Skip to content
Back to search

ai-design-skills

MarketplaceWorks with Claude CodeGitHub

AI Design Skills Collection: agentic skills, commands, and plugins for designing AI products — from interaction patterns to alignment, evaluation, agent orchestration, and prompt architecture.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/owl-listener--ai-design-skills/badge.svg)](/listings/owl-listener--ai-design-skills)

HTML

<a href="/listings/owl-listener--ai-design-skills"><img src="/api/listings/owl-listener--ai-design-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Pick the install command for your agent.

Claude Code

Add the marketplace, then install plugins from it.

claude plugin marketplace add Owl-Listener/ai-design-skills
claude plugin install model-interaction-design@ai-design-skills

To install all six plugins at once:

for p in model-interaction-design ai-alignment-reasoning system-behavior-shaping evaluation design-agent-orchestration prompt-architecture; do
  claude plugin install "$p@ai-design-skills"
done

Gemini CLI

Gemini CLI installs one extension per directory and expects the manifest at the install source's root, so for this monorepo, clone and install each extension from its local path.

git clone https://github.com/Owl-Listener/ai-design-skills
cd ai-design-skills
gemini extensions install ./gemini-extension/model-interaction-design

To install all six:

for ext in gemini-extension/*/; do gemini extensions install "./$ext"; done

For development (symlink instead of copy, so edits take effect immediately):

