Find workflows for designing, testing, and maintaining reusable agent capabilities.
73 skills
25 engineering workflows for requirements, planning, implementation, testing, review, performance and production delivery.
Plan page hierarchy, navigation, URLs and internal links for a coherent website.
Frame social-science research questions, literature maps, evidence routes and defensible claims, then review novelty and feasibility.
Develop rough ideas into implementation plans with explicit decisions and handoff details.
25 engineering workflows for requirements, planning, implementation, testing, review, performance and production delivery.
Plan page hierarchy, navigation, URLs and internal links for a coherent website.
Frame social-science research questions, literature maps, evidence routes and defensible claims, then review novelty and feasibility.
Develop rough ideas into implementation plans with explicit decisions and handoff details.
Plan paid campaign structure, audiences, budget allocation and optimization priorities.
Plan portraits, couple, wedding and family photography through direction choices, looks, scene zones, poses and shot lists.
Use an Adlerian psychology framework to examine procrastination or interrupted action when you already know what you intend to do.
Update the official dbskill collection while preserving other installed skills and user archives.
Compile documents, research papers, and notes into a persistent knowledge wiki with source citations and reusable context retrieval.
Rewrite a vague question into a brief an agent can reason about, critique, and verify, and assess how much of it can be automated.
Generate an MCP server from an OpenAPI or Swagger specification using the mcp-use TypeScript SDK.
Convert specifications into ordered, independently verifiable tasks with dependencies and acceptance criteria.
Plan illustrations at useful points in an article, keep the visual style consistent and insert supplied images into Markdown.
Audit agent configuration, instruction drift, hooks, and MCP setup.
Organize project rules, task context and references so coding agents receive relevant information at the right time.
Use two reasoning agents to reassess a difficult problem, investigate root causes and produce a plan.
Ask Claude Code or Codex how one app feature works, get the code evidence, and plan your own implementation with REA.
Inspect session context savings, consumption ratios, and per-tool usage statistics.
Review AI engineering, learning and product questions through software paradigms, building to understand and reliability engineering.
Operate Unity Editor scenes, GameObjects, scripts, and tests through MCP tools and resources.
Recall relevant context, summarize sessions and preserve durable memories through a configured Memori MCP connection.
Write and refine prompts for a specified language model, coding assistant, image tool, or video tool.
Switch connected Unity projects between released, branch, and local MCP for Unity package sources.
Extract a central message and audience from article text or subtitles, then design a cover image prompt.
Turn an unclear intention into a concrete deliverable with scope, constraints, and observable acceptance criteria.
Choose, clarify, combine, or compare the relevant skills for your current task, then continue working in the same conversation.
Keep final artifacts, labels, commits, and handoffs focused on accepted requirements after a conversation includes corrections or discarded proposals.
Create reusable launch, interaction and verification instructions for an explicitly selected application.
Turn copy, notes, or a topic into a stickman director’s proposal, English narration, and standalone video prompts. Choose a visual style, 16:9 or 9:16, and a duration in ten-second increments.
Audit project rules, identify their source of truth, standardize naming, and build bridges for consistent use across agent hosts.
Design and implement MCP servers with discoverable tools, clear schemas and task-based evaluations.
Choose marketing tactics according to product stage, budget, timeline and growth goals.
Turn a rough goal into an agent task brief with researched constraints and acceptance criteria.
Plan phased launches and coordinate owned, rented and borrowed distribution channels.
Turn a recurring problem into one installable skill through needs analysis and staged validation; prepare public distribution only when requested.
Remove context-mode knowledge and session data using the supported project or session scope.
Explore startup and builder ideas through structured questions and produce a design document before implementation.
Diagnose context-mode runtimes, hooks, plugin registration, search support, and installed versions.
Design a knowledge video around a learning objective, evidence, script and storyboard before production.
Turn a poster brief into structured prompts with audience, message, density, emotion, color and illustration style.
Open the context-mode Insight dashboard for team engineering analytics.
Index bounded local files and directories in context-mode for later focused retrieval.
Install, synchronize, inspect, deduplicate, or uninstall individual skills and collections across compatible agent hosts.
Build TypeScript MCP servers and MCP Apps with mcp-use tools, resources, views, and authentication.
Research business context and develop a reviewed marketing plan across acquisition and retention.
Create and improve reusable skills with test cases, comparative evaluations and trigger-description refinement.
Build prompts with distinct character and scene visual languages, combining two drawn styles or drawing with realism.
Map incoming engineering work to the relevant workflows in Addy's Agent Skills collection.
Find workflows for designing, testing, and maintaining reusable agent capabilities.