Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Unit Converter

ASecurity

Convert units accurately across measurement systems with precision handling and reference tables.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgogit

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill unit-converter --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Unit Converter?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Unit Converter
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-unit-converter/badge)](https://www.skillsdirectory.com/skills/aicodedecode-unit-converter)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: unit-converter
description: Convert units accurately across measurement systems with precision handling and reference tables.
category: utilities
---

## Overview

Unit conversion errors have crashed spacecraft — precision matters. This skill covers reliable
conversion across measurement systems (metric/imperial, temperature, data, currency-adjacent),
handling significant figures, avoiding the classic traps (temperature offsets, US vs imperial
gallons), and building conversion references you can trust.

## When to use

- Converting between metric and imperial units

- Handling temperature, data storage, or cooking conversions

- Checking conversion precision and significant figures

- Building conversion tables or calculator references

- Avoiding common conversion mistakes in technical work

## Core concepts

- - **Exact vs approximate factors.** Some conversions are defined exactly (1 inch = 2.54 cm, by
  international agreement). Others are measured (currency rates) or conventional (1 cup = 236.588 ml
  US, but 250 ml in many recipes). Know which you're dealing with.
- - **Temperature is special.** It's an offset scale, not just a multiplier: °F = °C × 9/5 + 32. For
  differences (not absolute temps), 1°C difference = 1.8°F difference — the offset drops out. Mixing
  these up is the classic error.
- - **Significant figures.** Converting 5 miles with a 10-digit factor gives 8.04672 km — but if the
  input was approximate, the output's precision is a lie. Match output precision to input precision.
- - **The gallon trap.** US gallon (3.785 L) ≠ imperial gallon (4.546 L). Same for pints, quarts,
  fluid ounces. Always clarify which system — "gallon" alone is ambiguous.
- - **Data units: decimal vs binary.** 1 KB = 1000 bytes (SI, storage marketing) vs 1 KiB = 1021024
  bytes (binary, OS reporting). The "missing" disk space on every hard drive is this confusion. Use
  KiB/MiB/GiB when you mean powers of 1024.
- - **Dimensional analysis.** Write units through the calculation: miles × (km/mile) = km. If the
  units don't cancel to what you want, the setup is wrong — this catches most errors before they
  happen.

## Practical workflow

1. 1. **Identify both systems precisely.** Not just "gallons" — US or imperial? Not just "tons" —
   metric tonne, US short ton, or imperial long ton? Ambiguity here is where errors breed.
2. 2. **Use defined factors.** Prefer exact definitions (inch = 2.54 cm) over rounded memories. For
   chained conversions, use one precise factor rather than rounding intermediates.
3. 3. **Handle temperature correctly.** Absolute: apply offset + scale. Differences: scale only.
   Double-check which one the problem needs.
4. 4. **Round to the input's precision.** If the input has 2 significant figures, the output gets 2
   (8.0 km, not 8.04672). Exception: keep extra digits in intermediate steps, round only the final
   answer.
5. 5. **Sanity-check the magnitude.** 100°F ≈ 38°C (fever), not 212. 70 kg ≈ 154 lb, not 700. Every
   conversion deserves a reality check — if it feels wrong, it probably is.
6. 6. **Document the factor.** In technical work, note the conversion factor used. "Converted at 1
   USD = 83.2 INR (2026-09-26)" beats a naked number when someone audits later.

**Quick reference (exact where defined):**
- Length: 1 in = 2.54 cm | 1 ft = 30.48 cm | 1 mi = 1.609344 km | 1 m = 3.28084 ft

- Mass: 1 lb = 453.59237 g | 1 oz = 28.3495 g | 1 kg = 2.20462 lb

- Volume: 1 US gal = 3.78541 L | 1 imp gal = 4.54609 L | 1 US fl oz = 29.5735 ml

- Temp: °F = °C×9/5+32 | K = °C+273.15

- Data: 1 KiB = 1024 B | 1 KB = 1000 B (SI)

## Common pitfalls

- - **US vs imperial volumes.** The silent killer in recipes, fuel economy, and engineering. Always
  disambiguate.
- - **Temperature offset errors.** Multiplying instead of offset-converting (or vice versa). Write
  the formula out; don't do it in your head.
- - **False precision.** Reporting 8.04672 km from "about 5 miles." Precision theater undermines
  credibility.
- - **KB vs KiB.** Expecting 1000-based and getting 1024-based (or reverse) in storage, memory, and
  network calculations.
- - **Currency as conversion.** Exchange rates fluctuate — a "conversion" is a snapshot with a
  timestamp, not a constant. Always date currency conversions.
- - **Chained rounding.** Rounding at each step of a multi-step conversion accumulates error. Keep
  full precision until the final result.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

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', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →