Contextual Help Design
- 35 installs
- 87 repo stars
- Updated June 9, 2026
- owl-listener/inclusive-design-skills
Helps with ai & agent building tasks during AI-assisted development.
About
contextual-help-design is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.
- contextual-help-design
- AI & Agent Building
- AI-coding skill
Contextual Help Design by the numbers
- 35 all-time installs (skills.sh)
- +5 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #8,740 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/owl-listener/inclusive-design-skills --skill contextual-help-designAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 35 |
|---|---|
| repo stars | ★ 87 |
| Last updated | June 9, 2026 |
| Repository | owl-listener/inclusive-design-skills ↗ |
What it does
Helps with ai & agent building tasks during AI-assisted development.
Files
Contextual Help Design
Design help that meets people where they are — on the screen they're stuck on, in language they understand, without requiring them to remember how they got there.
Core Principle
If a user gets stuck, they should be able to get help without leaving the screen they're on.
Design Patterns
Inline Help
- Tooltip or info icon next to fields that need explanation
- Examples shown next to input fields ("e.g., 15/03/2026")
- Help text visible by default for complex fields
- Inline definitions for specialist terms (underline + tooltip)
- "What's this?" links for uncommon concepts
Guided Tasks
- Step-by-step wizard as an alternative to complex forms
- Examples of completed tasks (filled-in sample forms)
- Templates or pre-built options alongside "start from scratch"
- Progress-aware hints that change based on where the user is
Escalation Path
- Self-service help (search, FAQ) as first option
- Chat or messaging as second option
- Phone or video as third option
- Never require users to re-explain when escalating between channels
- Show estimated wait times for human support
- Never require a reference number to get help
Error Recovery Support
- Error messages include: what happened + why + what to do next
- Link directly to the field or step that needs fixing
- Offer alternative paths when primary fails
- For complex errors: offer human support directly
Help Content Rules
- Write at grade 4–6 reading level
- Use the same terminology as the interface (not different words)
- One instruction per step
- Include images or diagrams for spatial or procedural instructions
- Make help searchable
- Test help content with people who have the actual problem
Assessment Questions
1. Can users get help without navigating away from their task? 2. Is help written in plain language that matches the interface? 3. Can users reach a human within 2 clicks when self-service fails? 4. Do help resources exist for the moments where users actually get stuck (not just the moments you anticipated)?
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10