New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Errors Mistakes

by hashgraph-online in hashgraph-online/awesome-codex-plugins

A skill your agent uses when designing to prevent errors of intention — wrong actions taken because the user's model of the situation was wrong.

Apache-2.0Auto-check passedWriting & Content

Install Errors Mistakes

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill errors-mistakes -a claude-code

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

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins errors-mistakes --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/errors-mistakes .claude/skills/errors-mistakes && 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
errors-mistakes
GitHub stars
1.2k
Token cost
~1.6k tokens
SKILL.md length
725 words
Files
2 (incl. references)
Skills in repo
736
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when designing to prevent errors of intention — wrong actions taken because the user's model of the situation was wrong.

  • Works in 3 steps: The "what's the user's model?" check.… → The state-visibility audit. What state… → The novel-situation walkthrough. For…
  • Designing to prevent errors of intention — wrong actions taken because the users model of the situation was wrong
  • SKILL.md covers The three mistake subtypes…, Common mistake-prevention…, Mistake-prone contexts and Anti-patterns, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Errors Mistakes is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill when designing to prevent errors of intention — wrong actions taken because the user's model of the situation was wrong. Trigger when designing for ambiguous information, novel situations, complex decisions, or contexts where users may proceed with confidence based on a wrong understanding. Sub-aspect of errors; read that first.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/mistake-prevention-cases.md`).

It sits in Writing & Content, covering Creative writing and fiction. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

  • Designing to prevent errors of intention — wrong actions taken because the users model of the situation was wrong
  • Designing for ambiguous information
  • Novel situations
  • Complex decisions

Example prompts

  • “/errors-mistakes”

Workflow steps

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

  1. The "what's the user's model?" check. Before designing a flow, ask what model the user is likely to bring. Designs that match it prevent…
  2. The state-visibility audit. What state are users in right now? Can they see it? If not, they can mistake.
  3. The novel-situation walkthrough. For unfamiliar features, walk a new user through. Note where their model diverges from the system; design…

What it can do on your machine

Read from SKILL.md and the folder at commit 16b4156. 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 (its code samples are html).

    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

Errors Mistakes loads about 1.6k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 91 tokens; SKILL.md has 725 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

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 hashgraph-online/awesome-codex-plugins at commit 16b4156, republished under its Apache-2.0 licence (© hashgraph-online). 725 words, ~1,576 tokens.

Download SKILL.mdSave it as .claude/skills/errors-mistakes/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
errors-mistakes
description
Use this skill when designing to prevent errors of intention — wrong actions taken because the user's model of the situation was wrong. Trigger when designing for ambiguous information, novel situations, complex decisions, or contexts where users may proceed with confidence based on a wrong understanding. Sub-aspect of `errors`; read that first.

Mistakes: errors of intention

A mistake happens when the user's action matched their intent — but the intent was wrong because their model of the situation was wrong. They misread an alarm; misjudged a chart; chose the wrong option from a menu they misunderstood. Unlike slips, mistakes are usually unrecognized at the moment they happen — the user is confident they're doing the right thing.

The design responses for mistakes work upstream of action: better information, clearer system state, training, conventions that match user expectations.

The three mistake subtypes (from the book)

Perception mistakes

Wrong action because of misread information.

Design responses:

  • Improve situational awareness (clear, distinctive feedback).
  • Show trends and historical data, not just point-in-time values.
  • Provide clear and distinctive feedback at decision points.
html
<!-- Point-in-time only — perception-mistake-prone -->
<p>CPU: 45%</p>

<!-- With trend — clearer -->
<div class="metric">
  <p>CPU: 45%</p>
  <span class="trend trend--up">↑ Rising over last hour</span>
  <canvas class="sparkline"></canvas>
</div>
Decision mistakes

Wrong action under stress, bias, or overconfidence.

Design responses:

  • Minimize information and environmental noise.
  • Use checklists and decision trees for high-stakes decisions.
  • Train on error recovery and troubleshooting.
  • Reduce time pressure where possible.

A monitoring console for production incidents that surfaces a checklist of likely causes ("Check service X first, then Y, then Z") reduces decision mistakes during stressful incidents.

Knowledge mistakes

Wrong action because of missing knowledge.

Design responses:

  • Memory and decision aids in context.
  • Standardized naming and operational conventions.
  • Training using case studies and simulations.
  • Mnemonic devices.

A new user encountering an unfamiliar feature for the first time benefits from inline help, walkthroughs, or progressive-disclosure of complexity.

Common mistake-prevention patterns

Surfacing system state

Many mistakes flow from invisible system state. The user thinks the system is in mode A; it's actually in mode B; their action is correct for A but wrong for B.

Design response: make state visible. Modal indicators, status bars, breadcrumbs all help.

html
<header class="env-banner env-banner--prod">
  ⚠ Production environment — actions affect live customers
</header>

A visible "PROD" banner on production tools prevents the mistake of running staging-style commands against real customer data.

Decision trees and guided flows

For complex decisions, walk the user through. Each step narrows the option space.

Are you trying to...
  (•) Fix a customer issue
  ( ) Make a code change
  ( ) Run a migration

[Continue]

Then based on the answer, the next set of options is contextual. The user can't easily make a mistake by picking from a flat list of 30 options because the context narrows the space.

Trend-aware displays

Replace point-in-time displays with trend-aware ones. The single number "23%" hides a trajectory; the sparkline reveals it.

Checklists

Borrowed from aviation and medicine. A checklist forces the user to verify each prerequisite explicitly. Surgical "time-out" checklists, pilot pre-takeoff checklists, and software pre-deployment checklists all prevent decision and knowledge mistakes by externalizing memory.

Conventions and standards

When users encounter unfamiliar systems, they apply conventions from familiar ones. If your system honors conventions (cmd-K opens command palette, Esc closes overlays), users transfer prior knowledge correctly. If you violate them, users transfer prior knowledge incorrectly — knowledge mistakes ensue.

Show full SKILL.md (275 more words)Show less
Inline help in context

Don't rely on documentation pages users won't visit. Surface help in the moment: a "?" icon next to ambiguous fields with a tooltip, an info-banner explaining a section's purpose, contextual onboarding hints.

Mistake-prone contexts

  • Novel situations — the user's model doesn't apply.
  • Ambiguous information — multiple plausible interpretations.
  • High-stakes decisions under stress — judgment narrows.
  • Cross-domain transfers — applying conventions from one domain to another that doesn't share them.
  • Edge cases — situations the user hasn't seen before.
  • First-time users of any feature — knowledge gap.

Anti-patterns

  • Hidden system state. User assumes the system is in one state; it's actually in another.
  • Cryptic error messages that don't help the user understand what's wrong.
  • Conventions violated without warning. A "Save" button that doesn't save, or saves to a different location.
  • Onboarding for new users that's just a tour. Watching demo videos doesn't transfer knowledge as well as guided practice.
  • Single-point-in-time displays for trending phenomena. Hides the trajectory.

Heuristics

  1. The "what's the user's model?" check. Before designing a flow, ask what model the user is likely to bring. Designs that match it prevent mistakes; designs that violate it cause them.
  2. The state-visibility audit. What state are users in right now? Can they see it? If not, they can mistake.
  3. The novel-situation walkthrough. For unfamiliar features, walk a new user through. Note where their model diverges from the system; design responses there.
  • errors (parent).
  • errors-slips — the complementary error type; execution rather than intention.
  • mental-model — mistakes flow from wrong models; mental-model design prevents them.
  • expectation-effect — when the system violates expectation, mistakes follow.
  • visibility — system state must be visible to be reasoned about.
  • mimicry — borrowing conventions reduces knowledge-mistakes.

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/errors-mistakes of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/mistake-prevention-cases.md

Open the folder on GitHubat commit 16b4156

Compare with similar skills

Errors Mistakes 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.

Errors Mistakes compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Errors Mistakes this skillhashgraph-online/awesome-codex-plugins1.2k—~1.6kAutomated safety check: PassApache-2.0
Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode7.3k3 repos~3kAutomated safety check: PassMIT
Short Web Fiction Trend Scanzenstory-ai/oh-story-claudecode7.3k3 repos~1.2kAutomated safety check: PassMIT
InkOS Creative HarnessNarcooo/inkos10k1 repos~1.1kAutomated safety check: PassAGPL-3.0
Novel Arteternityspring/shuohao-skills4.2k—~1.1kAutomated safety check: NotesApache-2.0
Novel Import and Project Rebuildzenstory-ai/oh-story-claudecode7.3k2 repos~1.7kAutomated safety check: PassMIT

Similar skills

  • Story Multi-Perspective Review

    zenstory-ai/oh-story-claudecode

    Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.

