all publishers

rysweet

@rysweet source repo

242 published skills · page 1 of 3

  1. ▌
    E2e Outside In Test Generator 2 · rysweet bundle
    Generates comprehensive end-to-end test scenarios using outside-in methodology. Supports Web (Playwright), CLI, TUI, API, and MCP/gadugi-style scenarios. Auto-detects app type or accepts explicit override.
    76 repo stars
  2. ▌
    Microsoft Agent Framework 2 · rysweet bundle
    Comprehensive knowledge of Microsoft Agent Framework for building production AI agents and workflows. Auto-activates for agent building, workflow design, AutoGen migration, and enterprise AI tasks.
    76 repo stars
  3. ▌
    Goal Seeking Agent Pattern 2 · rysweet bundle
    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.
    76 repo stars
  4. ▌
    Model Evaluation Benchmark · rysweet
    Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for model benchmarking, comparison evaluation, or performance testing between AI models.
    76 repo stars
  5. ▌
    Goal Seeking Agent Pattern 4 · rysweet bundle
    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.
    76 repo stars
  6. ▌
    Documentation Writing 2 · rysweet bundle
    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. For prose style, or editing text written by a language model, use journalistic-writing-style instead.
    76 repo stars
  7. ▌
    Microsoft Agent Framework 4 · rysweet bundle
    Microsoft Agent Framework Skill
    76 repo stars
  8. ▌
    Outside In Testing · rysweet bundle
    Deprecated compatibility alias for qa-team. Use when existing recipes or agents still invoke outside-in-testing by name. Redirects future work to the qa-team skill for outside-in validation and parity loops.
    76 repo stars
  9. ▌
    Transcript Viewer 2 · rysweet
    Convert and browse session transcripts as HTML or Markdown. Supports Claude Code JSONL logs (auto-saved to ~/.claude/projects/) and GitHub Copilot CLI JSONL logs (auto-saved to ~/.copilot/session-state/*/events.jsonl). Auto-detects log source based on available directories and file format. Supports viewing the current session, a specific session by ID, agent background task output files, or all project sessions with optional date-range filtering.
    76 repo stars
  10. ▌
    Documentation Writing · rysweet bundle
    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. For prose style, or editing text written by a language model, use journalistic-writing-style instead.
    76 repo stars
  11. ▌
    Dev Orchestrator 2 · rysweet bundle
    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.
    76 repo stars
  12. ▌
    Auto Drive To Merge · rysweet
    Wraps default-workflow and drives the resulting PR all the way to merge: build the PR, loop with the crusty-old-engineer skill as the maintainer's proxy until its verdict is CLEAN or lists minor findings only (each filed as a follow-up issue linked to the plan task), then loop on the merge-ready criteria — qa-team scenarios, CI, conflicts, review threads — until every one holds, and merge behind an evidence gate. Both loops are terminated by agentic loop-health evaluation, never by an iteration count. Use when: "drive this to merge", "take this all the way", "build it and land it".
    76 repo stars
  13. ▌
    Cascade Workflow 2 · rysweet
    Graceful degradation through cascading fallback strategies - ensures system always completes while maintaining acceptable functionality
    76 repo stars
  14. ▌
    Transcript Viewer 4 · rysweet bundle
    Convert and browse session transcripts as HTML or Markdown. Supports Claude Code JSONL logs (auto-saved to ~/.claude/projects/) and GitHub Copilot CLI JSONL logs (auto-saved to ~/.copilot/session-state/*/events.jsonl). Auto-detects log source based on available directories and file format. Supports viewing the current session, a specific session by ID, agent background task output files, or all project sessions with optional date-range filtering.
    76 repo stars
  15. ▌
    Signal Setup · rysweet bundle
    End-to-end, idempotent Signal device-linking for amplihack on a local or remote (azlin VM) host. Runs the full loop in one invocation: prerequisite check, prompt to open the phone's scan screen, mint a fresh device-link under systemd-run, render the QR DIRECTLY in the terminal (zero delivery latency, ANSIUTF8i inverted for dark terminals), verify linkage, and optionally start the JSON-RPC daemon, ensure the amplihack self-group, and post a test message. Use when onboarding a host to the amplihack Signal channel, when a prior link attempt showed "invalid response from server", or when you need to re-link / verify a fleet host's Signal account.
