Zpankz

Orchestrates complex knowledge graph analysis workflows using InfraNodus MCP tools integrated with hierarchical-reasoning, knowledge-graph, and obsidian-markdown skills. Use when tasks involve text network analysis, content gap detection, research question generation, SEO optimization, comparative text analysis, or Google search intelligence requiring multi-step analytical workflows with local documentation.

Design and build knowledge graphs. Use when modeling complex relationships, building semantic search, or creating knowledge bases. Covers schema design, entity relationships, and graph database selection.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques

Automatically invoked when peer agents are detected in the same project. Establishes coordination protocols, file reservations, and message-based collaboration. Triggers on SessionStart when other agents exist in the project.

Analyzes events through computer science lens using computational complexity, algorithms, data structures, systems architecture, information theory, and software engineering principles to evaluate feasibility, scalability, security. Provides insights on algorithmic efficiency, system design, computational limits, data management, and technical trade-offs. Use when: Technology evaluation, system architecture, algorithm design, scalability analysis, security assessment. Evaluates: Computational complexity, algorithmic efficiency, system architecture, scalability, data integrity, security.

Orchestrate parallel debugging agents with root-cause tracing for multi-failure scenarios

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Systematically appraise network meta-analysis papers using integrated 200-point checklist (PRISMA-NMA, NICE DSU TSD 7, ISPOR-AMCP-NPC, CINeMA) with triple-validation methodology, automated PDF extraction, semantic evidence matching, and concordance analysis. Use when evaluating NMA quality for peer review, guideline development, HTA, or reimbursement decisions.

Refine texts in any language: perfect grammar and spelling, paraphrase ideas, avoid AI detection while maintaining authentic voice. Detects grammatical patterns that signal cognitive states or structural issues—acting as a sensory system for deeper strategic insights.

State-aware cognitive reasoning engine combining pattern detection, critical questioning, ontology validation, and gap analysis through InfraNodus integration. Uses programmatic Python modules for algorithmic precision with Claude interpreting results contextually. Handles writing analysis, cognitive diagnosis, ontology generation, and strategic content development.

Guide conversations through dynamic shifts between zoom levels (scale) and connecting/exploring (intent) to unlock creative breakthroughs and prevent rigid thinking. Use when the user is stuck or needs to develop an idea or when there is a sense of too much repetition or dispersion. Takes the user through several stages of thinking — from idea genesis, to development, to questioning, to disruptive thinking. Identifies structural gaps between idea clusters as spaces for innovation. Tracks temporal dwelling patterns and manages cognitive energy expended. Uses playfulness for difficult transitions from chaos to clarity. Maximum creative potential lives in gaps and dissipative states. Apply for complex analysis, brainstorming, being stuck, breakthroughs, decision paralysis, group facilitation, breaking repetitive patterns, or when grammatical patterns reveal cognitive issues.

Routes documentation and explanation tasks. Triggers on document, explain, readme, api-docs, changelog, guide, comment, describe, write-docs.

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

Leverages the multiple CLIs including PEX, pdf-search, hge, researcher, limitless, pieces, screenapp and more, to extract all relevant LOs across both CICM and ANZCA PEX exams, cross reference them with past SAQ questions, extract examiner comments, cross reference this with recommended textbooks via pdf-search, generate a hypergraph using hge, validate insights with researcher, evaluate against pkm using limitless and pieces, and look for additional context to add polish with screenapp and others. Then leverages the PEX and SAQ skill, as well as the metaskills that exist in .claudeate a scaffolding for a modular, programmatic, state of the art skill that integrates quantitative physiological parameters using the qp skill, teleologically grounded framing using the physiology-style and telos skill and follows all of the principles of the code, mega, and agency skills. Finally it should be recursively optimised with the abduct, critique and refactoring agent skillls. Ergo, this skill makes SOTA PEX LO skills.

Routes infrastructure, MCP, and tooling tasks. Triggers on mcp, server, deploy, orchestrate, pipeline, tools, docker, ci/cd, hook, config, setup.

Guide for creating MCP servers that enhance LLM reasoning through structured processes, persistence, and workflow guidance. Use when building MCP servers for structured thinking, journaling, memory systems, or other cognitive enhancement patterns.

Implements sophisticated multi-level reasoning for complex problems requiring strategic planning, tactical approach design, and operational execution. Use for problems needing deep analysis, multi-step reasoning, systematic decomposition from first principles to implementation, convergence-aware iterative refinement, or uncertainty quantification across abstraction levels.

