Evaluate Presets
CheckedEvaluates preset configurations to determine their effectiveness and suitability for a given task, saving time and optimizing results.
Install on your platform
evaluate-presets. SKILL.md is marked internal, so the skills CLI hides it.We check each listing against its upstream repository with the rules the skills CLI uses, last on 2026-10-16. We don't show a command we know will fail.
What we know about this skill
Publisher
mikeyobrien
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned mikeyobrien/ralph-orchestrator at edc2b3268c.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- edc2b3268c
- Scanned
- 1 file, 216 lines
About this skill
What it does
The evaluate-presets skill allows an AI agent to assess and compare different preset configurations. It can analyze the impact of various settings on a system's performance or behavior, providing insights for optimization. This enables agents to select the most suitable presets based on defined criteria and goals.
When to use it
- System Tuning: When configuring a new software application and needing to determine optimal initial parameters.
- Performance Optimization: To identify preset combinations that maximize efficiency or minimize resource consumption in an existing system.
- A/B Testing: For comparing the effects of different preset configurations on user experience or other key metrics.
- Automated Configuration: To automatically select and apply the best preset based on real-time conditions or predefined objectives.
Key capabilities
- Preset Analysis: Evaluates the impact of various presets.
- Comparative Assessment: Compares multiple preset configurations side-by-side.
- Performance Metrics: Provides insights into system performance under different settings.
- Configuration Selection: Recommends optimal presets based on defined criteria.
Example prompts
- "Evaluate these three presets for the image generation model and tell me which produces the most realistic results."
- "Compare preset A and preset B for this audio processing pipeline, focusing on latency."
- “Which of these presets uses the least memory?”
Tips & gotchas
The effectiveness of this skill depends on having clearly defined evaluation criteria. Ensure you provide specific metrics or goals for the AI agent to optimize against when requesting an assessment.