    76 repo stars
  16. ▌
    Claude Agent Sdk 2 · rysweet bundle
    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.
    76 repo stars
  17. ▌
    Default Workflow 3 · rysweet
    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.
    76 repo stars
  18. ▌
    Amplihack Migrate · rysweet bundle
    Move the active amplihack CLI session (Copilot/Claude/Amplifier) to a fresh azlin-managed VM, preserving auth, plugins, skills, plan.md, todos, and conversation history. Resumes the session in a detached tmux on the destination host.
    76 repo stars
  19. ▌
    QA Team 2 · rysweet bundle
    QA team for outside-in validation, side-by-side parity loops, and A/B behavioral comparison. Use when you need behavior-driven tests, legacy-vs-new comparison, or rollout shadow validation. Creates executable scenarios and parity workflows that agents can observe, compare, and iterate on. Supports local, observable tmux, remote SSH, and shadow-mode divergence logging patterns.
    76 repo stars
  20. ▌
    Merge Ready 2 · rysweet bundle
    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.
    76 repo stars
  21. ▌
    Cascade Workflow 3 · rysweet
    Graceful degradation through cascading fallback strategies - ensures system always completes while maintaining acceptable functionality
    76 repo stars
  22. ▌
    Signal · rysweet
    Drive an agent session from a Signal group chat. Opens an operator-only Signal group for a topic and turns every operator message into a real agent prompt with full session context.
    76 repo stars
  23. ▌
    QA Team 3 · rysweet bundle
    QA team for outside-in validation, side-by-side parity loops, and A/B behavioral comparison. Use when you need behavior-driven tests, legacy-vs-new comparison, or rollout shadow validation. Creates executable scenarios and parity workflows that agents can observe, compare, and iterate on. Supports local, observable tmux, remote SSH, and shadow-mode divergence logging patterns.
    76 repo stars
  24. ▌
    Claude Profile Rotation · rysweet
    Set up and run automatic rotation of the default Claude login in ~/.claude across several amplihack login profiles, so plain `claude` always uses the account with the most session and weekly capacity. Use when the user has more than one Claude account, hits usage limits, asks to rotate or swap Claude logins, or mentions the claude-rotator tmux session.
    76 repo stars
  25. ▌
    Github Copilot CLI Expert · rysweet bundle
    Expert knowledge of GitHub Copilot CLI - installation, configuration, usage, custom agents, MCP servers, and version management. Use when asking about copilot cli, copilot commands, installing copilot, updating copilot, copilot features.
    76 repo stars
  26. ▌
    Journalistic Writing Style · rysweet
    A journalistic writing style for correcting long-form text produced by language models. Use it when drafting, editing or reviewing any document where clarity, simplicity and neutrality are wanted: reports, memos, research notes, engineering plans, README files, status files and conversational replies. For the structure, placement or Diataxis type of software documentation, use documentation-writing instead.
    76 repo stars
  27. ▌
    Gh Aw Adoption 2 · rysweet bundle
    Adopt GitHub Agentic Workflows (gh-aw) in any repository. Investigates existing workflows, identifies gaps, creates agentic workflows, and handles CI/merge issues. Auto-activates for gh-aw adoption, agentic workflow setup, or workflow automation requests.
    76 repo stars
  28. ▌
    Session Replay 2 · rysweet bundle
    Analyze claude-trace JSONL files for session health, patterns, and actionable insights. Use when debugging session issues, understanding token usage, or identifying failure patterns.
    76 repo stars
  29. ▌
    Github Copilot CLI 2 · rysweet bundle
    Expert knowledge of GitHub Copilot CLI - installation, configuration, usage, MCP servers, skills, custom agents, and troubleshooting. Use when asking about copilot cli, installing copilot, gh copilot, copilot commands, MCP setup, or copilot extensibility.