    7.3k GitHub starsUsed in 3 repos~3k tokens
    Writing & ContentAuto-check passed

  • Short Web Fiction Trend Scan

    zenstory-ai/oh-story-claudecode

    Scans popular short web-fiction rankings on Chinese platforms such as Dianzhong and Heiyan to surface trending emotional hooks, themes and topic candidates with an expiry warning.

    7.3k GitHub starsUsed in 3 repos~1.2k tokens
    Writing & ContentAuto-check passed

  • InkOS Creative Harness

    Narcooo/inkos

    Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.

    10k GitHub starsUsed in 1 repo~1.1k tokens
    Writing & ContentAuto-check passed

  • Novel Art

    eternityspring/shuohao-skills

    给 AI 短剧出美术设定集（场景 + 叙事道具）：场景的设计意图、一致性锚点、光照时段变体、 空景提示词；道具的戏剧功能、状态变体、尺度参照、白底无手提示词。

    4.2k GitHub stars~1.1k tokensUpdated 11 days ago
    Writing & ContentAuto-check: notes

  • Novel Import and Project Rebuild

    zenstory-ai/oh-story-claudecode

    Reverse-imports an existing novel, half-finished or complete, into the standard project structure so story-long-write or story-short-write can continue it.

    7.3k GitHub starsUsed in 2 repos~1.7k tokens
    Writing & ContentAuto-check passed

  • Sepia

    Nanako0129/sepia

    Make AI-generated writing read as human-written, in fiction and in professional prose.

    3k GitHub stars~3.6k tokensUpdated yesterday
    Writing & ContentAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 736 skills in this repo

  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.2k GitHub stars~922 tokensUpdated yesterday
    Auto-check passed

  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.2k GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.2k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.2k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

  • Calle

    hashgraph-online/awesome-codex-plugins

    Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.

    1.2k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.2k GitHub stars~618 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Errors Mistakes

What does Errors Mistakes do?

A skill your agent uses when designing to prevent errors of intention — wrong actions taken because the user's model of the situation was wrong. Errors Mistakes is an agent skill from hashgraph-online/awesome-codex-plugins. Use this skill when designing to prevent errors of intention — wrong actions taken because the user's model of the situation was wrong.

When should I use Errors Mistakes?

Errors Mistakes fits situations like: designing to prevent errors of intention — wrong actions taken because the users model of the situation was wrong; designing for ambiguous information; novel situations; complex decisions.

How do I install Errors Mistakes in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill errors-mistakes -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/errors-mistakes in hashgraph-online/awesome-codex-plugins) into .claude/skills/errors-mistakes in your project. Claude Code loads it when a task matches its description.

How do I install Errors Mistakes in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill errors-mistakes -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/errors-mistakes in hashgraph-online/awesome-codex-plugins) into .agents/skills/errors-mistakes in your project. Codex loads it when a task matches its description.

Can I use Errors Mistakes 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 hashgraph-online/awesome-codex-plugins --skill errors-mistakes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/errors-mistakes, .gemini/skills/errors-mistakes, .github/skills/errors-mistakes and .opencode/skills/errors-mistakes in your project.

What does Errors Mistakes need to run?

SKILL.md names no scripts, command-line tools or credentials: Errors Mistakes is instructions for the agent only.

Does Errors Mistakes 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 Errors Mistakes 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 Errors Mistakes use?

Errors Mistakes is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Errors Mistakes use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Errors Mistakes?

Skills that share tags, products or a category with Errors Mistakes: Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.3k stars), Short Web Fiction Trend Scan (zenstory-ai/oh-story-claudecode, 7.3k stars), InkOS Creative Harness (Narcooo/inkos, 10k stars) and Novel Art (eternityspring/shuohao-skills, 4.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Errors Mistakes?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,232 GitHub stars. The repository holds 736 skills in this directory. The repository was last updated on October 6, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.