How do I install the Prompted Generator skill?

Run npx skillmds@latest add opendcai/prompted-generator-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Prompted Generator safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Prompted Generator?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Prompted Generator free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Prompted Generator?

opendcai (@opendcai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Prompted Generator by opendcai — Agent Skill

Name: Prompted Generator
Author: opendcai

Prompted Generator

Reference documentation for the PromptedGenerator operator. Covers constructor parameters, run() signature, actual row-processing behavior, and pipeline usage notes. Use when: integrating PromptedGenerator into a DataFlow pipeline for single-field LLM generation.

opendcai Updated Sep 21, 2026

File contents

PromptedGenerator Operator Reference

PromptedGenerator is DataFlow's basic single-field LLM generation operator.

For each row in the current DataFrame, it reads the value from input_key. If that value is truthy, it builds one LLM input as:

user_prompt + str(row[input_key])

It then calls llm_serving.generate_from_input(...) in batch and writes the generated results into output_key.

1. Import

from dataflow.operators.core_text import PromptedGenerator

2. Constructor

PromptedGenerator(
    llm_serving,                               # required
    system_prompt="You are a helpful agent.",  # optional
    user_prompt="",                            # optional
    json_schema=None,                          # optional
)

Parameter	Required	Default	Description
`llm_serving`	Yes	None	LLM service object implementing `generate_from_input(...)`
`system_prompt`	No	`"You are a helpful agent."`	System prompt passed to the serving layer
`user_prompt`	No	`""`	Prefix prepended directly before each valid row's input text
`json_schema`	No	`None`	Optional schema forwarded to the serving layer

3. run() Signature

op.run(
    storage=self.storage.step(),
    input_key="raw_content",
    output_key="generated_content",
)
# returns: output_key

Parameter	Required	Default	Description
`storage`	Yes	None	Current operator-step storage object
`input_key`	No	`"raw_content"`	Column read from the current DataFrame
`output_key`	No	`"generated_content"`	Column written back to the DataFrame

4. Actual Execution Logic

The operator performs the following steps:

Read the current DataFrame from storage.
Iterate over the DataFrame row by row.
For each row, read raw_content = row.get(input_key, "").
Only if raw_content is truthy, append user_prompt + str(raw_content) to the batch LLM input list.
Call:

llm_serving.generate_from_input(
    user_inputs=llm_inputs,
    system_prompt=system_prompt,
    json_schema=json_schema,
)

Write the generated list into dataframe[output_key].
Persist the updated DataFrame through storage.write(dataframe).
Return output_key.

5. Important Rules

input_key must exist in the current DataFrame.
user_prompt is a plain string prefix, not a template engine.
The implementation skips rows whose input_key value is empty, None, or otherwise falsy when building LLM inputs.

6. Typical Usage

from dataflow.operators.core_text import PromptedGenerator

prompted_gen = PromptedGenerator(
    llm_serving=self.llm_serving,
    system_prompt="You are a helpful agent.",
    user_prompt="Summarize the following content in one sentence:\n",
)

prompted_gen.run(
    storage=self.storage.step(),
    input_key="raw_content",
    output_key="summary",
)

7. Return Value

return output_key

This is intended for downstream operator chaining.

---name: prompted-generator-2description: Reference documentation for the PromptedGenerator operator. Covers constructor parameters, run() signature, actual row-processing behavior, and pipeline usage notes. Use when: integrating PromptedGenerator into a DataFlow pipeline for single-field LLM generation.---# PromptedGenerator Operator Reference`PromptedGenerator` is DataFlow's basic single-field LLM generation operator.For each row in the current DataFrame, it reads the value from `input_key`. If that value is truthy, it builds one LLM input as:```pythonuser_prompt + str(row[input_key])```It then calls `llm_serving.generate_from_input(...)` in batch and writes thegenerated results into `output_key`.## 1. Import```pythonfrom dataflow.operators.core_text import PromptedGenerator```## 2. Constructor```pythonPromptedGenerator( llm_serving, # required system_prompt="You are a helpful agent.", # optional user_prompt="", # optional json_schema=None, # optional)```| Parameter | Required | Default | Description ||-----------|----------|---------|-------------|| `llm_serving` | Yes | None | LLM service object implementing `generate_from_input(...)` || `system_prompt` | No | `"You are a helpful agent."` | System prompt passed to the serving layer || `user_prompt` | No | `""` | Prefix prepended directly before each valid row's input text || `json_schema` | No | `None` | Optional schema forwarded to the serving layer |## 3. run() Signature```pythonop.run( storage=self.storage.step(), input_key="raw_content", output_key="generated_content",)# returns: output_key```| Parameter | Required | Default | Description ||-----------|----------|---------|-------------|| `storage` | Yes | None | Current operator-step storage object || `input_key` | No | `"raw_content"` | Column read from the current DataFrame || `output_key` | No | `"generated_content"` | Column written back to the DataFrame |## 4. Actual Execution LogicThe operator performs the following steps:1. Read the current DataFrame from `storage`.2. Iterate over the DataFrame row by row.3. For each row, read `raw_content = row.get(input_key, "")`.4. Only if `raw_content` is truthy, append `user_prompt + str(raw_content)` to the batch LLM input list.5. Call:```pythonllm_serving.generate_from_input( user_inputs=llm_inputs, system_prompt=system_prompt, json_schema=json_schema,)```6. Write the generated list into `dataframe[output_key]`.7. Persist the updated DataFrame through `storage.write(dataframe)`.8. Return `output_key`.## 5. Important Rules1. `input_key` must exist in the current DataFrame.2. `user_prompt` is a plain string prefix, not a template engine.3. The implementation skips rows whose `input_key` value is empty, `None`, or otherwise falsy when building LLM inputs.## 6. Typical Usage```pythonfrom dataflow.operators.core_text import PromptedGeneratorprompted_gen = PromptedGenerator( llm_serving=self.llm_serving, system_prompt="You are a helpful agent.", user_prompt="Summarize the following content in one sentence:\n",)prompted_gen.run( storage=self.storage.step(), input_key="raw_content", output_key="summary",)```## 7. Return Value```pythonreturn output_key```This is intended for downstream operator chaining.

Frequently asked questions