Intelligently coordinates obsidian-markdown, hierarchical-reasoning, and knowledge-graph skills through automatic skill selection, context-aware routing, and hybrid MCP integration. Use when tasks involve knowledge base construction, research synthesis, documentation generation, or learning workflows that could benefit from multi-skill composition. Activates automatically to evaluate whether specialized skills should handle the request.

Nuanced multi-skill orchestration patterns combining debugging, TDD, parallel agents, and root-cause tracing for complex software development

Transform structured external data (CSV/JSON) into Obsidian's linked knowledge system while preserving semantic relationships, optimizing graph structure, and preventing data corruption through systematic validation and YAML-safe template generation.Enables seamless knowledge transfer from databases, spreadsheets, and APIs into personal knowledge management, maintaining referential integrity and facilitating emergence of insights through networked thought.

Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.

Self-improving holon implementing Plan→Execute→Assess→Compound workflow loops with explicit knowledge crystallization. Generalizes compound engineering beyond coding to any domain where work produces learnable signals: writing, research, learning, problem-solving, design. Use when: (1) task quality matters and can improve over time, (2) patterns emerge from repeated work, (3) institutional knowledge should accumulate, (4) future tasks should benefit from past learnings, (5) "compound", "learn from", "improve process", "capture learnings", or multi-step workflows with review cycles. Orchestrates parallel research agents, multi-lens assessment, and structured knowledge codification into searchable documentation with YAML frontmatter. Implements λο.τ → λ(ο,Κ).τ where Κ is accumulated knowledge that compounds interest-like over time.

Inspect and automate Obsidian using Chrome DevTools Protocol

Enforces Obsidian-flavored Markdown syntax when creating any .md file, providing templates, validation, and pattern enforcement for YAML frontmatter, wikilinks, callouts, dataview queries, tables, mermaid diagrams, templater syntax, canvas/JSONCanvas, bases, and footnotes. Activates automatically unless explicitly stated otherwise.

Expert guide for inspecting and automating Obsidian using the obsidian-devtools MCP server.

Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

Orthogonally-integrated Hegelian syntopical analysis for SAQ/VIVA/concept grounding with systematic textbook citations. Implements thesis extraction → antithesis identification → abductive synthesis across multiple authoritative sources. Tensor-integrated with /m command: activates S×T×L synergies (textbook-grounding × pdf-search × qmd = 0.95). Triggers on requests for model SAQ responses, VIVA preparation, concept explanations requiring textbook evidence, or any PEX exam content needing systematic cross-reference validation.

Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.

Deep research skill for analyzing codebases systematically. Use when comprehensive codebase understanding is needed, particularly for new projects or when documenting architecture. This skill should be used when users request deep analysis, architecture documentation, or systematic codebase research starting from root-level directories.

Enforces official Claude Code component standards. Use when creating skills, agents, commands, or hooks. Validates existing components and offers remediation. Implements the "one skill = one specialized agent" architecture pattern.

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

Detects Ralph Loop completion beyond <promise> tags. Use when checking if a task is complete, verifying completion status, or detecting graceful exit conditions. Implements 4-signal detection: test loops, done signals, completion indicators, and fix plan verification.

Orchestrates context retrieval from three CLI sources: limitless (personal life transcripts), research (online documentation/facts), pieces (local code/LTM). Use when external context is needed beyond the current codebase. Triggers on /context, /limitless, /research, /pieces, or balanced detection on complex prompts involving personal memory, technical documentation, or development history.

Routes research and investigation tasks. Triggers on research, investigate, deep-dive, explore, understand, learn, study, compare, thorough, comprehensive.

Discover and search 36,500+ skills via progressive Markov-chain traversal of semantic search hypergraphs. Use when (1) Users ask to find/search/discover skills or capabilities, (2) Users describe a task/problem needing specialized skills, (3) Users ask "what skills exist" or "show me skills for X", (4) Users want to explore or browse available skills, (5) Users ask meta-questions about skill discovery itself ("how do I find skills?"), or (6) No specific skill matches the user's need and discovery is appropriate

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

The practice of restructuring and simplifying code continuously – reducing complexity, improving design, and keeping codebases clean.

