bench-answer-generator

A reference for the BenchAnswerGenerator operator, which creates model answers for rows of benchmark questions. A benchmark is a set of test questions used to evaluate a model or system.

In plain words
What is it for?
Use it when adding model-generated answers to benchmark data before passing that data to a unified benchmark evaluator.
Why use it?
It explains the operator's constructor, inputs, generation behavior, and connection to unified benchmark evaluation pipelines.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/opendcai/dataflow-webui/bench-answer-generator
Any agent
npx skills add OpenDCAI/DataFlow-WebUI --skill bench-answer-generator
Clone the repo
git clone --depth 1 https://github.com/OpenDCAI/DataFlow-WebUI

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,748 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00055 $0.01748
Opus 5 $0.00028 $0.00874
Sonnet 5 $0.00011 $0.00350
Haiku 4.5 $0.00006 $0.00175

Measured 3d ago against content hash d8c078527003, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bench-answer-generator scanned grade A with 0 findings 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 3d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/canonical/core_text/generate/bench-answer-generator/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BenchAnswerGenerator Operator Reference

BenchAnswerGenerator generates model answers from a benchmark dataframe and is designed to align with UnifiedBenchDatasetEvaluator.

1. Import

from dataflow.operators.core_text import BenchAnswerGenerator

2. Constructor

BenchAnswerGenerator(
    eval_type="key2_qa",
    llm_serving=llm,
    prompt_template=FormatStrPrompt(f_str_template="Question: {question}\nAnswer:"),
    system_prompt="You are a helpful assistant specialized in generating answers to questions.",
    allow_overwrite=False,
    force_generate=False,
)
Parameter Required Default Description
eval_type No "key2_qa" Evaluation type
llm_serving Yes None LLM service object implementing generate_from_input(...)
prompt_template No FormatStrPrompt Prompt object used to build prompts. In practice, pass a FormatStrPrompt(...) instance, None, or a DIYPromptABC subclass instance
system_prompt No "You are a helpful assistant specialized in generating answers to questions." System prompt forwarded to the serving layer when supported
allow_overwrite No False Whether to overwrite an existing output column
force_generate No False Whether to force generation for some types that are skipped by default

Important prompt_template Note

Although the source code sets the default value to FormatStrPrompt, that default is the class object itself, not an instance.

In normal usage, you usually want to pass a FormatStrPrompt(...) instance so you can explicitly control the prompt text. None is also supported and makes the operator fall back to its built-in prompt builder.

Use one of these patterns instead:

from dataflow.prompts.core_text import FormatStrPrompt

prompt_template=FormatStrPrompt(
    f_str_template="Question: {question}\nAnswer:"
)

or

prompt_template=None

Read the full file on GitHub · 179 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 3d ago First seen · 179 lines · 55 tokens per session scan A d8c078527003

Subscribe to this mod's changes

bench-answer-generator is a skill published in the GitHub repository OpenDCAI/DataFlow-WebUI (224 stars, last pushed 7d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,748 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens