Skip to content
TrustedSkillsbeta
Back to all skills

Together Evaluations

Listed
zainhas·vlatest·ai-ml·MIT

Together Evaluations assesses large language model outputs for quality, safety, and alignment, streamlining evaluation workflows & improving LLM performance.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add zainhas/skills_draft --skill together-evaluations -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

zainhas

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.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: api.together.xyz.

    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.

    Hosts contacted

    api.together.xyzundeclared

    What it found (3 of 8)

    • skills/together-evaluations/references/api-reference.md:216contacts api.together.xyz
      curl -X POST "https://api.together.xyz/v1/evaluation" \
    • skills/together-evaluations/references/api-reference.md:295contacts api.together.xyz
      curl -X POST "https://api.together.xyz/v1/evaluation" \
    • skills/together-evaluations/references/api-reference.md:386contacts api.together.xyz
      curl -X POST "https://api.together.xyz/v1/evaluation" \

  • 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 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 zainhas/togetherai-skills at 0995dd3117.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
0995dd3117
Manifest
skills/together-evaluations/SKILL.md
Scanned
5 files, 1,736 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The together-evaluations skill allows AI agents to evaluate outputs from other models, providing feedback and scoring based on defined criteria. It can assess responses for relevance, accuracy, coherence, and overall quality. This enables iterative improvement of model performance through targeted analysis and refinement.

When to use it

  • Model Comparison: Evaluate the output of multiple language models against a specific task or prompt to determine which performs best.
  • Feedback Loop: Integrate evaluation scores into a training pipeline to automatically refine and improve a model's responses over time.
  • Content Quality Control: Assess generated content (e.g., articles, code) for quality before publication or deployment.
  • Prompt Engineering Optimization: Analyze how different prompts impact the quality of model outputs and identify optimal prompt formulations.

Key capabilities

  • Model output evaluation
  • Scoring based on defined criteria
  • Feedback generation
  • Relevance assessment
  • Accuracy verification

Example prompts

  • "Evaluate this response: [model output] against these criteria: relevance, accuracy, and coherence."
  • "Score the following text for quality, considering grammar, clarity, and factual correctness: [text to evaluate]."
  • "Compare the outputs of Model A and Model B given the prompt 'Summarize this article:' [article content]. Provide a detailed evaluation of each response."

Tips & gotchas

The effectiveness of this skill depends heavily on clearly defined evaluation criteria. Ambiguous or poorly-defined criteria will lead to inconsistent results.