DevOps & Infra

ndpvt-web Skill

Orchestrate multi-agent workflows using the Lemon Agent orchestrator-worker pattern with hierarchical scheduling, progressive context compression, and self-evolving memory. Use when asked to 'break this into parallel subtasks', 'orchestrate agents for a complex task', 'manage context across long-running agent workflows', 'set up an orchestrator-worker pipeline', 'compress agent context efficiently', or 'build a multi-agent system with memory'.

ndpvt-web Skill

Agentic differential oracle for triaging cross-implementation discrepancies. Decomposes bug triage into specialized sub-agents (discrepancy finder, spec checker, false-positive critic, duplicate checker) that independently gather evidence and synthesize a verdict. Use when: 'triage differential test results', 'build a differential oracle', 'reduce false positives in cross-engine testing', 'agentic bug triage pipeline', 'analyze spec compliance differences', 'filter noise from differential fuzzing'.

ndpvt-web Skill

Assess visual quality of translated product images using Vectra's 14-dimension scoring framework. Use when: 'evaluate translated image quality', 'score e-commerce product rendering', 'assess in-image translation defects', 'build IIMT quality pipeline', 'rate visual rendering of translated text on images', 'detect text hallucination in product photos'.

ndpvt-web Skill

Diagnose and fix systematic failure modes in LLM-based multi-agent systems performing root cause analysis on cloud incidents. Applies the 12-pitfall taxonomy from Kim et al. (2026) to audit agent architectures, harden inter-agent communication, and eliminate hallucinated reasoning in diagnostic workflows. Use when: - "audit my agent pipeline for common failure modes" - "why does my RCA agent keep hallucinating root causes" - "harden multi-agent communication for incident response" - "review this agent workflow for reasoning pitfalls" - "my agents lose context across handoffs" - "fix incomplete exploration in my diagnostic agent"

ndpvt-web Skill

Build Extract-and-Evaluate (EaE) hierarchical monitoring pipelines that detect sabotage and misbehavior in LLM agent outputs. Uses information filtering to exploit the "less-is-more" effect where monitors perform better with curated excerpts than full trajectories. Trigger phrases: - "monitor agent outputs for sabotage" - "detect misbehavior in LLM agent traces" - "build an oversight pipeline for AI agents" - "extract and evaluate agent reasoning" - "filter agent trajectories for suspicious behavior" - "hierarchical LLM monitoring system"

ndpvt-web Skill

Multi-agent table question answering using MATA's three-path reasoning strategy (Chain-of-Thought, Program-of-Thought, Text-to-SQL) with confidence-based answer selection and scheduler-driven efficiency. Use when: 'answer questions about this table', 'analyze this CSV and answer', 'query this spreadsheet data', 'build a table QA pipeline', 'compare multiple reasoning approaches on tabular data', 'reliable table analysis with verification'.

ndpvt-web Skill

Build trustworthy ML pipelines for large-scale scientific data analysis with calibrated uncertainties, simulation-based inference, and physics-informed constraints. Use when: 'build a photometric redshift pipeline', 'add uncertainty quantification to my ML model', 'create a simulation-based inference workflow', 'integrate ML into a scientific analysis pipeline', 'validate ML predictions against simulations', 'set up active learning for survey data'.

ndpvt-web Skill

Build efficient log parsing systems that extract structured templates from raw log messages using a dual-cache architecture with LLM-powered correction -- optimized for small/local models. Use when the user says 'parse logs', 'extract log templates', 'build a log parser', 'log analysis pipeline', 'structure unstructured logs', or 'log template mining'.

ndpvt-web Skill

Build LLM agent systems hardened against indirect prompt injection using hierarchical memory isolation, schema-validated return values, and event-triggered sanitization inspired by OS process isolation. Use this skill when a user asks to "build a secure agent pipeline", "protect agents from prompt injection", "isolate agent memory", "design a multi-agent system with security boundaries", "implement safe tool calling for LLM agents", or "add injection defense to an agent framework".

