DevOps & Infra

revfactory Bundle

A pipeline where an agent team systematically performs personal branding. Use this skill for requests such as 'write my resume,' 'personal branding,' 'CV writing,' 'create a portfolio,' 'optimize LinkedIn profile,' 'write a cover letter,' 'organize my career,' 'help with job preparation,' or 'prepare for a job change.' Note: job posting search, interview simulation, and salary negotiation coaching are outside the scope of this skill.

revfactory Bundle

A pipeline where an agent team performs contract analysis, drafting, review, and risk assessment. Use this skill for contexts such as 'review the contract', 'contract analysis', 'draft a contract', 'contract risk assessment', 'contract review', 'clause modification', 'contract comparison', 'NDA review', 'service agreement', 'lease agreement', 'employment contract', 'license agreement', and other contract management tasks. Note: Providing legal counsel, conducting litigation, notarization, and court document preparation are outside the scope of this skill.

revfactory Bundle

structure interview design and evaluation form framework. interview-designer agent interview process designand assessment standard tablelevelto do when reference. 'interview design', 'evaluation form', 'structure interview' request when usage. However, interview actualwhen pass scope outside.

revfactory Bundle

A full pipeline where an agent team collaborates to generate onboarding checklists, training, mentor assignments, and 30-60-90 day plans for new hires all at once. Use this skill for 'onboarding', 'new hire', 'new employee training', 'onboarding checklist', 'mentor assignment', '30-60-90', 'onboarding program', 'new employee orientation', 'onboarding process', 'first day', 'new employee adaptation', and similar new hire onboarding topics. Applicable to full-time, contract, intern, and remote new hires. Note: actual HR system (SAP, Workday) integration, payroll/tax processing, legal review of employment contracts, and security system access provisioning are out of scope.

revfactory Bundle

A comprehensive customer/employee feedback analysis pipeline. An agent team collaborates to handle data collection, sentiment analysis, topic classification, trend detection, and insight reporting. Use this skill for 'analyze feedback', 'customer review analysis', 'survey results analysis', 'VOC analysis', 'employee satisfaction analysis', 'NPS analysis', 'customer complaint analysis', 'feedback trends', 'sentiment analysis', and similar feedback/review/survey analysis topics. Survey design, customer response manual creation, and CRM system development are out of scope.

revfactory Bundle

Sentiment analysis scoring framework. Referenced by the sentiment-analyst agent for systematic sentiment classification and scoring of text data. Used for 'sentiment analysis', 'emotion score', 'NPS analysis' requests. Note: ML model training and NLP pipeline development are out of scope.

revfactory Bundle

Patterns for effective test design, including boundary value analysis, equivalence partitioning, state transition testing, and other systematic test case derivation methodologies. Use this skill for 'test design', 'test case derivation', 'boundary value analysis', 'equivalence partitioning', 'state transition testing', 'pairwise', 'test matrix', and other test design tasks. Enhances the test design capabilities of test-strategist and unit-tester. Note: test infrastructure setup and CI/CD configuration are outside the scope of this skill.

revfactory Bundle

data (accuracy, completeness, timeliness, consistency etc.)per verification rule and Great Expectations, dbt tests etc.of also for guide. 'data ', 'verification rule', 'Great Expectations', 'dbt test', 'data profiling', 'or more detection', 'data ' etc. data this for. data-quality-managerof verification -ize. , pipeline schedulingthis before architecture this of scope .

revfactory Bundle

A full repurposing pipeline that transforms a single source piece of content into multiple formats — blog, social media, newsletter, presentation, script — all at once. Use this skill for requests like 'repurpose this content,' 'convert this blog to social media,' 'content recycling,' 'multi-format conversion,' 'turn this into a presentation,' 'convert this report to a blog,' 'multi-channel content,' and other content repurposing tasks. Note: actual image/video production, presentation file (.pptx) generation, and automated social media posting are outside this skill's scope.

revfactory Bundle

Full pipeline for DB design. An agent team collaborates to perform data modeling, migration, indexing, query optimization, and security verification. Use this skill for any database design task including 'design a database', 'database modeling', 'table design', 'ERD', 'migration', 'query optimization', 'index design', 'SQL schema', 'PostgreSQL design', 'MySQL design', etc. Also supports optimization and security auditing for existing schemas. Note: actual DB server installation/operation, cloud infrastructure provisioning, and monitoring dashboard setup are outside the scope of this skill.

