bundled-compression-runtime
Compress or convert generated images for delivery, preview, and social upload. Use when the user asks to compress an image, optimize image size, convert to webp, or reduce file size after generation.
Best use case
bundled-compression-runtime is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Compress or convert generated images for delivery, preview, and social upload. Use when the user asks to compress an image, optimize image size, convert to webp, or reduce file size after generation.
Teams using bundled-compression-runtime should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/compression-runtime/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How bundled-compression-runtime Compares
| Feature / Agent | bundled-compression-runtime | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Compress or convert generated images for delivery, preview, and social upload. Use when the user asks to compress an image, optimize image size, convert to webp, or reduce file size after generation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Bundled Compression Runtime
Compress or convert generated images for delivery, preview, and social upload. Optimize image size, convert to webp, or reduce file size after generation.
This skill uses the best available local toolchain and stays self-contained.
Script:
- `scripts/main.ts`
## Use Cases
- files are too large to share easily
- output needs to be converted to `webp`
- a lighter preview image is needed
- images should be optimized before social upload
## Example Prompts
- `Compress my cover image to webp for social upload`
- `Optimize all images in the output directory to reduce file size`
- `Convert this PNG to a lighter webp format at quality 80`
**Important**: at least one of `cwebp`, `magick`, or `sips` must be available locally.
## Backend Preference
Preferred order:
1. `cwebp` for WebP output
2. `magick` or `convert` for conversion and flexible processing
3. `sips` as a macOS-native fallback
## CLI
```bash
${BUN_X} {baseDir}/scripts/main.ts <input> [options]
```
## Options
| Option | Description |
| --- | --- |
| `<input>` | input file or directory |
| `--output`, `-o` | output file or directory |
| `--format`, `-f` | `webp`, `png`, or `jpeg` (default: `webp`) |
| `--quality`, `-q` | quality `0-100` (default: `80`) |
| `--keep`, `-k` | keep the original when the output extension matches the input |
| `--recursive`, `-r` | process directories recursively |
| `--json` | return JSON output |
## Common Examples
Single image to WebP:
```bash
${BUN_X} {baseDir}/scripts/main.ts input.png -f webp -q 80
```
Single image to JPEG:
```bash
${BUN_X} {baseDir}/scripts/main.ts input.png -f jpeg -q 82
```
Recursive directory compression:
```bash
${BUN_X} {baseDir}/scripts/main.ts ./images -r -f webp
```
JSON output:
```bash
${BUN_X} {baseDir}/scripts/main.ts input.png --json
```
## Workflow
1. Identify the input: a single image file or a directory of images.
2. Choose the target format (`webp`, `png`, or `jpeg`) and quality level.
3. Run the CLI with the chosen options.
4. Verify the output exists and is smaller than the input.
5. If processing a directory, use `--recursive` to handle nested folders.
## Output Convention
Recommended behavior:
- keep the original image untouched
- write the compressed result under a new name
- store results in the same directory or in a `compressed/` subdirectory
Example:
```text
cover-image/topic-slug/
├── cover.png
└── compressed/
└── cover.webp
```
## Re-run Behavior
- Re-compressing the same input produces a new output file (or overwrites an existing one at the same path).
- The original input is never modified unless `--keep` is used and the output extension matches the input.
- `--recursive` re-processes all matching files in the directory, including previously compressed ones.
- To avoid double-compression, point `--output` to a separate `compressed/` subdirectory.
## Definition of Done
- The compressed output file exists and is smaller than the input.
- The original file is preserved (not overwritten) unless `--keep` is used with matching extensions.
- Output format matches the requested `--format`.
- `--json` mode produces a valid JSON summary with input size, output size, and compression ratio.
## Current Behavior
- prefers `cwebp` -> `magick` / `convert` -> `sips`
- supports single files and directories
- supports recursive scanning
- supports JSON summaries
- does not delete the original just because the format changes; use `--keep` when the output extension matches the input
- `webp` output requires `cwebp` or ImageMagick; if only `sips` is available, prefer `png` or `jpeg`Related Skills
per-agent-compression-universal
Zero-config memory consolidation for multi-agent OpenClaw deployments. Auto-discovers agents and registers staggered cron tasks with full state tracking, deduplication, and domain-aware extraction.
runtime-attestation-probe
Helps validate that agent behavior at runtime matches the capabilities and constraints declared in its attestation. Detects divergence between what an agent claims to do and what it actually does during execution, catching the class of attacks that passes static analysis but activates conditionally at runtime.
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.