ndpvt-web Skill

Analyze and reduce cognitive load in tool-use agent workflows using the Cognitive Load Framework from AAAI 2026. Diagnoses why agent pipelines fail by decomposing task complexity into Intrinsic Load (tool dependency depth/branching) and Extraneous Load (ambiguity/parameter confusion). Use when: 'diagnose why my agent keeps failing', 'reduce tool-call complexity', 'optimize my agent workflow', 'analyze cognitive load of this pipeline', 'map capability boundaries', 'simplify my tool orchestration'.

ndpvt-web Skill

Build training-free pipelines that convert sparse 3D LiDAR point clouds into depth-encoded 2D images for classification by Vision-Language Models (CLIP, etc.). Covers the full workflow: point cloud denoising, temporal frame fusion, canonical orientation, orthographic projection, morphological cleanup, bilateral smoothing, and few-shot VLM prompting with semantic anchoring. Use when: 'classify vehicles from roadside LiDAR', 'convert point clouds to images for VLM', 'few-shot 3D object classification without training', 'bridge LiDAR to vision-language model', 'bootstrap labeled dataset from unlabeled LiDAR', 'cold start vehicle classifier from point clouds'.

ndpvt-web Skill

Deploy and optimize small language models (SLMs) as autonomous agents using the effGen framework. Implements prompt compression (70-80% context reduction), five-factor complexity routing, intelligent task decomposition, and unified memory for local SLM-based agent systems. Triggers: 'set up effgen agent', 'deploy small language model agent', 'optimize prompts for small model', 'compress agent context for SLM', 'build local AI agent with effgen', 'route tasks by complexity for small models'

ndpvt-web Skill

Detect license incompatibilities across LLM supply chains (OSS repos, models, datasets) using the LiAgent multi-agent extraction and compatibility analysis framework. Use when: 'check my project for license conflicts', 'are my HuggingFace model dependencies compatible', 'audit LLM supply chain licenses', 'find licensing risks in my ML pipeline', 'is this model license compatible with my repo', 'analyze license compatibility for my AI project'.

ndpvt-web Skill

Build rubric-grounded reward models and preference evaluation pipelines for multimodal AI outputs. Use when asked to 'evaluate model outputs with rubrics', 'build a preference dataset', 'score multimodal responses', 'create a reward model pipeline', 'judge which AI response is better', or 'rank model completions across dimensions'.

ndpvt-web Skill

Build competitive game-arena evaluation frameworks for LLM-generated code using ProxyWar's multi-layer pipeline: agent generation, hierarchical testing, iterative repair, and TrueSkill tournaments. Triggers: 'evaluate code generation in game arenas', 'build a competitive agent tournament', 'assess LLM agents with ProxyWar', 'iterative code repair pipeline', 'TrueSkill ranking for generated agents', 'dynamic assessment of code quality beyond benchmarks'

ndpvt-web Skill

Harden LLM agent systems against prompt injection using layered text/model/execution defenses and the AgentPI evaluation framework. Use when: 'secure my agent against prompt injection', 'audit this agent for injection vulnerabilities', 'add prompt injection defenses', 'evaluate agent trustworthiness', 'harden this LLM pipeline', 'test my agent with adversarial inputs'.

ndpvt-web Skill

Agentic Text-to-SQL with semantic memory that captures and reuses structured execution traces. Use when: 'write SQL for this database', 'query this schema', 'generate SQL from natural language', 'text to SQL with complex schema', 'help me explore this database and answer questions', 'build a reusable SQL generation pipeline'.

