Research

Investigates HEC-HMS internals through decompiled Java classes. Provides JythonHmsAPI reference, CLI options, version-specific differences (3.x vs 4.x), and guideson-demand decompilation for new discoveries. Use when debugging HMS behavior,discovering undocumented features, understanding version differences, validatingautomation approaches, or investigating HMS API capabilities. Includes completeJythonHms method reference, Python 2 vs 3 syntax differences, and decompilationtooling. Complements hms_doc_query (official docs) with internal implementation details.Trigger keywords: decompile, HMS internals, JythonHms API, HMS version differences,CLI options, undocumented, HMS jar, HMS classes, debugging HMS, HMS source code,HMS 3.x support, Python 2 vs 3, HMS methods, HMS parameters.

When creating or validating skills. Reference for SKILL-CREATOR and SKILL-VALIDATOR.

Recovers working context from the journal after /clear or at session start

This skill should be used when the user asks to "create a plot", "make a chart", "visualize data", "create a heatmap", "make a scatter plot", "plot time series", "create publication figures", "customize plot styling", "use matplotlib", "use seaborn", or needs guidance on Python data visualization, statistical graphics, or figure export.

Interprets Arduino/ESP32/RP2040 compiler errors in plain English for beginners. Use when user shares error messages, compilation failures, upload problems, or asks "what does this error mean". Covers common errors like undefined references, type mismatches, missing libraries, and board-specific issues.

This skill should be used when converting documents between formats (Markdown, DOCX, PDF, HTML, LaTeX, etc.) using pandoc. Use for format conversion, document generation, and preparing markdown for Google Docs or other word processors.

This skill should be used when creating Daggerheart adversaries, building stat blocks, designing encounters, or determining enemy difficulty. Invoke when the GM needs to create enemies, generate adversary stat blocks, calculate Battle Points for encounter balance, or reference adversary types (Bruiser, Horde, Leader, Minion, Ranged, Skulk, Social, Solo, Standard, Support).

Use when writing Vague (.vague) files - a declarative language for generating realistic test data with superposition, constraints, and cross-references

"Hierarchical task decomposition with control flow nodes and dual memory systems from ReAcTree research. Trigger keywords: ReAcTree, parallel execution, working memory, episodic memory, LOOP, CONDITIONAL, FEEDBACK, hierarchical agents, coordination, control flow, agent trees"

This skill should be used when the user mentions Confluence, references Confluence page URLs,asks to search for documentation, or needs to view Confluence content. Activates on keywords like"Confluence", "wiki", "documentation", Confluence URLs, or numeric page IDs in Confluence context.Provides read-only access to Confluence via command-line search and view scripts.

Master protocol for deconstructing agent frameworks to inform derivative system architecture. Use when (1) analyzing an agent framework's codebase comprehensively, (2) comparing multiple frameworks to select best practices, (3) designing a new agent system based on prior art, (4) documenting architectural decisions with evidence, or (5) conducting technical due diligence on AI agent implementations. This skill orchestrates sub-skills for data substrate, execution engine, cognitive architecture, and synthesis phases.

Research-backed code review skill with OWASP Top 10 security checks, SAST tool integration (SonarQube, CodeQL, Snyk), performance pattern detection, and automated quality standards enforcement. Auto-invoked for code review, security audit, PR analysis, and bug checking. Implements 2025 best practices with 92% faster vulnerability remediation.

Comprehensive arXiv paper search and retrieval tool with keyword search, category filtering, date range filtering, and daily paper fetching capabilities for academic research tracking without keywords

Create vertical (9:16) interactive presentations optimized for YouTube Shorts, TikTok, and Instagram Reels. Takes YouTube video URLs to extract facts via Playwright MCP and web research, then generates animated slides you can screen record and narrate. Perfect for quick educational content, fact-reveals, and viral short-form videos.

Create structured visualizations of stakeholder perspectives (says, thinks, does, feels) to build deep understanding. Use when conducting user research or validating assumptions.

Comprehensive financial statement analysis including ratio calculation, trend analysis, and peer comparison. Evaluates liquidity, profitability, efficiency, and leverage metrics. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0. Use when analyzing company fundamentals, comparing financial performance, or conducting equity research.

Complete HUMMBL Base120 mental models framework with all 120 models across 6 transformations (Perspective, Inversion, Composition, Decomposition, Recursion, Meta-Systems). Includes model selection guidance, application methodology, and validation checklist. Version 1.0-beta definitive reference.

Navigate a local emacs-twist/twist.nix checkout and point to relevant files for questions about twist.nix configuration, flake outputs, library functions, Home Manager integration, package build flow, or tests. Use when a user asks where something is defined or how twist.nix is wired and the answer should reference code rather than reproduce it. Ask for the repo path if it is not available.

Skill with external file references for testing detection

Create Reference Documents (REF) - supplementary documentation that doesn't participate in formal traceability chain