    76 repo stars
  30. ▌
    Github Copilot Sdk · rysweet bundle
    Comprehensive knowledge of GitHub Copilot SDK for embedding Copilot's agentic workflows in Python, TypeScript, Go, and .NET applications. Auto-activates for Copilot SDK integration, CopilotClient usage, session management, streaming responses, custom tools, and MCP server connections.
    76 repo stars
  31. ▌
    Fleet 2 · rysweet
    Fleet orchestration for distributed coding agents across Azure VMs. Invoked as `/fleet <command>`. Covers all fleet operations: status, scout, advance, adopt, watch, snapshot, dry-run, start, add-task, queue, auth, dashboard, tui, and more. Use when: user mentions fleet, agents, VMs, sessions, or asks "what are my agents doing".
    76 repo stars
  32. ▌
    Markitdown 2 · rysweet bundle
    Convert documents (PDF, Word, Excel, PowerPoint, images, HTML) to Markdown using microsoft/markitdown. Use for document analysis, content extraction, preprocessing for LLMs, or batch document conversion. Supports images with OCR/LLM descriptions, audio transcription, and ZIP archives.
    76 repo stars
  33. ▌
    Smart Test 4 · rysweet bundle
    Intelligent test selection based on code changes. Maps source files to tests via import analysis, implements tiered testing (fast < 1 min, impacted < 5 min, full suite), and tracks test reliability. Use when running tests after code changes to optimize feedback loops and CI time.
    76 repo stars
  34. ▌
    Azure Admin 4 · rysweet bundle
    Azure Administration Skill
    76 repo stars
  35. ▌
    Investigation Workflow 5 · rysweet
    6-phase investigation workflow for understanding existing systems. Auto-activates for research tasks. Optimized for exploration and understanding, not implementation. Includes parallel agent deployment for efficient deep dives and automatic knowledge capture to prevent repeat investigations.
    76 repo stars
  36. ▌
    Ultrathink Orchestrator 4 · rysweet bundle
    Auto-invokes ultrathink workflow for any work request (default orchestrator)
    76 repo stars
  37. ▌
    Eval Recipes Runner 4 · rysweet bundle
    eval-recipes Runner Skill
    76 repo stars
  38. ▌
    Philosophy Compliance Workflow 3 · rysweet
    Philosophy compliance guardian - ensures code aligns with amplihack's ruthless simplicity, brick philosophy, and Zen-like minimalism through systematic review
    76 repo stars
  39. ▌
    PPTX 3 · rysweet bundle
    Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
    76 repo stars
  40. ▌
    Azure Devops 3 · rysweet bundle
    Complete Azure DevOps automation - boards, repos, pipelines, artifacts
    76 repo stars
  41. ▌
    Pm Architect 3 · rysweet bundle
    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.
    76 repo stars
  42. ▌
    Debate Workflow 3 · rysweet
    Structured multi-perspective debate for important architectural decisions and complex trade-offs
    76 repo stars
  43. ▌
    Cascade Workflow 4 · rysweet
    Graceful degradation through cascading fallback strategies - ensures system always completes while maintaining acceptable functionality
    76 repo stars
  44. ▌
    Default Workflow 4 · rysweet
    Development workflow for features, bugs, refactoring. Auto-activates for multi-file implementations.
    76 repo stars
  45. ▌
    N Version Workflow 4 · rysweet
    N-version programming for critical implementations - generates N independent solutions and selects the best through comparison
    76 repo stars
  46. ▌
    Microsoft Agent Framework 5 · rysweet bundle
    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.
    76 repo stars
  47. ▌
    Github 2 · rysweet bundle
    GitHub CLI Skill
    76 repo stars
  48. ▌
    Lsp Setup 2 · rysweet bundle
    Auto-discovers and configures Language Server Protocol (LSP) servers for your project's languages
    76 repo stars
  49. ▌
    Skill Builder 3 · rysweet bundle
    Creates, refines, and validates Claude Code skills following amplihack philosophy and official best practices. Automatically activates when building, creating, generating, or designing new skills.
