Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

/form-compile — Генерация Form.xml · nikolay-shirokov | DecimalAI

Codingby nikolay-shirokov

/form-compile — Генерация Form.xml

Компиляция управляемой формы 1С из JSON-определения или из метаданных объекта. Используй когда нужно создать форму с нуля по описанию элементов или сгенерировать типовую форму

Never made a case worseMaintained

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

30%91%of test cases passed +61 pts

Without skill7 of 23

With skill21 of 23

14 fixed7 passed either way2 still failing0 broke

Model 10/10/2026v2 · latest is v5

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.8-flash on 11/1/2026 did not produce a publishable comparison (graded differently). The snapshot above is the previously measured run.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskConfigure the top-level properties of a JSON DSL form definition to open in modal lock mode ('LockOwnerWindow') and trigger a server setup event procedure named 'OnCreateServer'.

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add nikolay-shirokov-form-compile
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install nikolay-shirokov-form-compile

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/nikolay-shirokov-form-compile/SKILL.md https://app.decimal.ai/s/nikolay-shirokov-form-compile/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/nikolay-shirokov-form-compile/SKILL.md

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add nikolay-shirokov-form-compile

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("nikolay-shirokov-form-compile")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/nikolay-shirokov-form-compile/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add nikolay-shirokov-form-compile

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/nikolay-shirokov-form-compile/SKILL.md https://app.decimal.ai/s/nikolay-shirokov-form-compile/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/nikolay-shirokov-form-compile/SKILL.md

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/nikolay-shirokov-form-compile/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/nikolay-shirokov-form-compile.json

This gets SKILL.md only. The skill's 21 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v5 (v2 tested 10/10/2026)
Source: nikolay-shirokov/cc-1c-skills ↗
License: MIT

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

/form-compile — Генерация Form.xml

Два режима:

JSON DSL — из JSON-определения формы
From object (-FromObject) — заготовка формы объекта конфигурации по его метаданным: поля объекта в стиле ЕРП/УТ, служебные убраны; событий, команд, связей полей и итогов в ней нет

С чего начать

содержимое формы уже есть — /form-edit;
форма описана в задаче целиком (текстом или эскизом) — JSON по описанию;
описана часть формы (поля, блок, поведение) — для формы объекта, списка, выбора, группы или записи заготовка -EmitDsl, впишите в неё описанное, сборка -JsonPath; для остальных форм — JSON;
форма по образцу другой формы конфигурации («как у ЗаказКлиента») — изучите образец через /form-info; для этих же форм разложите по нему заготовку -EmitDsl, для остальных — JSON; обработчики образца переносите только вместе с кодом;
о форме ничего не сказано — для этих же форм -FromObject, для остальных — JSON.

Если раскладка формы не задана в задаче и заготовки нет — архетип формы, имена групп и ширины полей в references/layout-patterns.md. В заготовке -FromObject / -EmitDsl раскладка уже как в типовых.

Параметры

Параметр	Обязательный	Описание
JsonPath	режим 1	Путь к JSON-определению формы
OutputPath	да	Путь к выходному Form.xml
FromObject	режим 2	Флаг (без значения) — генерация по метаданным объекта
Purpose	нет	Назначение, если основная форма объекта названа нестандартно
EmitDsl	нет	Сохранить сгенерированное JSON-определение в файл

Команда

# Режим JSON DSL
powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/form-compile.ps1" -JsonPath "<json>" -OutputPath "<Form.xml>"

# Режим from-object: объект и назначение берутся из пути формы
powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/form-compile.ps1" -FromObject -OutputPath "<.../Documents/ИмяОбъекта/Forms/ФормаДокумента/Ext/Form.xml>"

# Заготовка для доработки: сохранить JSON, доработать, собрать режимом JSON DSL
powershell.exe -NoProfile -File "${CLAUDE_SKILL_DIR}/scripts/form-compile.ps1" -FromObject -OutputPath "<Form.xml>" -EmitDsl "<form.json>"

JSON DSL

Структура

{
  "title": "Заголовок формы",
  "properties": { "windowOpeningMode": "LockOwnerWindow" },
  "events": { ... },
  "elements": [ ... ],
  "attributes": [ ... ],
  "commands": [ ... ],
  "parameters": [ ... ]
}

title — заголовок формы (строка или {ru, en})
properties — свойства формы: windowOpeningMode, commandBarLocation, width, height и др. (полный список — references/form-properties.md)
events — обработчики событий формы: { "ИмяСобытия": "ИмяПроцедуры" }; имена по конвенции — списком: ["OnCreateAtServer", "OnOpen"] → ПриСозданииНаСервере, ПриОткрытии
excludedCommands — убрать стандартные команды формы: ["Reread", "Copy"]