ndpvt-web Skill

Reverse-engineer legacy numerical/scientific Fortran or C code and translate it into modern Python frameworks (Devito, NumPy, SciPy, FEniCS, etc.) using a multi-stage analysis pipeline with knowledge-graph-guided retrieval, structured code synthesis, and iterative validation. Trigger phrases: "convert this Fortran code to Python", "reverse engineer this finite difference code", "translate this legacy numerical solver to Devito", "modernize this scientific computing code", "what does this Fortran stencil do and how do I write it in Python", "migrate this CFD solver from Fortran to a modern framework"

ndpvt-web Skill

Build adaptive memory systems using coordinated multi-agent collaboration with hierarchical storage and consistency maintenance. Use when: 'build a memory system for my chatbot', 'add long-term memory to my agent', 'implement multi-granularity retrieval', 'create a memory-augmented LLM pipeline', 'handle memory conflicts in conversational AI', 'reduce context window usage with smart retrieval'.

ndpvt-web Skill

Trace and attribute RAG system responses back to specific tools and sources using Atomic Information Flow (AIF) -- a network flow model that decomposes outputs into atoms and computes precise attribution scores. Use when: "trace which tools contributed to this RAG response", "attribute this answer to its sources", "debug why my RAG pipeline returned wrong information", "compress RAG context without losing accuracy", "build attribution into my multi-agent system", "score tool contribution in my retrieval pipeline".

ndpvt-web Skill

Build systems that detect and fix reasoning gaps in LLM agents by comparing their chain-of-thought against reference reasoning, extracting structured discrepancies, and generating corrective instructions stored in a retrievable knowledge base. Use when: 'build a reasoning improvement pipeline', 'detect logic gaps in agent output', 'compare agent reasoning to expert reasoning', 'create a corrective knowledge base from reasoning errors', 'improve clinical decision support accuracy', 'patch reasoning with RAG-retrieved instructions'.

ndpvt-web Skill

Build multi-hop RAG systems that answer complex questions with only 2 LLM calls total, regardless of reasoning depth. Applies CompactRAG's offline atomic QA decomposition and online entity-consistent retrieval to slash token costs by 2-5x vs iterative RAG. Trigger phrases: - "build a multi-hop RAG pipeline" - "reduce LLM calls in my RAG system" - "answer complex questions over a knowledge base efficiently" - "implement CompactRAG" - "optimize token usage in retrieval-augmented generation" - "build a cost-efficient question answering system"

ndpvt-web Skill

Rerank retrieved passages for RAG pipelines using step-by-step logical reasoning to filter out semantically similar but logically irrelevant (SSLI) documents. Use when: 'rerank these search results', 'filter irrelevant passages from retrieval', 'build a scientific QA pipeline', 'improve RAG answer quality', 'passages look relevant but answers are wrong', 'reduce hallucinations in retrieval-augmented generation'.

ndpvt-web Skill

Agentic High-Level Synthesis (HLS) optimization: autonomously analyze, insert, and tune C/C++ HLS pragmas (pipeline, unroll, array_partition, dataflow) through closed-loop feedback with synthesis tools. Use when: 'optimize this HLS kernel', 'add pragmas to this C++ for FPGA', 'explore the design space for this Vitis HLS project', 'tune my hardware accelerator', 'analyze this HLS synthesis report', 'debug why my HLS design has poor throughput'.

ndpvt-web Skill

Apply PEARL's two-phase tool orchestration: offline tool exploration to learn valid usage patterns and failure modes, then structured plan-before-execute workflows for complex multi-step tool chains. Use when: 'plan a multi-tool workflow', 'chain multiple API calls', 'explore tools before executing', 'build a robust tool pipeline', 'multi-hop tool invocation', 'reduce tool call errors in a workflow'.

ndpvt-web Skill

Build multi-agent fact-checking pipelines that verify image-text claims through modality-specific analysis, cross-modal reasoning, and structured QA generation. Use when the user says 'verify this claim with evidence', 'fact-check this image and caption', 'build a multi-agent verification pipeline', 'check if this image matches the text', 'detect misinformation in multimodal content', or 'create an evidence-based claim verifier'.

ndpvt-web Skill

Evaluate deep research agents and LLM-generated long-form articles using the Wiki Live Challenge framework: 39 fine-grained writing criteria (well-written, broad coverage, neutral POV), factual verifiability via statement extraction and embedding-based matching, and citation accuracy checking. Use when: 'evaluate my research agent output', 'benchmark article quality against Wikipedia standards', 'check factual accuracy of generated report', 'audit citations in this article', 'score this article on Wikipedia Good Article criteria', 'build an evaluation pipeline for long-form generation'.