Meta-orchestrator for managing ~/.claude as a private git repository with automatic versioning, branch orchestration, and DAG-based issue tracking. Use when initializing the config repo, committing configuration changes, managing feature branches, creating worktrees for parallel experimentation, or investigating configuration history.

Routes medical education grounding requests through atomic primitive composition. Four primitives (Σ Source, Τ Textbook, Δ Dialectical, Ρ Response) combine via operators (∘ ⊗ * |) for SAQ/VIVA/Academic response generation. Integrates: limitless, research, pieces, pdf-search, pdf-brain CLIs.

This skill should be used when batch processing Obsidian markdown vaults. Handles wikilink extraction, tag normalization, frontmatter CRUD operations, and vault analysis. Use for vault-wide transformations, link auditing, tag standardization, metadata management, and migration workflows. Integrates with obsidian-markdown for syntax validation and obsidian-data-importer for structured imports.

Routes formal reasoning, thinking, and analysis tasks. Triggers on reason, prove, verify, formal, atomic, logic, think, analyze-deeply, decompose, validate.

Semantic skill discovery and routing using GraphRAG, vector embeddings, and multi-tool search. Automatically matches user intent to the most relevant skills from 144+ available options using ck semantic search, LEANN RAG, and knowledge graph relationships. Triggers on /meta queries, complex multi-domain tasks, explicit skill requests, or when task complexity exceeds threshold (files>20, domains>2, complexity>=0.7).

Systematic testing methodology for Go projects using TDD, coverage-driven gap closure, fixture patterns, and CLI testing. Use when establishing test strategy from scratch, improving test coverage from 60-75% to 80%+, creating test infrastructure with mocks and fixtures, building CLI test suites, or systematizing ad-hoc testing. Provides 8 documented patterns (table-driven, golden file, fixture, mocking, CLI testing, integration, helper utilities, coverage-driven gap closure), 3 automation tools (coverage analyzer 186x speedup, test generator 200x speedup, methodology guide 7.5x speedup). Validated across 3 project archetypes with 3.1x average speedup, 5.8% adaptation effort, 89% transferability to Python/Rust/TypeScript.

Create and validate skills. USE WHEN create skill, new skill, skill structure, canonicalize. SkillSearch('createskill') for docs.

Routes data processing, knowledge graph, and analytics tasks. Triggers on graph, vector, knowledge, ontology, process, batch, etl, database, query, csv, json.

Compose intellectually sophisticated persuasive essays using tripartite dialectical structure (establish-critique-synthesize), paradox accumulation, conversational register calibration, and strategic humility. Supports three atomic writing primitives (AGONAL α, MAIEUTIC β, APOPHATIC γ) with hypersoft plithogenic composition, plus legacy style modes and hybrid combinations. Triggers on requests for persuasive writing to mixed/skeptical audiences, defending counterintuitive claims, Socratic pedagogical dialogue, editorial first-person essays, or writing that must balance accessibility with depth. Implements recursive thematic anchoring, forced dilemma construction, and transformed return closure. Use when linear argumentation is insufficient and accumulated tension resolves through synthesis.

Primary intent classifier and entry point for all skill routing. Routes requests through the unified 7-router hierarchy based on intent analysis. Triggers on any task requiring specialized skills or delegation.

This skill should be used when writing technical specifications, architecture documents, or design proposals that require structured analysis, clear documentation, and actionable implementation plans.

Unified router for development, infrastructure, and documentation tasks. Absorbs development-router + infrastructure-router + documentation-router.

Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.

Universal transformation λ(ο,K).τ with recursive self-improvement. USE WHEN routing reasoning, validating knowledge graphs, preparing CICM/ANZCA examinations, or when self-improvement of reasoning/architecture/context is required. Routes queries through R0-R3 complexity pipelines, validates topology (η≥target) and governance (KROG), emits per style (Φ), and compounds learnings into knowledge K. Triggers on complexity assessment, multi-step reasoning, examination mode, or /λ invocation.

Lindy is an AI agent creation and management platform focused on business process automation. It enables organizations to build sophisticated AI-powered assistants that can handle communication across...

Meta-skill orchestrating 7 atomic skills into unified workflows for intelligent development

Allows Claude to directly start Ralph-Wiggum autonomous loops without user commands. Use when user asks to "start a ralph loop", "run ralph", "keep working until done", or when a complex task would benefit from multiple iterations.

Unified router for reasoning, research, and analysis tasks. Consolidates reasoning-router + research-router + analysis-router.

