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

Image Pro

ASecurity

Handle professional image tasks with format conversion, resizing, compression, and metadata workflows.

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

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill image-pro --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Image Pro?

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

Security grade badge for Image Pro
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-image-pro/badge)](https://www.skillsdirectory.com/skills/aicodedecode-image-pro)

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: image-pro
description: Handle professional image tasks with format conversion, resizing, compression, and metadata workflows.
category: media
---

## Overview

Working with images professionally means mastering the pipeline: choosing the right format, sizing
for the destination, compressing without visible loss, and managing metadata. This skill covers
practical image handling — format decisions, batch processing, optimization for web, and quality
control — using standard tools and techniques.

## When to use

- Converting between image formats (JPG, PNG, WebP, AVIF, TIFF)

- Resizing and cropping images for web, print, or social

- Compressing images without visible quality loss

- Batch-processing large sets of images

- Stripping or editing EXIF/metadata for privacy or delivery

## Core concepts

- - **Format decision matrix.** Photographs → JPEG/WebP/AVIF (lossy, small). Graphics with
  transparency → PNG/WebP. Simple graphics → SVG (vector, infinitely scalable). Print masters →
  TIFF. Web delivery in 2026: WebP as baseline, AVIF where supported.
- - **Lossy vs lossless.** Lossy (JPEG/WebP/AVIF) discards data for smaller files — fine for final
  delivery. Lossless (PNG, TIFF) preserves everything — for masters and intermediates. Never re-save
  a lossy file repeatedly; generation loss compounds.
- - **Resolution vs dimensions.** Dimensions (pixels) determine display size; DPI/PPI only matters
  for print (300 for print, irrelevant for screen). A "72 DPI" web image and "300 DPI" web image
  with identical pixels are identical on screen.
- - **Compression sweet spots.** JPEG quality 80-85 is visually lossless for most photos. WebP at
  quality 75-80 beats JPEG at smaller sizes. Always compare visually at 100% — metrics lie, eyes
  don't.
- - **Metadata matters.** EXIF contains camera data, GPS location, and timestamps. Strip GPS before
  publishing (privacy); preserve copyright metadata for professional delivery. Know what your
  exports carry.
- - **Color profiles.** sRGB for web (universal), Adobe RGB or ProPhoto for print/pro work.
  Mismatched profiles cause dull or shifted colors — embed the profile and convert deliberately.

## Practical workflow

1. 1. **Define the destination.** Web hero? Social thumbnail? Print? Each has target dimensions,
   format, and file-size budget. Start from the requirement, not the source.
2. 2. **Choose the format.** Photos for web → WebP (fallback JPEG). Transparency → PNG or WebP.
   Logos/icons → SVG. Archive masters → TIFF or PNG.
3. 3. **Resize correctly.** Downscale with high-quality resampling (Lanczos/bicubic sharper). Never
   upscale beyond ~150% without AI upscaling — invented pixels look soft. Crop to the composition
   first, then resize.
4. 4. **Compress and compare.** Export at candidate settings, view at 100% side by side with the
   original. Check critical areas: gradients (banding?), text edges, skin tones, fine detail. Pick
   the smallest file with no visible difference.
5. 5. **Handle metadata.** Strip location data for public sharing; keep copyright and creator info
   for professional work. Verify with an EXIF reader before publishing sensitive shoots.
6. 6. **Batch with scripts.** For large sets: scripted pipelines (ImageMagick, sips, or Python) with
   consistent settings. Example ImageMagick batch:
   `mogrify -path ./web -format webp -quality 80 -resize "1920x1920>" *.jpg`
   (resizes to max 1920px, converts to WebP — non-destructive to originals since output goes to
./web)
7. 7. **Quality-check the outputs.** Spot-check exports: correct dimensions, no corruption, metadata
   as intended, file sizes within budget. One bad batch setting can ruin hundreds of files — verify
   early.

## Common pitfalls

- - **Upscaling for "quality."** Enlarging a small image doesn't add detail. Deliver at native
  resolution or use proper upscaling tools with realistic expectations.
- - **PNG for photographs.** A photo saved as PNG can be 5-10x larger than WebP with zero visual
  benefit. Match format to content.
- - **Forgetting mobile.** A 4MB hero image on a phone over cellular is a bounce. Responsive images
  (srcset) with size-appropriate variants are standard practice.
- - **GPS in published photos.** Location data in shared images is a privacy and safety issue. Strip
  EXIF location before any public posting.
- - **Over-compression artifacts.** Banding in skies, blockiness in shadows, mushy text. The fix is
  always: raise quality or pick a better format — not "it's fine."
- - **Working from lossy originals.** Editing a JPEG, saving as JPEG, editing again — each cycle
  degrades. Keep a lossless master; export lossy only for delivery.

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', ...

698621 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 →