    76 repo stars
  50. ▌
    XLSX 3 · rysweet bundle
    Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
    76 repo stars
  51. ▌
    Azure Admin 3 · rysweet bundle
    Azure Administration Skill
    76 repo stars
  52. ▌
    MCP Manager 2 · rysweet
    Conversational interface for managing MCP (Model Context Protocol) server configurations in Claude Code
    76 repo stars
  53. ▌
    Remote Work 2 · rysweet
    Execute amplihack work on remote Azure VMs with automatic region and resource selection
    76 repo stars
  54. ▌
    Work Delegator 3 · rysweet bundle
    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.
    76 repo stars
  55. ▌
    Backlog Curator 2 · rysweet bundle
    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.
    76 repo stars
  56. ▌
    Roadmap Strategist 2 · rysweet
    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.
    76 repo stars
  57. ▌
    Eval Recipes Runner 3 · rysweet
    Run Microsoft's eval-recipes benchmarks to validate amplihack improvements against baseline agents. Activates when testing with eval-recipes, running evals, or benchmarking changes.
    76 repo stars
  58. ▌
    Workstream Coordinator 3 · rysweet bundle
    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.
    76 repo stars
  59. ▌
    Ultrathink Orchestrator 3 · rysweet bundle
    Auto-invokes ultrathink workflow for any work request (default orchestrator)
    76 repo stars
  60. ▌
    PDF 2 · rysweet bundle
    Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
    76 repo stars
  61. ▌
    DOCX 4 · rysweet bundle
    Create, edit, and analyze Word documents with tracked changes support
    76 repo stars
  62. ▌
    PPTX 2 · rysweet bundle
    Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
    76 repo stars
  63. ▌
    Aspire 2 · rysweet bundle
    Aspire orchestration for cloud-native distributed applications in any language (C#, Python, Node.js, Go). Handles dependency management, local dev with Docker, Azure deployment, service discovery, and observability dashboards. Use when setting up microservices, containerized apps, or polyglot distributed systems.
    76 repo stars
  64. ▌
    Quality Audit 4 · rysweet bundle
    Iterative codebase quality audit with multi-agent validation and escalating-depth SEEK/VALIDATE/FIX/RECURSE cycle. Enforces fix-all-per-cycle rule — every confirmed finding must be fixed before moving to the next cycle. Use for quality audit, code audit, codebase review, technical debt audit, refactoring opportunities, module quality check, or architecture review.
    76 repo stars
  65. ▌
    Multitask 2 · rysweet bundle
    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.
    76 repo stars
  66. ▌
    Code Atlas 2 · rysweet bundle
    Builds comprehensive, living code-atlases as multi-layer architecture documents derived from code-first truth. Defaults to both Graphviz DOT and Mermaid. User can override to single format. Language-agnostic (Go, TypeScript, Python, .NET, Rust, Java). Files issues with 'code-atlas-bughunt' label. Treats atlas-building as a multi-agent bug-hunting journey: graph-form reasoning exposes structural bugs, route/DTO mismatches, orphaned env vars, dead code paths, and stale documentation that linear review misses. Three-pass bug hunt with per-journey PASS/FAIL/NEEDS_ATTENTION verdicts. Use when: creating architecture documentation, investigating unfamiliar codebases, hunting structural bugs, setting up CI/CD diagram refresh, or publishing to GitHub Pages/mkdocs.
    76 repo stars
  67. ▌
    Smart Test 3 · rysweet bundle
    Intelligent test selection based on code changes. Maps source files to tests via import analysis, implements tiered testing (fast < 1 min, impacted < 5 min, full suite), and tracks test reliability. Use when running tests after code changes to optimize feedback loops and CI time.
    76 repo stars
  68. ▌
    Code Visualizer 3 · rysweet bundle
    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.