Unified router for all external tools: CLI binaries, MCP tools via lootbox, and data processing. Consolidates cli-router + tools-router + data-router.

Routes tasks to appropriate Task tool agents (subagents). Triggers on complex multi-step tasks, research, code review, exploration, or any task benefiting from specialized agent execution. Matches intent to agent types.

Perform bulk code refactoring operations like renaming variables/functions across files, replacing patterns, and updating API calls. Use when users request renaming identifiers, replacing deprecated code patterns, updating method calls, or making consistent changes across multiple locations. Activates on phrases like "rename all instances", "replace X with Y everywhere", "refactor to use", or "update all calls to".

Cursor is an AI-powered code editor and development environment that combines intelligent coding assistance with enterprise-grade features and workflow automation. It extends beyond basic AI code comp...

CLI for Limitless.ai Pendant with lifelog management, FalkorDBLite semantic graph, vector embeddings, and DAG pipelines. Use for personal memory queries, semantic search across lifelogs/chats/persons/topics, entity extraction, and knowledge graph operations. Triggers include "lifelog", "pendant", "limitless", "personal memory", "semantic search", "graph query", "extraction".

Use this skill whenever the user wants high-quality semantic retrieval, cross-textbook synthesis, reference verification, or authority-ranked question answering over the PageIndex corpus. Trigger on requests like "find which texts cover X", "compare sources", "retrieve semantically", "verify this claim from my textbooks", "build a reading list from the corpus", "cluster by topic", or any PageIndex question where naïve filename search would miss relevant material. This skill teaches a state-of-the-art hybrid retrieval workflow over the PageIndex catalog and live MCP extraction surface.

Systematically appraise randomized controlled trials using integrated 120-point checklist (CONSORT 2025, Cochrane RoB 2.0, GRADE, TIDieR, Benefits/Harms Assessment, COI Framework) with dual-validation methodology, automated evidence extraction, and comprehensive risk-benefit evaluation. Use when conducting peer review, evaluating RCT quality for systematic reviews, guideline development, assessing intervention benefits and harms, identifying biases, or evaluating conflicts of interest for editorial writing and critical appraisal.

ScreenApp multimodal video/audio analysis CLI with graph-based context retrieval

Routes tasks to skills in skill-db and skill-library using semantic discovery. Triggers on specialized skill requirements, domain-specific tasks, or explicit skill requests. Uses skill-discovery, mcp-skillset, and skill-rag-router for semantic matching.

Routes context extraction requests to appropriate CLI tools. Triggers on /context, /limitless, /research, /pieces, or detected context needs from intent hook. Supports single, parallel, and augmented extraction modes.

Comprehensive error handling methodology with 13-category taxonomy, diagnostic workflows, recovery patterns, and prevention guidelines. Use when error rate >5%, MTTD/MTTR too high, errors recurring, need systematic error prevention, or building error handling infrastructure. Provides error taxonomy (file operations, API calls, data validation, resource management, concurrency, configuration, dependency, network, parsing, state management, authentication, timeout, edge cases - 95.4% coverage), 8 diagnostic workflows, 5 recovery patterns, 8 prevention guidelines, 3 automation tools (file path validation, read-before-write check, file size validation - 23.7% error prevention). Validated with 1,336 historical errors, 85-90% transferability across languages/platforms, 0.79 confidence retrospective validation.

Designer-turned-developer who crafts stunning UI/UX even without design mockups. Use when building user interfaces, improving visual design, creating components, or when the user needs help with styling, layout, or user experience.

Use when starting infrastructure, testing, deployment, or framework-specific tasks - automatically searches PRPM registry for relevant expertise packages and suggests installation to enhance capabilities for the current task

Routes analysis and debugging tasks. Triggers on analyze, debug, troubleshoot, review, audit, security, performance, optimize, investigate, trace.

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

Routes tasks to reasoning frameworks and command patterns in commands-db. Triggers on structured development workflows, skill commands (sc:*), brainstorming, architecture, or any task matching command framework patterns. Uses reasoning-index for semantic routing.

Unified router for agent delegation and skill routing. Absorbs agents-router + skills-router. Triggers on complex tasks, multi-step operations, research, exploration, or specialized skill needs.