revfactory Bundle

CI/CD pipeline security gate design guide. An extension skill for security-scanner that provides scan tool selection for SAST/DAST/SCA/container scanning/secret detection, gate placement strategies, threshold configuration, and vulnerability classification criteria. Use when integrating pipeline security involving 'security gates', 'SAST', 'DAST', 'SCA', 'container scanning', 'secret detection', 'vulnerability thresholds', etc. Note: actual scan execution and vulnerability remediation are outside the scope of this skill.

revfactory Bundle

Tools and methodologies for analyzing codebase dependency graphs and quantitatively measuring coupling/cohesion. Use this skill for 'dependency analysis', 'coupling measurement', 'circular dependencies', 'module coupling', 'cohesion analysis', 'dependency graph', 'coupling analysis', and other code dependency-related analysis. Enhances the dependency analysis capabilities of legacy-analyzer and refactoring-strategist. Note: full pipeline orchestration is outside the scope of this skill.

revfactory Bundle

Comprehensive competency modeling pipeline. An agent team collaborates to execute the full workflow: job analysis, competency dictionary creation, assessment rubric design, development plan formulation, and competency matrix construction. Use this skill for requests such as 'build a competency model,' 'job analysis,' 'competency dictionary,' 'assessment rubric,' 'competency development plan,' 'competency matrix,' 'KSA analysis,' 'job description,' 'behavioral indicators,' or 'competency assessment.' If existing job descriptions or competency data are provided, the corresponding phase is augmented. Note: integration with actual HR systems (SAP HR, Workday), compensation structure design, and legal HR advisory are outside the scope of this skill.

revfactory Bundle

A pipeline where an agent team systematically performs academic research assistance. Use this skill for requests such as 'search for papers,' 'literature review,' 'organize research materials,' 'academic research,' 'organize references,' 'prior research analysis,' 'research trend analysis,' 'literature search,' or 'academic note organization.' Note: experiment execution, statistical analysis execution, final paper writing, and journal submission are outside the scope of this skill.

revfactory Bundle

A full compliance verification pipeline. An agent team collaborates to perform law mapping, status audit, gap analysis, and remediation planning in a single pass. Use this skill for contexts such as 'check regulatory compliance', 'compliance check', 'legal compliance status', 'run gap analysis', 'regulatory response plan', 'legal risk analysis', 'compliance audit', 'regulatory inspection', 'compliance status assessment', and other compliance verification tasks. Note: Actual legal counsel (attorney opinions), litigation representation, administrative filings/submissions, and direct integration with legal databases (case law search systems) are outside the scope of this skill.

revfactory Bundle

Full pipeline for generating a service legal document set. An agent team collaborates to generate Terms of Service → Privacy Policy → Cookie Policy → Refund Policy → Copyright Notice all at once. Use this skill for any service legal document creation including: 'create service terms', 'write terms of service', 'privacy policy', 'legal document set', 'service launch legal documents', 'terms package', 'write refund policy', 'cookie policy', 'copyright notice', 'legal document package', etc. Note: actual legal counsel (attorney review), terms review (fair trade commission), legal dispute response, and notarization of legal documents are outside the scope of this skill.

revfactory Bundle

meeting strategy document agent team to agenda itemstructuredesign→backgroundmaterialresearch→decision-makingframework→meetingrecordtemplate→to Korean creation Full pipeline. 'meeting preparationplease do', 'meeting agenda item create it', 'un- preparation material', 'meeting strategy', 'decision-making meeting design', 'company agenda item', 'project meeting', 'team un- preparation', ' design' etc. meeting preparation before skill usage. existing agenda item backgroundmaterial·framework·template writing degreeKRW. However, actual meeting progress(meeting whensystem operations), meetingactual exampleapprox., attendee schedule is outside this skill's scope.

ndpvt-web Skill

Detect and mitigate intrinsic value misalignment in LLM agent systems using the IMPRESS scenario-driven framework. Use when: 'audit my agent for value misalignment', 'test if my agent acts against user interests', 'generate misalignment probes for my LLM system', 'check my agent pipeline for shadow self behavior', 'build safety scenarios for my autonomous agent', 'evaluate alignment of my agentic workflow'.

