design-de-interacao-nao-intrusivo-para-ia

Defines UX policies for non-intrusive AI writing assistants in text editors.

Updated Jul 19, 2026
One-click install
npx skills add https://github.com/Ryanzucchi/Eldritch_Lich --skill design-de-interacao-nao-intrusivo-para-ia-ryanzucchi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: design-de-interacao-nao-intrusivo-para-ia
Source: https://github.com/Ryanzucchi/Eldritch_Lich/tree/main/.agents/skills/design-de-interacao-nao-intrusivo-para-ia
Command: npx skills add https://github.com/Ryanzucchi/Eldritch_Lich --skill design-de-interacao-nao-intrusivo-para-ia-ryanzucchi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI writing assistants often interrupt creative flow with unsolicited pop-ups and auto-generated prose, undermining the author's sense of ownership over their manuscript. This Skill establishes concrete UX policies so AI suggestions support the writer without breaking concentration or replacing human authorship. ## Core Features & Use Cases - Passive Sidebar Pattern: Configures AI suggestions to appear in a low-salience sidebar (opacity 0.6 when unfocused) that updates silently without animations, sounds, or notifications. - Explicit Opt-in Triggers: Inline suggestions only appear via author-controlled triggers such as reserved tokens like [nome?] or [gancho?], or the Ctrl+Space shortcut, with pop-ups auto-dismissing after 6 seconds. - Isolated Brainstorming Mode: Interactive brainstorming sessions (premise inversion, SCAMPER, consequence maps) run in a separate screen, never as an overlay on the manuscript. - Use Case: A frontend team building a co-pilot feature for a fiction editor uses these policies to ensure the AI suggests character names and plot hooks in a sidebar while the novelist keeps typing uninterrupted. ## Quick Start Apply this skill to configure the AI suggestion panel in the editor so that suggestions appear only in a passive sidebar or through explicit trigger tokens, never interrupting the author's typing.

Frequently Asked Questions about design-de-interacao-nao-intrusivo-para-ia

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design non-intrusive AI suggestions for a writing app?▼

Use a passive sidebar that updates silently at paragraph boundaries with reduced opacity (0.6) when unfocused. Inline pop-ups should only appear through explicit triggers like reserved tokens or Ctrl+Space, and must auto-dismiss within 6 seconds or 300ms after the author resumes typing.

What triggers should activate inline AI writing suggestions?▼

Inline suggestions should activate only through explicit opt-in triggers: reserved textual tokens such as [nome?], [gancho?], [ref?], and [local?], or the Ctrl+Space keyboard shortcut. Never show floating suggestions automatically near the cursor.

Should AI assistants generate full paragraphs for fiction writers?▼

No. Proactive long-form generation without explicit author triggers undermines the writer's sense of authorship. The AI should only suggest secondary creative inputs like names, concepts, and plot hooks, while all narrative prose remains written by the human author.

When should AI suggestion pop-ups not be used?▼

These interaction policies do not apply to administrative contexts like account management, license dialogs, or file export modals. They also do not apply to critical security alerts or database synchronization error messages.

How do I measure whether AI suggestions disrupt creative flow?▼

Track the rate of interrupted writing sessions during suggestion display, targeting 5% or lower in usability tests. Also measure declared creative agency on a 7-point Likert scale, targeting a score of 6 or higher for perceived authorial control.