Agent skill

Error Prevention and Recovery

by Owl-Listener in Owl-Listener/inclusive-design-skills

Designs forgiving forms and flows: prevent input errors, write messages that say what happened and what to do, and add undo, confirmation and recovery paths.

MITAuto-check passedFrontend & Design

Install Error Prevention and Recovery

skills CLI
$ npx skills add Owl-Listener/inclusive-design-skills --skill error-prevention-recovery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Owl-Listener/inclusive-design-skills error-prevention-recovery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Owl-Listener/inclusive-design-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cognitive-accessibility/skills/error-prevention-recovery .claude/skills/error-prevention-recovery && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
error-prevention-recovery
GitHub stars
105
Token cost
~739 tokens
SKILL.md length
357 words
Files
1
Skills in repo
55
Repo updated
First seen
Licence
MIT

At a glance

Designs forgiving forms and flows: prevent input errors, write messages that say what happened and what to do, and add undo, confirmation and recovery paths.

  • Works in 3 steps: What happened? (specific, not generic) → Why? (in plain language) → What do I do now? (a clear, single action)
  • Designing forms, checkout flows or account creation
  • SKILL.md covers Prevention Strategies, Error Message Design and Recovery Design
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill takes a cognitive-accessibility view of mistakes: prevent them where possible and help people recover without shame, confusion or lost work. Prevention covers forgiving input (several date and phone formats, auto-formatting, trimming whitespace, format examples beside fields), smart defaults (preselecting common options, prefilling known data, defaulting to the safest choice for irreversible settings), validation on blur with success states and no clearing of input on error, and minimal demands such as asking only for what is needed and splitting long forms into steps.

Every error message has to answer what happened, why, and what to do next, in neutral wording that never blames the user and offers an alternative path when possible. The skill contrasts weak and strong versions for invalid input, a 403 and a password rule. Recovery design adds undo for at least 10 seconds, confirmation with useful detail before destructive actions, previews before consequential submissions, automatic progress saving and alternative paths when the main one fails.

When your agent uses it

  • Designing forms, checkout flows or account creation
  • Rewriting vague error messages so users know what to do next
  • Adding undo and confirmation to destructive actions
  • Reducing abandonment in flows where users often make mistakes

Example prompts

  • “Review our signup form and rewrite every error message so it says what went wrong and what to do.”
  • “Add forgiving date and phone input to the booking form.”
  • “Design the delete-project flow with a detailed confirmation and a short undo window.”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. What happened? (specific, not generic)
  2. Why? (in plain language)
  3. What do I do now? (a clear, single action)

What it can do on your machine

Read from SKILL.md and the folder at commit 6e0740f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Error Prevention and Recovery loads about 739 tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 357 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~739

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Owl-Listener/inclusive-design-skills at commit 6e0740f, republished under its MIT licence (© Owl-Listener). 357 words, ~739 tokens.

Download SKILL.mdSave it as .claude/skills/error-prevention-recovery/SKILL.md (or your agent's skills folder).
name
error-prevention-recovery
description
Design error prevention, error messages, and recovery flows for cognitive accessibility. Use when designing forms, checkout flows, account creation, settings, data entry, or any flow where users can make mistakes. Triggers on: error handling, error messages, form errors, validation, users make mistakes, users abandon, error recovery, undo, forgiving design.

Error Prevention and Recovery

Design systems that prevent errors before they happen, and when errors do occur, help people recover without shame, confusion, or lost work.

Prevention Strategies

Forgiving Input
  • Accept multiple date formats ("15/03/2026", "15 March 2026", "March 15, 2026")
  • Accept multiple phone formats ("(555) 123-4567", "555-123-4567", "5551234567")
  • Auto-format as the user types
  • Case-insensitive matching
  • Trim whitespace automatically
  • Show format examples next to fields ("e.g., 15/03/2026")
Smart Defaults
  • Pre-select the most common option
  • Pre-fill known information (name from account, address from postcode)
  • Show the recommended choice for complex decisions
  • Default to the safest option for irreversible settings
Progressive Validation
  • Validate each field when the user moves to the next (on blur)
  • Show success states for correctly completed fields
  • Never validate while the user is still typing
  • Never clear user input on error — always preserve their work
Minimal Demands
  • Only ask for information you strictly need
  • Mark optional fields, not required ones (most fields should be required by design — if they aren't needed, remove them)
  • Break long forms into steps with clear progress

