Updated 4mo ago
by Owl-Listener
ai-design-skills
AI Design Skills Collection: agentic skills, commands, and plugins for designing AI products — from interaction patterns to alignment, evaluation, agent orchestration, and prompt architecture.
188 GitHub stars (188)
+12 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | +1 |
| Oct 2 | +1 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | +1 |
| Oct 7 | +1 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | +3 |
| Oct 11 | +1 |
| Oct 12 | +3 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 30 skills (30 skills found in its SKILL.md files)
- 36 forks (36 forks)
- 4mo ago last update (Last updated 4mo ago)
Install
Skills CLI
npx skills add Owl-Listener/ai-design-skills
Asks which skills and agents to install. Just one: npx skills add Owl-Listener/ai-design-skills --skill bias-detection-design — add -g for every project.
Claude Code
git clone https://github.com/Owl-Listener/ai-design-skillscp -r "ai-design-skills/skills/ai-alignment-reasoning/bias-detection-design" ~/.claude/skills/
Copies the bias-detection-design skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Owl-Listener/ai-design-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 132 files.
-
bias-detection-design
Designing review workflows to surface and mitigate bias in AI outputs.
skills/ai-alignment-reasoning/bias-detection-design/SKILL.md on GitHub (opens in a new tab) -
consent-and-agency
Designing for informed user consent, opt-out, and human override.
skills/ai-alignment-reasoning/consent-and-agency/SKILL.md on GitHub (opens in a new tab) -
escalation-design
When and how AI should escalate to humans, refuse, or ask for clarification.
skills/ai-alignment-reasoning/escalation-design/SKILL.md on GitHub (opens in a new tab) -
guardrail-design
Defining behavioral boundaries — what the AI should and shouldn't do.
skills/ai-alignment-reasoning/guardrail-design/SKILL.md on GitHub (opens in a new tab) -
harm-anticipation
Proactively identifying failure modes, misuse, and unintended consequences.
skills/ai-alignment-reasoning/harm-anticipation/SKILL.md on GitHub (opens in a new tab) -
transparency-patterns
Showing users what the AI knows, doesn't know, and how confident it is.
skills/ai-alignment-reasoning/transparency-patterns/SKILL.md on GitHub (opens in a new tab) -
trust-calibration
Helping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling.
skills/ai-alignment-reasoning/trust-calibration/SKILL.md on GitHub (opens in a new tab) -
value-specification
Translating organisational values and user expectations into system constraints.
skills/ai-alignment-reasoning/value-specification/SKILL.md on GitHub (opens in a new tab) -
agent-role-design
Defining what each agent does, knows, and owns in a multi-agent system.
skills/design-agent-orchestration/agent-role-design/SKILL.md on GitHub (opens in a new tab) -
failure-recovery
What happens when an agent fails — retry, fallback, escalate, or graceful degradation.
skills/design-agent-orchestration/failure-recovery/SKILL.md on GitHub (opens in a new tab) -
handoff-protocols
Designing smooth transitions between agents and between AI and humans.
skills/design-agent-orchestration/handoff-protocols/SKILL.md on GitHub (opens in a new tab) -
human-in-the-loop
Designing intervention points where humans review, approve, or redirect agent work.
skills/design-agent-orchestration/human-in-the-loop/SKILL.md on GitHub (opens in a new tab) -
observability-design
Making multi-agent workflows visible and debuggable for designers and developers.
skills/design-agent-orchestration/observability-design/SKILL.md on GitHub (opens in a new tab) -
state-management
Managing shared context, memory, and state across multiple agents.
skills/design-agent-orchestration/state-management/SKILL.md on GitHub (opens in a new tab) -
task-decomposition
Breaking complex user goals into subtasks that agents can handle.
skills/design-agent-orchestration/task-decomposition/SKILL.md on GitHub (opens in a new tab) -
comparative-evaluation
A/B testing, side-by-side comparison, and preference ranking for AI outputs.
skills/evaluation/comparative-evaluation/SKILL.md on GitHub (opens in a new tab) -
failure-taxonomy
Classifying AI failures — hallucination, refusal, irrelevance, tone mismatch, latency.
skills/evaluation/failure-taxonomy/SKILL.md on GitHub (opens in a new tab) -
heuristic-evaluation-ai
Adapting Nielsen's heuristics and new AI-specific heuristics for AI interfaces.
skills/evaluation/heuristic-evaluation-ai/SKILL.md on GitHub (opens in a new tab) -
longitudinal-measurement
Tracking AI product quality over time — drift, degradation, and improvement.
skills/evaluation/longitudinal-measurement/SKILL.md on GitHub (opens in a new tab) -
output-quality-rubrics
Defining what "good" looks like for AI outputs — accuracy, relevance, helpfulness.
skills/evaluation/output-quality-rubrics/SKILL.md on GitHub (opens in a new tab) -
task-success-metrics
Measuring whether the AI actually helped users accomplish their goals.
skills/evaluation/task-success-metrics/SKILL.md on GitHub (opens in a new tab) -
user-satisfaction-signals
Interpreting implicit and explicit feedback — edits, regenerations, abandonment.
skills/evaluation/user-satisfaction-signals/SKILL.md on GitHub (opens in a new tab) -
context-window-design
Designing around token limits, memory, and conversation persistence.
skills/model-interaction-design/context-window-design/SKILL.md on GitHub (opens in a new tab) -
conversation-patterns
Turn-taking, repair sequences, grounding, and dialogue structure for human-AI interaction.
skills/model-interaction-design/conversation-patterns/SKILL.md on GitHub (opens in a new tab) -
feedback-loops
User correction, thumbs up/down, inline editing, and reinforcement signals.
skills/model-interaction-design/feedback-loops/SKILL.md on GitHub (opens in a new tab) -
frustration-detection
Reading user emotional state from text signals — caps, punctuation density, repetition, latency — and adapting before the user disengages.
skills/model-interaction-design/frustration-detection/SKILL.md on GitHub (opens in a new tab) -
generative-ui
Designing interfaces where AI generates UI components dynamically.
skills/model-interaction-design/generative-ui/SKILL.md on GitHub (opens in a new tab) -
mixed-initiative-flow
When the AI leads vs. when the user leads, and how to hand off control.
skills/model-interaction-design/mixed-initiative-flow/SKILL.md on GitHub (opens in a new tab) -
multimodal-orchestration
Coordinating text, image, voice, and tool-use modalities in a single interaction.
skills/model-interaction-design/multimodal-orchestration/SKILL.md on GitHub (opens in a new tab) -
progressive-disclosure
Revealing AI capability gradually to match user mental models.
skills/model-interaction-design/progressive-disclosure/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
skillsby anthropics Public repository for Agent Skills