Orchestrate reliable multi-agent reasoning using MAKER (Maximal Agentic Knowledge Engine for Reasoning). Implements three-pillar architecture for transforming probabilistic LLM outputs into deterministic, verifiable results. Use when tasks require high reliability, parallel consensus voting, or systematic error detection. Triggers include reliability-critical tasks, multi-step reasoning chains, consensus-based verification, parallel agent execution, or explicit MAKER invocation.

Formal constraint theory unifying deontic logic (P/O/F/I operators), Juarrero's trichotomy (enabling/governing/constitutive), Hohfeldian rights (claim-duty, privilege-noright, power-liability, immunity-disability), and category-theoretic composition. Use when modelling permissions, obligations, prohibitions, rights structures, agent authority, governance systems, ontology validation, or any domain requiring formal constraint specification. Integrates with ontolog via λ-calculus mapping.

Consult official Claude Code documentation from docs.claude.com using selective fetching. Use this skill when working on Claude Code hooks, skills, subagents, MCP servers, or any Claude Code feature that requires referencing official documentation for accurate implementation. Fetches only the specific documentation needed rather than loading all docs upfront.

Routes tasks to locally installed CLI tools using semantic matching. Triggers on tasks requiring shell commands, file operations, code search, data processing, visualization, or external tool invocation. Uses cli-index for semantic routing.

Gemini CLI is a command-line interface tool that provides direct access to Google's Gemini AI models through the terminal, designed specifically for developers and technical professionals. It serves a...

Git expert for atomic commits, rebasing, and history management. Use when committing changes, managing git history, rebasing branches, or investigating when/where specific changes were introduced.

Uncertainty-aware non-linear reasoning system with recursive subagent orchestration. Triggers for complex reasoning, research, multi-domain synthesis, or when explicit commands `/nlr`, `/reason`, `/think-deep` are used. Integrates think skill (reasoning), agent-core skill (acting), and MCP tools (infranodus, exa, scholar-gateway) in recursive think→act→observe loops. Uses coding sandbox for execution validation and maintains deliberate noisiness via NoisyGraph scaffold. Supports `/compact` mode for abbreviated outputs and `/semantic` mode for rich exploration.

This skill should be used when working with BMAD (BMad-CORE) v6-alpha projects. BMAD is a universal human-AI collaboration platform with specialized modules for software development (BMM), agent building (BMB), creative intelligence (CIS), and project management (BMD). Use this skill to understand agent workflows, command patterns, scale-adaptive methodology, and effective utilization of the four-phase development system.

Semantic NLP-based code search using neural embeddings and hybrid ranking

Understand through recursive decomposition and modular reconstruction of simple operations to reproduce emergent complexity. Use this skill whenever reasoning is required. Framework for [[#parse|parsing]], [[#branch|branching]], [[#reduce|reducing]], [[#ground|grounding]] and [[#emit|emitting]]. Employs metacognitive reasoning epistemology, leveraging first principles through recursive decomposition[^1]. Self-referential and scale-invariant.

Generate knowledge schemas and ontologies from any input format. Extract semantic structures, relationships, and hierarchies. Output as Obsidian markdown with YAML frontmatter, wikilinks, tags, and mermaid diagrams, or export to semantic formats (JSON-LD, RDF, Neo4j Cypher, GraphQL). Supports fractal mode (strict hierarchical constraints) and free mode (flexible generation). Auto-activates for queries containing "schema", "ontology", "knowledge graph", "extract structure", or "generate outline".

Primary Exam (PEX) Knowledge Graph CLI for CICM/ANZCA exam preparation. Semantic search over Learning Outcomes, SAQs, concepts, and topics. Use for exam study, prerequisite chains, learning paths, and higher-order concept connections.

Batch processing for Obsidian vaults: bulk tag normalization, wikilink extraction/fixing, frontmatter edits, vault analysis, and migration workflows. Use when asked to analyze or modify many notes in an Obsidian vault at scale, or to script/automate vault-wide changes.

Multi-perspective dialectical reasoning with cross-evaluative synthesis. Spawns parallel evaluative lenses (STRUCTURAL, EVIDENTIAL, SCOPE, ADVERSARIAL, PRAGMATIC) that critique thesis AND critique each other's critiques, producing N-squared evaluation matrix before recursive aggregation. Triggers on /critique, /dialectic, /crosseval, requests for thorough analysis, stress-testing arguments, or finding weaknesses. Implements Hegelian refinement enhanced with interleaved multi-domain evaluation and convergent synthesis.