    76 repo stars
  69. ▌
    Tla Plus Expert 4 · rysweet
    TLA+ formal specification expert for writing specs, model checking, and applying formal methods to amplihack workflows
    76 repo stars
  70. ▌
    Azure Devops 2 · rysweet bundle
    Complete Azure DevOps (ADO) automation — work items, boards, sprints, repos, pull requests, pipelines, builds, artifacts. Use when user mentions ADO, work items, user stories, bugs, sprints, builds, releases, or Azure DevOps URLs.
    76 repo stars
  71. ▌
    Pm Architect 2 · rysweet bundle
    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.
    76 repo stars
  72. ▌
    Fleet Copilot 2 · rysweet
    Autonomous co-pilot — agent formulates goal from natural language, enables lock mode with SessionCopilot reasoning, works until goal is achieved.
    76 repo stars
  73. ▌
    N Version Workflow 3 · rysweet
    N-version programming for critical implementations - generates N independent solutions and selects the best through comparison
    76 repo stars
  74. ▌
    Gh Work Report 2 · rysweet bundle
    Generates comprehensive GitHub activity reports across all authenticated accounts. Gathers repos, PRs, features, and themes for configurable time periods (1/5/7/30/90 days). Produces shareable markdown with tables, mermaid charts, and executive summaries. Can create a private repo with GitHub Actions automation and GitHub Pages aggregation site. Use when: "github report", "work report", "activity summary", "what did I work on", "gh-work-report", "show my github activity".
    76 repo stars
  75. ▌
    Gherkin Expert 2 · rysweet
    Gherkin/BDD expert for writing, reviewing, and refactoring Cucumber feature files and step definitions.
    76 repo stars
  76. ▌
    Code Smell Detector 2 · rysweet bundle
    Identifies anti-patterns specific to amplihack philosophy. Use when reviewing code for quality issues or refactoring. Detects: over-abstraction, complex inheritance, large functions (>50 lines), tight coupling, missing __all__ exports. Provides specific fixes and explanations for each smell.
    76 repo stars
  77. ▌
    Knowledge Extractor 4 · rysweet bundle
    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.discoveries), suggests PATTERNS.md updates, and recommends new agent creation. Ensures knowledge persists across sessions via Kuzu memory backend.
    76 repo stars
  78. ▌
    Pr Review Assistant 2 · rysweet bundle
    Philosophy-aware PR reviews checking alignment with amplihack principles. Use when reviewing PRs to ensure ruthless simplicity, modular design, and zero-BS implementation. Suggests simplifications, identifies over-engineering, verifies brick module structure. Posts detailed, constructive review comments with specific file:line references.
    76 repo stars
  79. ▌
    Debate Workflow 2 · rysweet
    Structured multi-perspective debate for important architectural decisions and complex trade-offs
    76 repo stars
  80. ▌
    Testing Code 2 · rysweet
    Generates and improves tests following TDD principles. Activates when new features are implemented, test coverage is low, or user requests tests. Ensures comprehensive test coverage with unit, integration, and edge case tests.
    76 repo stars
  81. ▌
    Amplihack Expert 2 · rysweet bundle
    Comprehensive knowledge of amplihack framework architecture, patterns, and usage
    76 repo stars
  82. ▌
    Session Learning 2 · rysweet bundle
    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.
    76 repo stars
  83. ▌
    Investigation Workflow 4 · rysweet
    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.
    76 repo stars
  84. ▌
    Reviewing Code 2 · rysweet
    Performs systematic code review checking for correctness, maintainability, security, and best practices. Activates when user requests review, before creating PRs, or when significant code changes are ready. Ensures quality gates are met before code proceeds to production.
    76 repo stars
  85. ▌
    Pre Commit Manager 2 · rysweet bundle
    Manage pre-commit hooks with preference memory and template-based configuration. Use when installing, configuring, enabling/disabling, or checking status of pre-commit hooks. Supports templates for python, javascript, typescript, go, rust, and generic projects.