ndpvt-web Skill

Design and orchestrate multi-agent systems using reusable Agent Primitives (Review, Voting/Selection, Planning/Execution) that compose into task-specific pipelines. Use when asked to: 'build a multi-agent workflow', 'create an agent pipeline for this task', 'set up agents to review and refine output', 'orchestrate parallel agent voting', 'decompose this into a planning and execution pipeline', 'design a reusable agent architecture'.

ndpvt-web Skill

Agentic secure code review for detecting immature vulnerabilities at pre-commit stage. Uses a two-phase Detector-Validator pipeline with SAST-rule semantic memory and CWE-tree validation to localize, classify, and explain security weaknesses in code diffs. Trigger phrases: "review this diff for security issues", "secure code review", "find vulnerabilities in my changes", "pre-commit security check", "check this PR for security weaknesses", "agentic security review"

ndpvt-web Skill

Scan text for leaked secrets using a two-stage pipeline: regex candidate extraction followed by contextual classification to eliminate false positives. Use when the user says 'scan for secrets', 'check for leaked credentials', 'find API keys in this text', 'detect hardcoded secrets', 'audit issue text for sensitive data', or 'prevent secret leaks'.

ndpvt-web Skill

Design and implement multi-LM collaboration pipelines using the MoCo framework's 26 methods across four collaboration levels (API routing, text exchange, logit fusion, weight merging). Use when: 'set up model collaboration pipeline', 'combine multiple LLMs for better accuracy', 'implement multi-agent debate or refinement', 'route queries to the best model', 'merge model weights', 'build an LLM ensemble system'.

ndpvt-web Skill

Design and optimize RAG pipelines for Turkish and other morphologically rich languages (Turkish, Finnish, Hungarian, Korean, etc.) using evidence-based stage configurations. Trigger phrases: 'build a Turkish RAG pipeline', 'optimize RAG for agglutinative languages', 'RAG reranking for Turkish', 'morphology-aware retrieval', 'cross-encoder reranking pipeline', 'HyDE for non-English RAG'.

ndpvt-web Skill

Implement self-reconfiguring agent workflows where configuration (sub-goals, strategy, toolbox, context) is a mutable tool the agent calls at runtime. Use when: 'build an adaptive agent', 'self-reconfiguring pipeline', 'agent that adjusts its own strategy', 'dynamic tool selection workflow', 'multi-stage task with runtime adaptation', 'ToolSelf pattern'.

ndpvt-web Skill

Adaptive curriculum-driven iterative optimization for autonomous ML engineering tasks. Uses Evolving Data Buffers and Learnability Potential sampling from the AceGRPO paper to structure multi-step agent workflows that avoid behavioral stagnation. Triggers: 'optimize ML pipeline iteratively', 'adaptive curriculum for code tasks', 'iterative agent optimization', 'prioritize learning tasks', 'evolving task buffer', 'curriculum-based code improvement'.

ndpvt-web Skill

Generate structured autonomous driving scenarios and MCQ benchmarks using AgentDrive's factorized 7-axis prompt-to-JSON pipeline. Use when asked to: 'generate driving scenarios for AV testing', 'create autonomous driving benchmarks', 'build LLM evaluation datasets for driving', 'design safety-critical simulation scenarios', 'evaluate LLM reasoning on driving tasks', 'create multiple-choice questions for autonomous systems'.

ndpvt-web Skill

Multi-agent framework for scoring subjective, open-ended responses (interviews, essays, reflections) using transcript refinement + criterion-specific parallel scoring with calibrated few-shot examples. Use when: 'score these interview responses', 'evaluate candidate answers', 'grade these essays on a rubric', 'assess soft skills from text', 'build an automated scoring pipeline', 'rate open-ended responses against criteria'.