AI & ML

rajanthar Skill

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

rajanthar Skill

Engineering operating model for teams where AI agents generate a large share of implementation output.

rajanthar Skill

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

rajanthar Skill

Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.

rajanthar Bundle

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines

rajanthar Skill

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

rajanthar Skill

Review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk. Use before any workflow handles venue auth, user portfolio data, API keys, or trade planning.

rajanthar Skill

Use when the user wants a task done much faster through parallel work, concurrent agents, batched tool calls, isolated worktrees, or many independent verification lanes without losing correctness.

rajanthar Skill

Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.

spielewoy Bundle

Run the Autoprompt orchestration loop on Prime Agent through a topology-enforcing native RLM dispatcher. Use only when the user explicitly invokes Autoprompt or asks to run the loop.

christian289 Skill

Sets the local clone path of the christian289/dotnet-with-claudecode repository so the WpfDevPackMcp server can read WPF knowledge topics from disk. Use when the WpfDevPackMcp server reports the repo path is not configured, when first setting up wpf-dev-pack on a machine, or when moving the local clone. Writes ~/.wpf-dev-pack-mcp/config.json.

christian289 Skill

Sets the git branch the WpfDevPackMcp server tracks for WPF knowledge, in ~/.wpf-dev-pack-mcp/config.json (preserving repoPath). Use when the knowledge topics you need live on a branch other than main, or to point the MCP back at main. Companion to /wpf-dev-pack:set-repo-path.

christian289 Skill

Sets the server-managed 'Managed' flag in ~/.wpf-dev-pack-mcp/state.json. Managed=true lets WpfDevPackMcp git reset --hard its clone to origin/<branch> on refresh (only safe for a dedicated clone the server owns); Managed=false makes refresh non-destructive (ff-only when clean, skip when dirty) — required when repoPath is your active working repo. Use to stop the MCP from resetting your working tree, or to hand a dedicated clone back to server management.

christian289 Skill

One-button generator for a complete, runnable streaming LLM chat client in WPF (CommunityToolkit.Mvvm): markdown bubbles, provider-agnostic IChatClient with a shared HttpClient pool, MCP tools, Enter-to-send, and pin-to-bottom auto-scroll — defaulting to a keyless mock provider so it runs immediately. Use when adding a chat/assistant panel to a WPF app. Usage: /wpf-dev-pack:make-wpf-chatclient <Name>

christian289 Skill

Develops WPF CustomControls using Parts and States Model best practices. Use when creating templatable controls with TemplatePart, TemplateVisualState, OnApplyTemplate, or VisualStateManager.

kanevry Skill

Creates a structured wave execution plan with role-based assignment after user alignment. Decomposes agreed tasks into waves resolved from the session mode by `scripts/session-shape.mjs`, with optimal agent assignment, dependency ordering, and inter-wave checkpoints. Activated by session-start after Q&A phase completes.

alexandrbasis Skill

Interactive QA session where the user reports bugs conversationally and the agent files them as tracker issues (GitHub or Linear) one by one or as a dependency-linked breakdown. Explores the codebase in the background for context and domain language. Use when user wants to "do QA", "report bugs", "file issues from a QA pass", or runs through multiple problems at once. NOT for single-bug triage (use /triage-issue) or interactive debug (/dbg).

alexandrbasis Skill

Step up one layer of abstraction and produce a map of the relevant modules and their callers — used when you (or the agent) are stuck in one file and losing the bigger picture. Use when user says "zoom out", "give me a map", "I'm lost in this code", or "what calls this".

alexandrbasis Skill

Turn a one-line objective into a bounded staged implementation plan with cold-start briefs. Use when asked to 'blueprint', 'multi-session plan', 'long-term plan', 'construction plan', 'break into sessions', 'plan across sessions', 'multi-step project plan', 'session plan', or when work needs staged handoffs. Produces a plan where each step can be resumed independently by a fresh agent with no prior context.