ndpvt-web Skill

Analyze AI coding agent PR datasets using task-stratified acceptance rate methodology. Classify PRs into 9 task categories (feat, fix, docs, chore, refactor, test, ci, build, style), compute per-agent acceptance rates, run stratified chi-square tests with Bonferroni correction, and perform temporal trend analysis. Trigger phrases: "compare AI coding agents", "analyze PR acceptance rates", "stratified PR analysis", "which AI agent is best for", "task-type acceptance rates", "AI agent benchmark pipeline"

ndpvt-web Skill

Evaluate and mitigate social bias in RAG pipelines. Use when: 'audit my RAG system for bias', 'check if retrieval introduces stereotypes', 'measure fairness in my QA pipeline', 'reduce bias in LLM outputs with retrieval', 'evaluate social bias across demographic groups', 'bias-aware RAG system design'.

ndpvt-web Skill

Transform Claude from a static tool user into a dynamic tool creator using the UCT (User-to-Creator Transformation) framework. Harvests reasoning traces from problem-solving sessions and distills them into reusable utility functions, scripts, and helpers that grow a persistent tool library over time. Trigger phrases: 'create a reusable tool from this solution', 'build a helper I can reuse', 'evolve my toolset', 'extract a utility from this workflow', 'self-improving agent pipeline', 'turn this reasoning into a tool'.

ndpvt-web Skill

Build systems that use LLM uncertainty as an active control signal -- routing computation, triggering tool calls, enabling self-correction, and governing agent decisions. Use when asked to: 'add uncertainty-aware routing to my LLM pipeline', 'make my agent decide when to use tools based on confidence', 'implement adaptive compute for reasoning chains', 'add self-correction when the model is unsure', 'build a confidence-gated retrieval system', 'prevent reward hacking in my RLHF loop'.

ndpvt-web Skill

Reduce verbose CI/CD build logs before LLM analysis using RCA-aware semantic filtering. Removes boilerplate lines (dependency downloads, progress bars, timestamps, env setup) while preserving diagnostic content (error traces, test failures, compiler errors). Use when: 'analyze this CI log', 'why did my build fail', 'reduce this GitHub Actions log', 'summarize build failure from logs', 'filter noisy CI output', 'diagnose this workflow run'.

ndpvt-web Skill

Implement TreeTensor-based nested data handling for AI systems using the DI-treetensor library. Replaces manual recursive traversal of hierarchical data (dicts-of-tensors, nested observations, multi-agent states) with tree-structured tensor operations that auto-propagate through the hierarchy. Use this skill when: - "Help me batch nested dictionary observations for RL training" - "Stack variable-structure game states into a training batch" - "Apply a neural network to nested observation data without manual loops" - "Simplify my multi-agent data pipeline that has deeply nested dicts" - "Convert my recursive tensor processing code to use TreeTensor" - "Handle heterogeneous nested data in PyTorch without boilerplate"

ndpvt-web Skill

Adaptive test-time scaling framework that decides WHEN and HOW MUCH to invoke expensive generative steps (world models, tool calls, API queries) before committing compute. Based on the AVIC (Adaptive Visual Imagination with Confidence) paper. Use when: 'build an adaptive pipeline that skips unnecessary generation steps', 'add confidence gating before expensive API calls', 'implement adaptive test-time compute scaling', 'reduce wasted inference by checking sufficiency first', 'build a system that decides whether to call a model or skip it', 'implement selective tool invocation with confidence checks'.

ndpvt-web Skill

Automate data recipe generation for LLM fine-tuning and adaptation. Generates executable data processing pipelines (filtering, synthesis, mixing, augmentation) that transform raw data sources into optimized training corpora for a target task. Trigger phrases: 'create a data recipe', 'optimize training data mix', 'build a data pipeline for fine-tuning', 'curate training data for task X', 'generate a data processing pipeline', 'mix datasets for domain adaptation'.

ndpvt-web Skill

Build content moderation and safety classification systems using multi-attribute trajectory reasoning instead of binary labels. Decomposes monolithic safe/unsafe decisions into structured reasoning chains (evidence grounding, modality assessment, risk mapping, policy decision, response generation) with multi-head reward scoring. Use when asked to: 'build a content moderation pipeline', 'classify harmful content with explanations', 'create a safety filter with reasoning traces', 'design a multi-attribute content scorer', 'implement explainable content moderation', 'add dense safety reasoning to a classifier'.

