ai-design-skills
github.com/Owl-Listener/ai-design-skills
| Skill | Added | Review |
|---|---|---|
failure-taxonomy gemini-extension/evaluation/skills/failure-taxonomy/SKILL.md Classifying AI failures — hallucination, refusal, irrelevance, tone mismatch, latency. | 28 28 Impact — No eval scenarios have been run Securityby  Passed No findings from the security scan Version: f41b650 | |
longitudinal-measurement gemini-extension/evaluation/skills/longitudinal-measurement/SKILL.md Tracking AI product quality over time — drift, degradation, and improvement. | 29 29 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
consent-and-agency gemini-extension/ai-alignment-reasoning/skills/consent-and-agency/SKILL.md Designing for informed user consent, opt-out, and human override. | 30 30 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
comparative-evaluation gemini-extension/evaluation/skills/comparative-evaluation/SKILL.md A/B testing, side-by-side comparison, and preference ranking for AI outputs. | 33 33 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
frustration-detection claude-plugin/model-interaction-design/skills/frustration-detection/SKILL.md Reading user emotional state from text signals — caps, punctuation density, repetition, latency — and adapting before the user disengages. | 45 45 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
prompt-versioning gemini-extension/prompt-architecture/skills/prompt-versioning/SKILL.md Managing prompt iterations, testing changes, and tracking what works. | 20 20 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
context-engineering gemini-extension/prompt-architecture/skills/context-engineering/SKILL.md Designing what information goes into the context window and in what order. | 23 23 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
handoff-protocols skills/design-agent-orchestration/handoff-protocols/SKILL.md Designing smooth transitions between agents and between AI and humans. | 28 28 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
cultural-adaptation claude-plugin/system-behavior-shaping/skills/cultural-adaptation/SKILL.md Adapting AI behavior for different cultural contexts, languages, and norms. | 25 25 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
transparency-patterns claude-plugin/ai-alignment-reasoning/skills/transparency-patterns/SKILL.md Showing users what the AI knows, doesn't know, and how confident it is. | 23 23 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
cultural-adaptation gemini-extension/system-behavior-shaping/skills/cultural-adaptation/SKILL.md Adapting AI behavior for different cultural contexts, languages, and norms. | 25 25 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
chain-of-thought-design gemini-extension/prompt-architecture/skills/chain-of-thought-design/SKILL.md Designing reasoning chains that produce better outputs. | 27 27 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
user-satisfaction-signals gemini-extension/evaluation/skills/user-satisfaction-signals/SKILL.md Interpreting implicit and explicit feedback — edits, regenerations, abandonment. | 39 39 1.02x Agent success vs baseline Impact 95% 1.02xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: f41b650 | |
emotional-design claude-plugin/system-behavior-shaping/skills/emotional-design/SKILL.md How the AI responds to user frustration, confusion, delight, and distress. | 27 27 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
conversation-patterns gemini-extension/model-interaction-design/skills/conversation-patterns/SKILL.md Turn-taking, repair sequences, grounding, and dialogue structure for human-AI interaction. | 25 25 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
observability-design claude-plugin/design-agent-orchestration/skills/observability-design/SKILL.md Making multi-agent workflows visible and debuggable for designers and developers. | 25 25 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
agent-role-design skills/design-agent-orchestration/agent-role-design/SKILL.md Defining what each agent does, knows, and owns in a multi-agent system. | 30 30 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
template-design claude-plugin/prompt-architecture/skills/template-design/SKILL.md Creating reusable, parameterised prompt templates for consistent outputs. | 25 25 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
context-window-design gemini-extension/model-interaction-design/skills/context-window-design/SKILL.md Designing around token limits, memory, and conversation persistence. | 25 25 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
guardrail-design skills/ai-alignment-reasoning/guardrail-design/SKILL.md Defining behavioral boundaries — what the AI should and shouldn't do. | 23 23 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
trust-calibration gemini-extension/ai-alignment-reasoning/skills/trust-calibration/SKILL.md Helping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling. | 34 34 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
task-decomposition claude-plugin/design-agent-orchestration/skills/task-decomposition/SKILL.md Breaking complex user goals into subtasks that agents can handle. | 25 25 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
value-specification gemini-extension/ai-alignment-reasoning/skills/value-specification/SKILL.md Translating organisational values and user expectations into system constraints. | 28 28 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
domain-voice claude-plugin/system-behavior-shaping/skills/domain-voice/SKILL.md Tailoring AI behavior for specific professional domains. | 18 18 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 | |
guardrail-design claude-plugin/ai-alignment-reasoning/skills/guardrail-design/SKILL.md Defining behavioral boundaries — what the AI should and shouldn't do. | 23 23 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: f41b650 |