SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add benchflow-ai/skillsbench --skill image-editinggit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/benchflow-ai/skillsbench/image-editing)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/image-editing"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/image-editing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/image-editing"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/image-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 89 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.00997 |
| Opus 5 | $0.00015 | $0.00498 |
| Sonnet 5 | $0.00006 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade B, and why
image-editing scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- convert: Run `sudo apt install imagemagick` to install. After that, you can use `convert` command. Copies of this mod
1 near-identical copy found in the catalogue:
- image_editing — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command-line Tools: Convert
Overview
This guide covers essential image processing operations using ImageMagick, a collection of command-line tools that can be applied to modify and manipulate images. With this toolkit, you can edit images in batch on Linux command-line.
Image Operations
Use the convert command to resize an image, blur, crop, despeckle, dither, draw on, flip, join, re-sample, and much more.
Example Usage We list a few examples of the command here to illustrate its usefulness and ease of use. To get started, let's reduce the size of our rose:
convert -resize 50% rose.jpg
You can resize all your JPEG images in a folder to a maximum dimension of 256x256 with this command:
convert -resize 256x256 *.jpg
Finally, we convert all our PNG images in a folder to the JPEG format:
convert -format jpg *.png
Here image files 1.png, 2.png, etc., are left untouched and files 1.jpg, 2.jpg, etc., are created. They are copies of their respective PNG images except are stored in the JPEG image format.
Useful image operations and their corresponding command:
-auto-orient
Adjusts an image so that its orientation is suitable for viewing (i.e. top-left orientation). This operator reads and resets the EXIF image profile setting 'Orientation' and then performs the appropriate 90 degree rotation on the image to orient the image, for correct viewing.
-background <color>
Set the background color. The color is specified using the format described under the -fill option. The default background color (if none is specified or found in the image) is white.
-blend <geometry>
Blend an image into another by the given absolute value or percent. Blend will average the images together ('plus') according to the percentages given and each pixels transparency. If only a single percentage value is given it sets the weight of the composite or 'source' image, while the background image is weighted by the exact opposite amount. That is a -blend 30% merges 30% of the 'source' image with 70% of the 'destination' image. Thus it is equivalent to -blend 30x70%.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 90 lines · 29 tokens per session scan B 31e664a2fadb
image-editing is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 997 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
llm-council
Query multiple LLM models in parallel from CodeAct and cross-reference their responses.
environment-discovery
Systematic exploration of unknown environments before starting work.
performant-code
Writing efficient code that handles large data and tight constraints.
rag-eval
NVIDIA RAG Blueprint evaluation guidance for measuring retrieval and answer quality with stable datasets, baselines, and reproducible scoring workflows.