    76 repo stars
  86. ▌
    Supply Chain Audit 2 · rysweet bundle
    Auditing software supply chain security across CI/CD pipelines, container images, and language ecosystems. Detects mutable dependency references, insecure CI patterns, credential exposure risks, and missing SBOM/SLSA controls. Use when performing a supply chain audit, checking action pinning, auditing dependencies, scanning for CI security issues, reviewing container security, or assessing dependency security. Covers GitHub Actions, containers, Python, Node, Go, Rust, .NET, and more.
    76 repo stars
  87. ▌
    Awesome Copilot Sync 2 · rysweet
    Monitors awesome-copilot releases for drift against the amplihack integration. Checks latest commits on github/awesome-copilot via the GitHub API and reports whether the local integration is current or has drifted behind upstream changes. Use when auditing integration freshness or before updating awesome-copilot features.
    76 repo stars
  88. ▌
    Workflow Enforcement 2 · rysweet bundle
    Workflow step compliance guidance with mandatory step reminders and visual progress tracking. Reminds Claude to complete all workflow steps before PR creation.
    76 repo stars
  89. ▌
    Silent Degradation Audit 2 · rysweet bundle
    Production-ready skill for detecting silent degradation across codebases. Uses multi-wave audit system with 6 specialized category agents, multi-agent validation panel, and convergence detection.
    76 repo stars
  90. ▌
    Dotnet Exception Handling 2 · rysweet bundle
    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.
    76 repo stars
  91. ▌
    Self Improving Agent Builder 2 · rysweet
    Encodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle".
    76 repo stars
  92. ▌
    Philosophy Compliance Workflow 2 · rysweet
    Philosophy compliance guardian - ensures code aligns with amplihack's ruthless simplicity, brick philosophy, and Zen-like minimalism through systematic review
    76 repo stars
  93. ▌
    Setting Up Projects 2 · rysweet
    Automates project setup with best practices including pre-commit hooks, linting, formatting, and boilerplate. Activates when creating new projects, missing configuration files, or setting up development environment. Ensures quality tooling from the start.
    76 repo stars
  94. ▌
    Creating Pull Requests 2 · rysweet
    Creates high-quality pull requests with comprehensive descriptions, test plans, and context. Activates when user wants to create PR, says 'ready to merge', or has completed feature work. Analyzes commits and changes to generate meaningful PR descriptions.
    76 repo stars
  95. ▌
    DOCX 3 · rysweet bundle
    Create, edit, and analyze Word documents with tracked changes support
    76 repo stars
  96. ▌
    Skill Builder 2 · rysweet bundle
    Creates, refines, and validates Claude Code skills following amplihack philosophy and official best practices. Automatically activates when building, creating, generating, or designing new skills.
    76 repo stars
  97. ▌
    Model Evaluation Benchmark 2 · rysweet
    Model Evaluation Benchmark Skill
    76 repo stars
  98. ▌
    Verus Expert 2 · rysweet
    Verus deductive-verification expert for proving Rust functional correctness, panic-freedom, and arithmetic-overflow-freedom with SMT-backed specs and LLM-assisted proof synthesis
    76 repo stars
  99. ▌
    Auto Drive To Merge 2 · rysweet
    Wraps default-workflow and drives the resulting PR all the way to merge: build the PR, loop with the crusty-old-engineer skill as the maintainer's proxy until zero concerns remain, then loop on the merge-ready criteria — qa-team scenarios, CI, conflicts, review threads — until every one holds, and merge behind an evidence gate. Both loops are terminated by agentic loop-health evaluation, never by an iteration count. Use when: "drive this to merge", "take this all the way", "build it and land it".
    76 repo stars
  100. ▌
    Crusty Old Engineer 2 · rysweet bundle
    Curmudgeonly engineering advisor that provides grounded skepticism, evidence-linked judgment, and constructive progress on architectural decisions, legacy refactors, tooling choices, and broad "how should I start?" questions. Sounds like a senior systems engineer who has reviewed too many designs to be impressed, but still cares about correctness. Use when: architectural decisions, legacy replacements, new tooling evaluation, broad planning questions.
    76 repo stars