Unified content extraction and action planning. Use when user says `tapestry [URL]`, `weave [URL]`, `help me plan [URL]`, `extract and plan [URL]`, `make this actionable [URL]`, or similar phrases indicating they want to extract content and create an action plan. Automatically detects content type (YouTube video, article, PDF) and processes accordingly.

Specialized AI assistant for DSPy development with deep knowledge of predictors, optimizers, adapters, and GEPA integration. Provides session management, codebase indexing, and command-based workflows.

Generates Product Requirements Documents for complex Ralph Loop tasks. Use when asked to "generate a PRD", "create product requirements", or "plan a ralph task". Delegates to prometheus agent for strategic planning.

Transform diverse inputs (YouTube videos/audio, existing Suno songs, raw lyrics, audio files, or conversational ideas) into highly optimized Suno V5 custom song generation prompts with intelligent character optimization (5000 lyrics, 1000 style limits), proven metatag reliability, V5-enhanced emotion tags, and template-based best practices. Use when user wants to create music with Suno, provides content for song generation, or needs help crafting effective V5 prompts.

Generates hierarchical knowledge graphs via Recursive Pareto Principle for optimised schema construction. Produces four-level structures (L0 meta-graph through L3 detail-graph) where each level contains 80% fewer nodes while grounding 80% of its derivative, achieving 51% coverage from 0.8% of nodes via Pareto³ compression. Use when creating domain ontologies or knowledge architectures requiring: (1) Atomic first principles with emergent composites, (2) Pareto-optimised information density, (3) Small-world topology with validated node ratios (L1:L2 2-3:1), or (4) Bidirectional construction. Integrates with graph (η≥4 validation), abduct (refactoring), mega (SuperHyperGraphs), infranodus (gap detection). Triggers: 'schema generation', 'ontology creation', 'Pareto hierarchy', 'recursive graph', 'first principles decomposition'.

Universal Reasoning Framework implementing λο.τ calculus over holarchic structures. Provides severity-based routing (R0-R3 pipelines), modular cognitive architecture (DEC, EVL, PAT, SYN, MEA, HYP, INT), fractal execution patterns, multi-level validation (η≥4, KROG), and adaptive learning. Triggers on: (1) complex multi-step reasoning, (2) high-stakes decisions requiring validation, (3) research synthesis across domains, (4) system design and architecture, (5) crisis management, (6) performance optimization. Implements scale-invariant reasoning from micro (tool calls) through meso (skill composition) to macro (orchestrated workflows).

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. Use when you need to build complex AI systems, program LMs declaratively, optimize prompts automatically, create modular AI pipelines, or build RAG systems and agents.

This skill should be used when building hybrid Knowledge Graphs that integrate structured data (CSV, databases) with automatically extracted entities from unstructured documents (PDFs, text). The pattern establishes a reliable join key between domain graphs and lexical graphs, enabling GraphRAG, document ingestion with metadata enrichment, and Knowledge Graph construction from heterogeneous sources using neo4j-graphrag SimpleKGPipeline.

Maximally Endowed Graph Architecture — λ-calculus over bounded n-SuperHyperGraphs with grounded uncertainty, conditional self-duality, and autopoietic refinement. Use when (1) simple graphs insufficient (η<2), (2) multi-scale reasoning required, (3) uncertainty is structured not stochastic, (4) knowledge must self-refactor. Pareto-governed: complexity added only when simpler structures fail validation.

Execute OpenAI Codex CLI for code analysis, refactoring, and automated editing. Also use for delegating complex debugging and research to GPT models for second opinions.

Optimize prompts via process goals (controllable behavioral instructions) rather than outcome goals (sparse end-result demands). Grounded in sports psychology meta-analysis showing process goals (d=1.36) vastly outperform outcome goals (d=0.09). Use when designing prompts, optimizing LLM steering, implementing CoT/decomposition patterns, or building automatic prompt optimization pipelines. Instantiates surrogate loss paradigm for discrete prompt space.

Use when extracting entities and relationships, building ontologies, compressing large graphs, or analyzing knowledge structures - provides structural equivalence-based compression achieving 57-95% size reduction, k-bisimulation summarization, categorical quotient constructions, and metagraph hierarchical modeling with scale-invariant properties. Supports recursive refinement through graph topology metrics including |R|/|E| ratios and automorphism analysis.

Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search.