gemini extensions link ./gemini-extension/model-interaction-design

Both agents load skills the same way: each skill has a `description` field in its frontmatter, the agent matches your wording against those descriptions, and the relevant skill loads automatically. You do not pick the skill — the agent does.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 18 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "ai-design-skills",
  3. "owner": {
  4. "name": "MC Dean",
  5. "url": "https://github.com/Owl-Listener"
  6. },
  7. "metadata": {
  8. "description": "Agentic skills, commands, and plugins for designing AI products — from interaction patterns to alignment, evaluation, agent orchestration, and prompt architecture."
  9. },
  10. "plugins": [
  11. { "name": "model-interaction-design", "source": "./claude-plugin/model-interaction-design" },
  12. { "name": "ai-alignment-reasoning", "source": "./claude-plugin/ai-alignment-reasoning" },
  13. { "name": "system-behavior-shaping", "source": "./claude-plugin/system-behavior-shaping" },
  14. { "name": "evaluation", "source": "./claude-plugin/evaluation" },
  15. { "name": "design-agent-orchestration", "source": "./claude-plugin/design-agent-orchestration" },
  16. { "name": "prompt-architecture", "source": "./claude-plugin/prompt-architecture" }
  17. ]
  18. }
README.md · README · 149 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # AI Design Skills Collection
  2. > **Part of the [Designer Skills suite](https://github.com/Owl-Listener/designer-skills).**
  3. > Install this collection and four more with one command in Claude Code:
  4. >
  5. > `/plugin marketplace add Owl-Listener/designer-skills`
  6. >
  7. > This repo still works on its own. The suite just gives everyone one front door.
  8. Agentic skills, commands, and plugins for designing AI products — from interaction patterns to alignment, evaluation, agent orchestration, and prompt architecture.
  9. **44 skills** and **18 commands** across **6 plugins**, available for both [Claude Code](https://docs.anthropic.com/en/docs/claude-code) and [Gemini CLI](https://github.com/google-gemini/gemini-cli). Same skills, same shape, both supported as first-class agents.
  10. ---
  11. ## Why this exists
  12. Agentic Experience Design (AXD) is a new discipline. It has its own vocabulary, definitions, and practices, and it is emerging in real time. *Mixed-initiative flow. Harm anticipation. Handoff protocol. Error personality.* These are real, useful, often-academic terms. They have not yet been collected into a form designers can reach for in real work.
  13. This repo is the collection. Six plugins, mapped to six layers of the discipline: *model interaction, alignment reasoning, system behaviour, evaluation, agent orchestration, prompt architecture.* Inside each, seven skills and three commands your AI agent can load when you are designing or auditing agentic experiences. The work in the underlying ideas was done by alignment researchers and HCI scholars over the last three years; the translation into installable skills is the contribution. [`REFERENCES.md`](./REFERENCES.md) lists the source papers. [`RESEARCH.md`](./RESEARCH.md) makes the translation explicit — for each paper, what was adopted, what was reframed, and how the academic concept became the practitioner skill.
  14. ---
  15. ## Quick Start
  16. Pick the install command for your agent.
  17. ### Claude Code
  18. Add the marketplace, then install plugins from it.
  19. ```bash
  20. claude plugin marketplace add Owl-Listener/ai-design-skills
  21. claude plugin install model-interaction-design@ai-design-skills
  22. ```
  23. To install all six plugins at once:
  24. ```bash
  25. for p in model-interaction-design ai-alignment-reasoning system-behavior-shaping evaluation design-agent-orchestration prompt-architecture; do
  26. claude plugin install "$p@ai-design-skills"
  27. done
  28. ```
  29. ### Gemini CLI
  30. Gemini CLI installs one extension per directory and expects the manifest at the install source's root, so for this monorepo, clone and install each extension from its local path.
  31. ```bash
  32. git clone https://github.com/Owl-Listener/ai-design-skills
  33. cd ai-design-skills
  34. gemini extensions install ./gemini-extension/model-interaction-design
  35. ```
  36. To install all six:
  37. ```bash
  38. for ext in gemini-extension/*/; do gemini extensions install "./$ext"; done
  39. ```
  40. For development (symlink instead of copy, so edits take effect immediately):
  41. ```bash
  42. gemini extensions link ./gemini-extension/model-interaction-design
  43. ```
  44. Both agents load skills the same way: each skill has a `description` field in its frontmatter, the agent matches your wording against those descriptions, and the relevant skill loads automatically. You do not pick the skill — the agent does.
  45. ---
  46. ## First time using a CLI agent?
  47. If you have not used either Claude Code or Gemini CLI before, the path is short.
  48. 1. Pick an agent. Both work with this skill set; both are well-documented; both are free for personal use. Set-up instructions for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) and [Gemini CLI](https://github.com/google-gemini/gemini-cli).
  49. 2. Open a terminal in any project folder.
  50. 3. Run the install command for your agent (above).
  51. 4. From then on, the agent will load the relevant skills automatically when you ask agentic-experience-design questions.
  52. Try this as a first prompt to see the difference:
  53. > *"I am designing an AI assistant for customer support. Help me write the error states for when the assistant does not understand the user's question. Walk me through the trade-offs."*
  54. You will see the agent reach for `error-personality`, `tone-calibration`, and (depending on the framing) `harm-anticipation` automatically. Compare the answer to the same question without the skills installed — the difference is what this repo is for. A worked example of that exact comparison is at [`examples/error-states-walkthrough.md`](./examples/error-states-walkthrough.md).
  55. ---
  56. ## Where to start
  57. You can install all six plugins at once, but if you want to start small, here is a guide based on what you are working on.
  58. - **Building any agentic feature:** start with `model-interaction-design` and `prompt-architecture`. These are the foundation.
  59. - **Shipping a feature soon:** add `evaluation` and `ai-alignment-reasoning`. You need the failure modes mapped before launch.
  60. - **Working on a multi-agent system:** add `design-agent-orchestration`. Handoff protocols and orchestration anti-patterns are non-negotiable here.
  61. - **Designing the agent's voice:** add `system-behavior-shaping`. Persona architecture, error personality, tone calibration.
  62. - **Just curious:** install all six. They are small.
  63. ---
  64. ## What Are Skills and Commands?
  65. **Skills** are domain knowledge units (nouns). They teach the agent about designing AI products — like crafting conversation patterns, specifying guardrails, or structuring system prompts.
  66. **Commands** are workflows (verbs). They chain multiple skills together to accomplish a task — like designing a complete AI persona or auditing a prompt for effectiveness.
  67. When you ask your agent a question, it matches your wording against the `description` field in each skill's frontmatter and loads the relevant ones automatically.
  68. ---
  69. ## The Six Plugins
  70. | Plugin | What it covers | Skills | Commands |
  71. | --- | --- | ---: | ---: |
  72. | `model-interaction-design` | How humans and agents take turns | 8 | 3 |
  73. | `ai-alignment-reasoning` | Outside-of-the-model alignment work | 8 | 3 |
  74. | `system-behavior-shaping` | How the agent shows up — persona, tone, error personality | 7 | 3 |
  75. | `evaluation` | Failure taxonomies, output rubrics, agent-specific heuristics | 7 | 3 |
  76. | `design-agent-orchestration` | Multi-agent role design, handoffs, observability | 7 | 3 |
  77. | `prompt-architecture` | Chain-of-thought, constraint specification, system prompts | 7 | 3 |
  78. Each plugin has its own `README.md` with a full skill-by-skill table.
  79. ---
  80. ## References
  81. The skills are translations of academic and industry work into a form coding agents can use.
  82. - [`REFERENCES.md`](./REFERENCES.md) — Full bibliography: every paper and resource that informed the collection.
  83. - [`RESEARCH.md`](./RESEARCH.md) — Research-to-practice mappings: for each paper, the core academic contribution, the translation moves made to turn it into a practitioner skill, and a cross-reference index of all 44 skills back to their source papers. Start here if you are a researcher studying the gap between HCI scholarship and practitioner tools, or a practitioner who wants to trace a skill to its academic source.
  84. ---
  85. ## Contributing
  86. Skill files are plain markdown. Editing one is a sentence and a commit. New skills welcome — see [`CONTRIBUTING.md`](./CONTRIBUTING.md) for the file conventions and what makes a skill substantive.
  87. If you build something on top of these — a workflow, a higher-level command, a derivative plugin for a specific domain — open an issue or a PR. The discipline gets better when more of us write it.
  88. ---
  89. ## License
  90. [MIT](./LICENSE) — fork it, modify it, ship it. Attribution appreciated, not required.
  91. ---
  92. *Built by [MC Dean](https://marieclairedean.substack.com). Read about why AXD is a discipline now in [the launch essay](https://marieclairedean.substack.com).*

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.