-weak tools, review gates for opacity-prone tools, compounding checkpoints for stateless…
Delete a saved render profile by name. Use when the user says "delete the render profile", "remove my preset", or "clean up old render profiles".
Test-Driven Development patterns for testing AI deliberation features. Use when adding new deliberation features, adapters, convergence detection, or decision graph components.
Execute one stage from your master checklist: spec review, implementation, testing, and PR open.
Compare reply rates, bounce rates, and positive reply rates broken down by inbox type (SMTP / Gmail / Outlook) for a Smartlead account.
Use when designing cloud infrastructure, CI/CD pipelines, or deployment strategies
Expert delivery management for release planning, deployment coordination, incident response, change management, and SLA tracking across continuous delivery pipelines.
Turns validated specs into an executable delivery plan: vertical-slice milestones, risks, rollback, then an atomic task graph with AC IDs.
Shipped-state proof across source landing, artifacts, deployment, rollback, and production readback. Use when delivering a change or deciding whether it is truly released or live.