Classifier Candidate Benchmark

Community

Sahil-SS9

classifier-candidate-benchmark

Run candidates through the frozen exam and report each verdict with its gates, utility, calibration, determinism and latency — including the candidates that fail.

Overview

Publisher	Sahil-SS9
Repository	`agent-personas`
Skill name	`classifier-candidate-benchmark`
Stars	67
Forks	4
Bundled files	1
License	MIT
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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Sahil-SS9 on GitHub. Read the source before you install it.

Installation

Install the Classifier Candidate Benchmark 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.
https://github.com/Sahil-SS9/agent-personas/tree/main/skills/classifier-candidate-benchmark
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/Sahil-SS9/agent-personas/tree/main/skills/classifier-candidate-benchmark

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

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/Sahil-SS9/agent-personas.git /tmp/agent-personas
mkdir -p .claude/skills
cp -r /tmp/agent-personas/skills/classifier-candidate-benchmark .claude/skills/classifier-candidate-benchmark

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

Use it in TypingMind

Enable Classifier Candidate Benchmark 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 Classifier Candidate Benchmark 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 Classifier Candidate Benchmark 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.

Classifier candidate benchmark

When to use

Evaluating models for a decision, including reproductions of commercial ones.

Procedure

Run each candidate through the identical harness and save raw answers, not just scores.
Report per candidate: gates passed or failed, utility at the operating point, calibration, determinism across repeats, latency, and marginal cost.
Adopt the canonical serving path the author specifies before judging a candidate; an adapted path is a different model.
Record byte-identical determinism checks across runs.
Publish the rejects with their reason. A benchmark that only reports a winner is not a benchmark.

Decision rules

Non-determinism disqualifies a candidate where reproducible routing is required.
Latency is a gate, not a footnote. A qualifying model at eight seconds per input against a 100-millisecond budget is a design problem, not a pass.
Hosted commercial references are useful as calibration and unacceptable as a hard dependency when spend or retention is a constraint.
Re-run after any upstream correction, and report whether the verdict moved.

Pitfalls

Judging a model on a non-canonical serving path and blaming the model.
Reporting only the winner.
Ignoring marginal cost per call in a high-volume pre-filter.

Done

Every candidate has a dated verdict with gates, utility, calibration, determinism, latency and cost — and the rejects are documented as thoroughly as the winner.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

NOTICE1 KB

Frequently asked questions

What does the Classifier Candidate Benchmark AI skill do?

Run candidates through the frozen exam and report each verdict with its gates, utility, calibration, determinism and latency — including the candidates that fail.

Why use Classifier Candidate Benchmark on TypingMind?

Because you install it once and use it with any model. Classifier Candidate Benchmark 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 Classifier Candidate Benchmark in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Sahil-SS9/agent-personas/tree/main/skills/classifier-candidate-benchmark. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Classifier Candidate Benchmark?

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 Classifier Candidate Benchmark?

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

Is the Classifier Candidate Benchmark AI skill free?

Yes. It is published on GitHub by Sahil-SS9 under the MIT license. 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

Tdd Workflow

affaan-m

CommunityPopular

Usar este skill al escribir nuevas funcionalidades, corregir bugs o refactorizar código. Aplica el desarrollo guiado por pruebas con 80%+ de cobertura incluyendo pruebas unitarias, de integración y…

Angular Developer

Angular コードを生成し、アーキテクチャガイダンスを提供します。プロジェクトの作成、コンポーネント、またはサービスを作成するとき、または反応性（シグナル、linkedSignal、リソース）、フォーム、依存性注入、ルーティング、SSR、アクセシビリティ（ARIA）、アニメーション、スタイリング（コンポーネントスタイル、Tailwind CSS）、テスト、または CLI ツール作成のベスト…

Anatomy

Explain an idea as an interactive isometric machine figure.

Auteur

Design and build cinematic, award-level web pages.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Classifier candidate benchmark

When to use

Procedure

Decision rules

Pitfalls

Done

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now