Error Message Design

Every error message must answer three questions:

  1. What happened? (specific, not generic)
  2. Why? (in plain language)
  3. What do I do now? (a clear, single action)
Show full SKILL.md (153 more words)Show less
Examples

Bad: "Invalid input" Good: "Please enter a date in the format DD/MM/YYYY — for example, 15/03/2026"

Bad: "Error 403" Good: "You don't have permission to view this page. Contact your team admin to request access."

Bad: "Password does not meet requirements" Good: "Your password needs at least 8 characters and one number. You have 6 characters."

Error Message Tone
  • Never blame the user ("You entered an invalid email")
  • State the situation neutrally ("We need a valid email to continue")
  • Be specific about what needs to change
  • Offer an alternative path when possible

Recovery Design

  • Undo available for at least 10 seconds after any action
  • Confirmation before destructive actions with useful detail: "Delete 'Project Alpha'? This removes all 23 files. This cannot be undone."
  • Preview before submission for any consequential action
  • Save progress automatically in long flows
  • Alternative path when primary path fails: "Can't upload a photo? You can describe what you see instead."

© Owl-Listener, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in cognitive-accessibility/skills/error-prevention-recovery of Owl-Listener/inclusive-design-skills.

Open the folder on GitHubat commit 6e0740f

Compare with similar skills

Error Prevention and Recovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Error Prevention and Recovery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Error Prevention and Recovery this skillOwl-Listener/inclusive-design-skills105—~739Automated safety check: PassMIT
Accessibility Fixeribelick/ui-skills9.6k4 repos~1.2kAutomated safety check: PassMIT
Color Auditrome-os/rome748—~2.7kAutomated safety check: PassMIT
Dont Make Me Thinkluongnv89/skills131—~2.5kAutomated safety check: PassMIT
Super UI UX Designsyahiidkamil/Software-Engineer-AI-Agent-Atlas401—~9kAutomated safety check: PassNone
Glycemicgpt UI Foundationlumose-health/GlycemicGPT141—~707Automated safety check: PassGPL-3.0

Similar skills

  • Accessibility Fixer

    ibelick/ui-skills

    Audits and fixes HTML accessibility problems such as ARIA labels, keyboard navigation, focus management, contrast and form errors with minimal changes.

    9.6k GitHub starsUsed in 4 repos~1.2k tokens
    Frontend & DesignAuto-check passed
  • Color Audit

    rome-os/rome

    Audit a design system's color palette against measurable color-science disciplines — WCAG/APCA contrast of declared token pairs, perceptual (OKLCH) ramp uniformity, color-blindness safety of…

    748 GitHub stars~2.7k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Dont Make Me Think

    luongnv89/skills

    Review UI usability using Steve Krug's principles and produce a scannable report.

    131 GitHub stars~2.5k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Super UI UX Design

    syahiidkamil/Software-Engineer-AI-Agent-Atlas

    Complete UI/UX design capability — a wiki-style knowledge map of design theory (UX laws, Nielsen heuristics, usability, visual hierarchy, typography, contrast/WCAG, design systems…

    401 GitHub stars~9k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed
  • Glycemicgpt UI Foundation

    lumose-health/GlycemicGPT

    A skill your agent uses when adding or changing GlycemicGPT web UI structure, shared styling, Tailwind classes, semantic theme tokens, typography, base primitives, product UI components, TextInput…

    141 GitHub stars~707 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Design Critique

    getcrew44/crew44

    Walks an agent through five review passes on a screen, flow or mockup, then returns ranked findings with a severity and a suggested fix for each one.

    356 GitHub stars~691 tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed

More from Owl-Listener/inclusive-design-skills

All 55 skills in this repo
  • Assistive Technology Scenarios

    Owl-Listener/inclusive-design-skills

    Writes usage scenarios, use cases and storyboards that show real people using screen readers, switches, voice control and other assistive technology to finish tasks.

