Eval

Community

jh941213

eval

Evaluate code output on 4 axes (functionality/quality/originality/security) with scoring. Spawns an independent Evaluator agent. Triggers on: eval, evaluate, quality score, code evaluation. NOT for: writing code, implementation, review.

Overview

Publisher	jh941213
Repository	`my-cc-harness`
Skill name	`eval`
Stars	125
Forks	35
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by jh941213 on GitHub. Read the source before you install it.

Installation

Install the Eval AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/jh941213/my-cc-harness.git /tmp/my-cc-harness
mkdir -p .claude/skills
cp -r /tmp/my-cc-harness/skills_en/eval .claude/skills/eval

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Eval in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Eval on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Eval is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Code Eval (independent evaluation)

Spawns an Evaluator agent separated from the Generator (implementer) for independent assessment.

How to evaluate with a separate model: run via the gemini CLI (if installed) or in a separate new session. If neither is possible, run an independent subagent that does not reference the generation context, even within the same session.

Process

Step 1: Spawn the Evaluator agent


Agent(subagent_type="evaluator",
  prompt="Read ~/.claude/agents/evaluator.md and evaluate the current project.
         4 axes (functional correctness/code quality/originality/usability&security), 100 points total.
         Save the result to EVAL_REPORT.md.")

Step 2: Review results

When the Evaluator finishes, read EVAL_REPORT.md and summarize for the user:


📊 Eval result: [PASS/CONDITIONAL/FAIL] — [N]/100

Functional correctness: [N]/40 | Code quality: [N]/25
Originality: [N]/20 | Usability & security: [N]/15

[Summary of items needing fixes]

Step 3: On CONDITIONAL/FAIL

List the required fixes concretely and ask whether to re-evaluate after fixing. Re-evaluation applies the same criteria (max 3 rounds).

pass@k idempotency test (optional)

Run the same prompt k times to measure quality consistency:

bash
# k=3 example
for i in 1 2 3; do
  run /eval → record score
done
# all 3 runs 85+ → idempotency achieved
# score variance > 15 points → unstable (harness needs tuning)

Level idempotency: measures whether the same quality level holds — not byte-identical code.

Frequently asked questions

What does the Eval AI skill do?

Why use Eval on TypingMind?

Because you install it once and use it with any model. Eval is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Eval in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jh941213/my-cc-harness/tree/main/skills_en/eval. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Eval?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Eval?

As many as you like. As long as a model supports skills, you can use Eval with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Eval AI skill free?

It is published on GitHub by jh941213. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Slides

nextlevelbuilder

OrganizationPopular

Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman",…

Migration

Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.

Blog Post

A long-form article / blog post — masthead, hero image placeholder, article body with figures and pull quotes, author byline, related posts. Use when the brief asks for "blog", "article", "post",…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Code Eval (independent evaluation)

Process

Step 1: Spawn the Evaluator agent

Step 2: Review results

Step 3: On CONDITIONAL/FAIL

pass@k idempotency test (optional)

Frequently asked questions

Related AI Skills

Set up your own AI workspace now