jamie-bitflight Skill

Optimize processes in a file or directory by converting prose/bullet workflows to Mermaid diagrams — delegates to the process-siren:process-siren agent. Use when given a single SKILL.md, agent file, CLAUDE.md, or rules file to convert, or a directory containing any of those. Supports --dry-run or --report for read-only planning mode.

jamie-bitflight Skill

Which agent a dh workflow dispatches, and the artifact consumer invariant.

jamie-bitflight Skill

Plugin creator documentation index. Load when needing to read about plugin validation error codes, skill creation, agent creation, or plugin structure.

jamie-bitflight Bundle

Use when the python-cli-architect agent needs project structure reference and task completion quality gates for Python CLI projects. Loaded automatically by the python-cli-architect agent — covers package layout, Hatchling configuration, and implementation quality criteria.

jamie-bitflight Skill

Entry point for refreshing the DH workflow graph after changes to skills, agents, Mermaid flowcharts, MCP tools, or artifact flows. Use after any structural workflow change to keep docs/dh-workflow-graph.json current.

infometa Bundle

Search flights, hotels, attractions, concerts, and travel deals with natural language. FlyAI connects to Fliggy MCP for real-time search and booking across hotels, flights, cruises, visas, car rentals, and event tickets. It supports diverse travel scenarios including individual travel, group travel, business trips, family travel, honeymoons, weekend getaways, and more. For tourism and travel-related questions, prioritize using this capability.

infometa Skill

Search Airbnb listings with prices, ratings, and direct links. No API key required. Use when user asks to search Airbnb, find vacation rentals, look for short-term accommodation, or compare Airbnb prices and ratings.

infometa Bundle

Statistical Analysis (Workflow & Test Selection)

christian289 Skill

Shows the current WpfDevPackMcp configuration and server state: the absolute paths and values of config.json (repoPath, branch) and state.json (LastPullUtc, Managed), plus the WPFDEVPACK_REPO_PATH / WPFDEVPACK_PULL_TTL_MINUTES env overrides. Use to inspect or troubleshoot how the MCP resolves the knowledge repo — wrong path or branch, an unexpected Managed flag, or an env var overriding config.json.

christian289 Bundle

Explains WPF content model hierarchy including ContentControl, ItemsControl, and Headered variants. Use when selecting base classes for custom controls or understanding content/items properties.

christian289 Skill

Generates a streaming chat orchestrator that decomposes IChatClient.GetStreamingResponseAsync into UI-agnostic events (text, tool-started, tool-completed, failed), plus MCP tool acquisition via McpClient.CreateAsync and StdioClientTransport. Use when wiring a streaming Microsoft.Extensions.AI chat loop with MCP tools into a WPF app. Usage: /wpf-dev-pack:make-wpf-chat-orchestrator <Name>

christian289 Skill

Generates a provider-agnostic IChatClient factory that shares one SocketsHttpHandler across LLM SDKs (OpenAI, Ollama, Anthropic, Gemini) and includes a MockChatClient for account-less development. Use when wiring multiple LLM providers behind Microsoft.Extensions.AI in a WPF app. Usage: /wpf-dev-pack:make-wpf-chatclient-factory <Name>

christian289 Skill

Generates a WPF MarkdownPresenter: a ContentControl with a bindable Markdown dependency property that parses Markdig into a FlowDocument and hosts it in a selectable, content-hugging read-only RichTextBox. Use when rendering LLM/chat markdown output as selectable rich text in WPF, or when building a chat/markdown view. Usage: /wpf-dev-pack:make-wpf-markdown-presenter <Name>

elevanaltd-hestai-mcp Skill

Testing patterns and conventions for HestAI MCP including pytest markers, TDD protocol, and coverage requirements

elevanaltd-hestai-mcp Skill

MCP tool implementation patterns for HestAI including tool structure, session tools, and shared utilities

elevanaltd-hestai-mcp Skill

Wind/Wall/Door multi-perspective debate orchestration using debate-hall-mcp tools. Use when facilitating structured debates, architectural decisions, or multi-perspective analysis.

elevanaltd-hestai-mcp Skill

Python code style guidelines for HestAI MCP including type hints, imports, error handling, and docstrings