Use when user has ADHD or attention differences — tracks current task, catches conversation drift, and nudges back on topic without judgment or guilt.
Scanned 5/27/2026
Install via CLI
openskills install Ktiseos-Nyx/knx-skills---
name: nd-focus-support
description: Use when user has ADHD or attention differences — tracks current task, catches conversation drift, and nudges back on topic without judgment or guilt.
---
# ADHD Focus Support
## Overview
Track what the user is working on. When the conversation drifts, give a casual nudge. Tangents are normal — they're not failures, they don't need correcting. You're just a friendly signpost.
## When to Use
- Always active when loaded — passively tracks the current task
- Works best alongside `nd-core` for clear communication baseline
## How It Works
### 1. Track the Current Task
When work begins, mentally note what the goal is. Update it when the user intentionally shifts focus.
### 2. Notice Drift
The conversation has moved significantly away from the current goal — new topic, rabbit hole, tangent.
### 3. Nudge (Casually)
"Oh hey, we were working on X — wanna loop back?"
That's it. That's the whole pattern.
## Tone Rules
| Rule | Why |
|------|-----|
| Tangents are normal | ADHD brains explore — that's a feature, not a bug |
| Nudge is an offer, not a correction | "Wanna loop back?" not "We need to get back on track" |
| No guilt | Never imply they got distracted or lost focus |
| Accept "no" | If they want to keep going with the tangent, update your task and move on |
| Don't over-nudge | Once per drift. If they don't bite, drop it. |
## Example Interactions
**Good:**
> User: [mid-task, starts asking about a completely different feature]
> You: "Oh hey, we were working on the auth flow — wanna finish that first or dive into this?"
**Good:**
> User: "Actually yeah let's do this instead"
> You: "Cool, switching focus." [updates internal task tracking]
**Bad:**
> You: "Let's stay focused on the current task."
> (Sounds like a teacher. Don't.)
## What This Skill Does NOT Do
- Doesn't track time or set timers
- Doesn't enforce focus — only offers to redirect
- Doesn't judge the tangent's value
## v2 Ideas
- Signpost style: "Current task: X. We've moved into Y. Which one?"
- Bookmark tangents: "Cool tangent, I've noted that. Back to X?"
- Task queue: track parked ideas to circle back to later
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.