rysweet

Auto-generates code flow diagrams from multi-language module analysis. Detects when architecture diagrams become stale (code changed, diagram didn't). Supports Python, TypeScript/JavaScript, Rust, and Go out of the box. Use when: creating new modules, reviewing PRs for architecture impact, or checking diagram freshness across polyglot repositories. Generates mermaid diagrams showing imports, dependencies, and module relationships.

Execute multiple independent development tasks in parallel using subprocess isolation. Each task runs in a clean /tmp clone with Recipe Runner code-enforced workflow execution. Proven pattern: 4/5 PRs created successfully in first production use.

Interactive teaching agent for the goal-seeking agent generator and eval system. Provides a structured 14-lesson curriculum covering agent generation, SDK selection, multi-agent architecture, progressive evaluation (L1-L12), retrieval strategies, intent classification, math code generation, self-improvement loops with patch proposer and reviewer voting, and memory export/import.

Development workflow for features, bugs, refactoring. Normally executed as a sub-recipe by dev-orchestrator/smart-orchestrator. Supports direct invocation via recipe runner for standalone use.

Default task orchestrator for all development and investigation work. Classifies tasks, decomposes into parallel workstreams if appropriate, and routes execution through the recipe runner. Replaces ultrathink-orchestrator.

Writing clear, discoverable software documentation following the Eight Rules and Diataxis framework. Use when creating README files, API docs, tutorials, how-to guides, or any project documentation. Automatically enforces docs/ location, linking requirements, and runnable examples.

Generates comprehensive end-to-end test scenarios using outside-in methodology. Supports 5 app types: Web (Playwright), CLI, TUI, API, and MCP (gadugi YAML). Auto-detects app type or accepts explicit override.

Guides architects on when and how to use goal-seeking agents as a design pattern. This skill helps evaluate whether autonomous agents are appropriate for a given problem, how to structure their objectives, integrate with goal_agent_generator, and reference real amplihack examples like AKS SRE automation, CI diagnostics, pre-commit workflows, and fix-agent pattern matching.

Development workflow for features, bugs, refactoring. Normally executed as a sub-recipe by dev-orchestrator/smart-orchestrator. Supports direct invocation via recipe runner for standalone use.

Generates an illustrated, plain-language walkthrough document for a pull request — problem statement, approach overview, step-by-step code tour with mermaid diagrams, deep diff links, key decisions, and testing summary. Use when explaining, documenting, or summarizing a PR, creating a reviewer-friendly illustrated guide, or producing walkthrough notes at the end of default-workflow. Works with GitHub and Azure DevOps.

Checks whether a PR/pull request satisfies the project's merge criteria and records the required evidence in the PR/pull request description. Use with `/merge-ready` before review or merge when QA-team scenarios, docs links, quality-audit convergence, checks/build validation status, and diff scope must be verified.

Expert project manager orchestrating backlog-curator, work-delegator, workstream-coordinator, and roadmap-strategist sub-skills. Coordinates complex software projects through delegation and strategic oversight. Activates when managing projects, coordinating work, or tracking overall progress.

Comprehensive knowledge of amplihack framework architecture, patterns, and usage

Comprehensive .NET exception handling quality improvement workflow. Auto-detects .NET projects, investigates 10 common exception handling mistakes, generates prioritized findings, and orchestrates fixes following best practices.

6-phase investigation workflow for understanding existing systems. Normally executed as a sub-recipe by dev-orchestrator/smart-orchestrator. Supports direct invocation via recipe runner for standalone use.

Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Stores discoveries in memory (via `amplihack memory store-discovery` CLI), suggests PATTERNS.md updates, and recommends new agent creation. Ensures knowledge persists across sessions via Kuzu memory backend.

Orchestrate large-scale changes across a codebase in parallel

Review changed code for reuse, quality, and efficiency, then fix any issues found

Consolidated Claude Code sync and parity tracking for RustyClawd. Fetches latest Claude Code features from official sources, compares against the local feature inventory, identifies gaps, and optionally creates GitHub issues. Also supports deep analysis by deminifying the installed Claude Code cli.js.

Track and report agent invocation metrics including usage counts, success/failure rates, and completion times. Use for understanding which agents are utilized, identifying underused agents, and optimizing agent delegation patterns.

Automated dependency conflict detection and resolution. Detects local vs CI environment mismatches, compares versions, and generates pinning recommendations. Run as pre-push check to catch issues early.

Auto-discovers and configures Language Server Protocol (LSP) servers for your project's languages

Multi-repository orchestration for coordinating atomic changes across dependent repositories. Tracks dependency graphs, coordinates cross-repo PRs, and detects breaking changes.

Cross-session learning system that extracts insights from session transcripts and injects relevant past learnings at session start. Uses simple keyword matching for relevance. Complements DISCOVERIES.md/PATTERNS.md with structured YAML storage.

Generates agentic outside-in tests using gadugi-agentic-test framework for CLI, TUI, Web, and Electron apps. Use when you need behavior-driven tests that verify external interfaces without internal implementation knowledge. Creates YAML test scenarios that AI agents execute, observe, and validate against expected outcomes. Supports progressive complexity from simple smoke tests to advanced multi-step workflows.

Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.

Complete Azure DevOps automation - boards, repos, pipelines, artifacts

Expert backlog manager that prioritizes work using multi-criteria scoring, analyzes dependencies, and recommends optimal next tasks. Activates when managing backlogs, prioritizing work, adding items, or analyzing what to work on next.

Auto-generates code flow diagrams from Python module analysis. Detects when architecture diagrams become stale (code changed, diagram didn't). Use when: creating new modules, reviewing PRs for architecture impact, or checking diagram freshness. Generates mermaid diagrams showing imports, dependencies, and module relationships.

Proactive context window management via token monitoring, intelligent extraction, and selective rehydration. Features predictive budget monitoring, context health indicators, and priority-based retention. Use when approaching token limits or needing to preserve essential context. Complements /transcripts and PreCompact hook with proactive optimization.

Development workflow for features, bugs, refactoring. Auto-activates for multi-file implementations.

Writing clear, discoverable software documentation following the Eight Rules and Diataxis framework. Use when creating README files, API docs, tutorials, how-to guides, or any project documentation. Automatically enforces docs/ location, linking requirements, and runnable examples.

Expert guidance for Azure DevOps CLI (az devops) - automation, pipelines, repos, boards, and artifacts management. Use when working with Azure DevOps, managing pipelines, creating work items, or when user mentions ADO, builds, releases, or Azure repos.

Expert backlog manager that prioritizes work using multi-criteria scoring, analyzes dependencies, and recommends optimal next tasks. Activates when managing backlogs, prioritizing work, adding items, or analyzing what to work on next.

Run Microsoft's eval-recipes benchmarks to validate amplihack improvements against baseline agents. Activates when testing with eval-recipes, running evals, or benchmarking changes.

Expert knowledge of Microsoft Agent Framework for building production AI agents and workflows. Use when building agents with Microsoft's framework, multi-agent orchestration, or tool integration.

Expert project manager orchestrating backlog-curator, work-delegator, workstream-coordinator, and roadmap-strategist sub-skills. Coordinates complex software projects through delegation and strategic oversight. Activates when managing projects, coordinating work, or tracking overall progress.

Expert strategist managing project roadmaps, goals, milestones, and strategic direction. Tracks goal progress, ensures alignment, and provides strategic recommendations. Activates when planning roadmaps, setting goals, tracking milestones, or discussing strategic direction.

Expert delegation specialist that creates comprehensive context packages for coding agents, analyzes requirements, identifies relevant files, and generates clear instructions. Activates when delegating work, assigning tasks, creating delegation packages, or preparing agent instructions.

Expert workstream coordinator managing multiple concurrent tasks, tracking progress, detecting conflicts and stalls, analyzing dependencies, and ensuring smooth parallel execution. Activates when coordinating workstreams, tracking progress, checking status, or managing concurrent work.

Reference guide for LLM-based vulnerability detection in binary code. Provides best practices, techniques, and prompting strategies for using LLMs to find vulnerabilities in stripped binaries, firmware, and decompiled code. Use when analyzing binaries with AI, writing vulnerability analysis prompts, or optimizing detection pipelines.

Comprehensive binary security assessment including hardening, attack surface, and vulnerability analysis. Use when analyzing an ELF or PE binary.

Compare two binaries for security differences. Use for patch analysis or regression testing.

Look up CWE entries and explain their relevance. Use when discussing vulnerability types or CWE classifications.

Explain a specific vulnerability finding in detail with remediation guidance. Use when the user wants to understand a finding or how to fix it.

Multi-language source code security audit. Use when analyzing source code for vulnerabilities. Supports Python, JavaScript, Go, Rust, Java, C/C++.

Generate a threat model for the analyzed target. Use after ingesting a binary or source code to understand the threat landscape.

Run a comprehensive vulnerability scan on the current investigation. Use when the user wants to find security vulnerabilities in ingested code or binaries. Combines pattern detection, data flow analysis, and AI reasoning.

Comprehensive knowledge of LadybugDB, the active community fork of the archived Kuzu graph database. Covers the Python SDK (real_ladybug package), Cypher query language, vector search extensions, full-text search, graph algorithms, import/export, and migration from Kuzu.

Knowledge graph pack manager. Build, install, list, query, and update domain-expert knowledge packs. Use when user says /kg-pack or wants to add expert knowledge to Claude Code.

Expert physics knowledge from curated Wikipedia articles

Generates a plain-language illustrated walkthrough for non-trivial pull requests at the end of default-workflow. Detects the hosting platform (GitHub or Azure DevOps) from the git remote, skips trivial PRs with configurable thresholds, and produces a reviewer-oriented markdown document that explains the problem, the approach, and the step-by-step implementation with code snippets, mermaid diagrams, deep links to the diff, and — when GUI or TUI paths change — embedded screenshots. Use when: a non-trivial PR has just been opened and an unfamiliar reviewer needs a clear, complete, jargon-free explanation of what changed and why.