    105 GitHub stars~1.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Accessible Heading Structure

    Owl-Listener/inclusive-design-skills

    Designs heading hierarchies for screen reader navigation and cognitive accessibility on pages, articles, dashboards and forms.

    105 GitHub stars~763 tokensUpdated 4 mo ago
    Auto-check passed
  • Ability Spectrum Mapping

    Owl-Listener/inclusive-design-skills

    Maps a feature across a range of vision, hearing, motor and cognitive ability to find where the design starts to fail, and to explain accessibility scope to stakeholders.

    105 GitHub stars~917 tokensUpdated 4 mo ago
    Auto-check passed
  • Accessibility Debt Tracking

    Owl-Listener/inclusive-design-skills

    Track and manage accessibility debt — known accessibility issues that have been deferred.

    105 GitHub stars~869 tokensUpdated 4 mo ago
    Auto-check passed
  • Accessibility Testing Strategy

    Owl-Listener/inclusive-design-skills

    Plan what to test, how to test, and who should test for accessibility.

    105 GitHub stars~1k tokensUpdated 4 mo ago
    Auto-check passed
  • Alt Text Design

    Owl-Listener/inclusive-design-skills

    Write meaningful alternative text for images, charts, diagrams, and visual content.

    105 GitHub stars~946 tokensUpdated 4 mo ago
    Auto-check passed

Questions about Error Prevention and Recovery

What does Error Prevention and Recovery do?

Designs forgiving forms and flows: prevent input errors, write messages that say what happened and what to do, and add undo, confirmation and recovery paths. The skill takes a cognitive-accessibility view of mistakes: prevent them where possible and help people recover without shame, confusion or lost work. Prevention covers forgiving input (several date and phone formats, auto-formatting, trimming whitespace, format examples beside fields), smart defaults (preselecting common options, prefilling known data, defaulting to the safest choice for irreversible settings), validation on blur with success states and no clearing of input on error, and minimal demands such as asking only for what is needed and splitting long forms into steps.

When should I use Error Prevention and Recovery?

Error Prevention and Recovery fits situations like: designing forms, checkout flows or account creation; rewriting vague error messages so users know what to do next; adding undo and confirmation to destructive actions; reducing abandonment in flows where users often make mistakes.

How do I install Error Prevention and Recovery in Claude Code?

Run `npx skills add Owl-Listener/inclusive-design-skills --skill error-prevention-recovery -a claude-code`. Or copy the skill folder (cognitive-accessibility/skills/error-prevention-recovery in Owl-Listener/inclusive-design-skills) into .claude/skills/error-prevention-recovery in your project. Claude Code loads it when a task matches its description.

How do I install Error Prevention and Recovery in Codex?

Run `npx skills add Owl-Listener/inclusive-design-skills --skill error-prevention-recovery -a codex`. Or copy the skill folder (cognitive-accessibility/skills/error-prevention-recovery in Owl-Listener/inclusive-design-skills) into .agents/skills/error-prevention-recovery in your project. Codex loads it when a task matches its description.

Can I use Error Prevention and Recovery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Owl-Listener/inclusive-design-skills --skill error-prevention-recovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/error-prevention-recovery, .gemini/skills/error-prevention-recovery, .github/skills/error-prevention-recovery and .opencode/skills/error-prevention-recovery in your project.

What does Error Prevention and Recovery need to run?

SKILL.md names no scripts, command-line tools or credentials: Error Prevention and Recovery is instructions for the agent only.

Does Error Prevention and Recovery access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Error Prevention and Recovery safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Error Prevention and Recovery use?

Error Prevention and Recovery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Error Prevention and Recovery use?

About 739 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Error Prevention and Recovery?

Skills that share tags, products or a category with Error Prevention and Recovery: Accessibility Fixer (ibelick/ui-skills, 9.6k stars), Color Audit (rome-os/rome, 748 stars), Dont Make Me Think (luongnv89/skills, 131 stars) and Super UI UX Design (syahiidkamil/Software-Engineer-AI-Agent-Atlas, 401 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Error Prevention and Recovery?

Owl-Listener (a GitHub user) maintains it in Owl-Listener/inclusive-design-skills, which has 105 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on June 9, 2026.

Source: Owl-Listener/inclusive-design-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.