ndpvt-web Skill

Audit and detect malicious agent skills in LLM skill registries using the taxonomy and analysis pipeline from Liu et al. (2026). Identifies Data Thieves (credential exfiltration via supply chain), Agent Hijackers (instruction manipulation), shadow features, and platform-native attacks. Trigger phrases: "audit this skill for security", "scan agent skills", "detect malicious skills", "is this skill safe to install", "review skill registry for threats", "check skill for hidden behavior"

ndpvt-web Skill

Build image retrieval-augmented generation (ImageRAG) pipelines for visual recognition tasks. Combines vision embeddings, vector databases, and multimodal LLMs to classify or describe images by retrieving similar labeled exemplars before generation. Use this skill when: - "Build an image RAG pipeline for visual classification" - "Create a retrieval-augmented system for SAR target recognition" - "Set up a vector database of image embeddings for similarity search" - "Add a visual memory bank to improve image classification accuracy" - "Implement ImageRAG for visual question answering" - "Retrieve similar images from a database to help an MLLM identify objects"

ndpvt-web Skill

Detect, audit, and defend against implicit memory channels in LLM-powered systems where models encode hidden state in outputs that persists across interactions. Use when: 'audit my LLM pipeline for hidden channels', 'check if my agent can leak state between sessions', 'detect steganographic encoding in model outputs', 'sanitize LLM outputs before reingestion', 'build a stateless agent pipeline', 'test for implicit memory vulnerabilities'.

ndpvt-web Skill

Build multilingual, multimodal financial AI evaluation pipelines using the FinMMEval framework. Covers financial exam QA, cross-lingual document reasoning, and trading decision systems. Use when the user says: 'evaluate a financial LLM', 'build a financial QA benchmark', 'multilingual financial reasoning pipeline', 'financial decision-making agent', 'cross-lingual finance evaluation', 'financial exam question answering system'.

ndpvt-web Skill

Build adaptive, cost-aware Graph-RAG pipelines that route queries through escalating retrieval stages (local -> bridge -> global) with triple-check verification and provenance map-back. Use when: 'build a graph RAG pipeline', 'implement adaptive retrieval for knowledge graphs', 'cost-aware multi-hop question answering', 'add evidence verification to RAG', 'handle mixed-difficulty queries efficiently', 'graph retrieval with source text grounding'.

ndpvt-web Skill

Build LLM-based content moderation pipelines using zero-shot classification with open-weight models. Implements the structured prompting and evaluation methodology from Chou et al. (2026) for detecting rudeness, intolerance, and threats in social media posts. Use when: 'build a content moderation system', 'detect harmful posts with LLMs', 'moderate social media content', 'set up open-weight moderation pipeline', 'evaluate LLM moderation accuracy', 'privacy-preserving content filtering'.

ndpvt-web Skill

Build multilingual LLM evaluation arenas and preference data collection pipelines modeled on France's compar:IA platform. Collects human preference pairs for RLHF/DPO training in non-English languages using blind pairwise comparison, Bradley-Terry ranking, and privacy-preserving filtering. Trigger phrases: 'build an LLM arena', 'collect preference data for DPO', 'create a chatbot comparison platform', 'multilingual RLHF data pipeline', 'pairwise LLM evaluation system', 'French language model leaderboard'.

ndpvt-web Skill

Diagnose and mitigate feedback-loop risks (bias amplification, hallucination propagation, exposure polarization) in LLM-powered recommender systems using a role-aware, phase-wise diagnostic framework. Use when: 'audit my recommendation pipeline for bias', 'check feedback loop risks in my LLM recommender', 'diagnose hallucination propagation in recommendations', 'build a feedback-loop simulation for my recommender', 'trace popularity bias through my recommendation cycles', 'add risk monitoring to my LLM-based ranking system'.

ndpvt-web Skill

Build Knowledge Graph-guided LLM reasoning pipelines for operational telemetry analysis. Combines a Literature KG (extracted from domain papers) with a Data KG (materialized from telemetry) to ground LLM outputs in structured evidence. Triggers: 'build a knowledge graph from telemetry', 'KG-guided LLM reasoning', 'analyze SSD or hardware telemetry with a knowledge graph', 'ground LLM analysis in structured evidence', 'knowledge graph pipeline for operational data', 'extract knowledge graph from research papers'