Элементы (ключ определяет тип)

Ключ	Элемент	Значение ключа
`group`	Обычная группа	ориентация: `vertical` / `horizontalIfPossible` / `alwaysHorizontal`
`input`	Поле ввода	имя
`check`	Флажок	имя
`radio`	Переключатель	имя
`label`	Надпись	имя (текст — в `title`)
`labelField`	Поле-надпись (значение без редактирования)	имя
`table`	Таблица	имя
`columnGroup`	Группа колонок (внутри `columns` таблицы)	`horizontal` / `vertical` / `inCell`
`pages` / `page`	Страницы / страница	имя
`button`	Кнопка	имя
`buttonGroup`	Группа кнопок (в командной панели или подменю)	имя
`popup`	Подменю	имя
`cmdBar`	Командная панель в раскладке формы	имя
`autoCmdBar`	Командная панель самой формы	имя (обычно `ФормаКоманднаяПанель`)
`picture`	Картинка	имя
`picField`	Поле-картинка	имя

Табличный документ, HTML, календарь, диаграммы и другие особые поля — по индексу ниже.

Общие свойства элементов

Ключ	Описание
`name`	Имя элемента, если отличается от значения ключа типа. Имена в форме уникальны
`title`	Заголовок (строка или `{ru, en}`); `""` — без заголовка
`tooltip`	Всплывающая подсказка
`visible: false` / `enabled: false` / `readOnly: true`	Скрыть / сделать недоступным / только чтение
`titleLocation`	`none` / `left` / `right` / `top` / `bottom` / `auto`
`width` / `height`	Размер
`horizontalStretch` / `verticalStretch`	Растягивать
`autoMaxWidth: false`	Снять предел ширины (поле тянется на всю доступную ширину)
`events`	Обработчики: `{ "OnChange": "ИмяОбработчика" }`; имена по конвенции — списком: `["OnChange", "StartChoice"]` (элемент списка может задать имя сам: `{ "event": "Clearing", "handler": "Имя" }`)

События

Имена регистрозависимы.

Частые:

Форма: OnCreateAtServer, OnOpen, NotificationProcessing, BeforeClose, OnClose, ChoiceProcessing, FillCheckProcessingAtServer, OnLoadDataFromSettingsAtServer; у формы объекта или записи — OnReadAtServer, BeforeWrite, BeforeWriteAtServer, AfterWrite, AfterWriteAtServer input: OnChange, StartChoice, ChoiceProcessing, Clearing, AutoComplete, TextEditEnd check / radio: OnChange table: Selection, OnActivateRow, BeforeAddRow, BeforeDeleteRow, AfterDeleteRow, BeforeRowChange, OnStartEdit, OnEditEnd, BeforeEditEnd, OnChange, OnActivateCell, ChoiceProcessing, Drag; только у таблицы динамического списка — OnGetDataAtServer, BeforeLoadUserSettingsAtServer, OnUpdateUserSettingSetAtServer label / labelField: Click, URLProcessing picture / picField: Click pages: OnCurrentPageChange spreadsheet: Selection, OnChangeAreaContent, OnActivate, DetailProcessing html: OnClick, DocumentComplete

Остальные события этих и других полей (календарь, планировщик, диаграммы, документы) — references/events.md. У кнопки, страницы, группы колонок, командной панели и подменю событий нет.

Поле ввода (input)

Ключ	Описание
`path`	Путь к данным: `"Объект.Организация"`, `"ИмяРеквизита"`
`multiLine: true`	Многострочное (комментарий)
`choiceButton` / `clearButton` / `dropListButton`	Кнопки выбора, очистки, выпадающего списка
`markIncomplete: true`	Подсвечивать незаполненное
`inputHint`	Подсказка в пустом поле
`skipOnInput: true`	Пропускать при переходе по Enter/Tab
`maxWidth`	Предел ширины

Список выбора, маска, формат, пароль и другие кнопки — references/input-fields.md.

Флажок (check) и переключатель (radio)

check: path, titleLocation (по умолчанию заголовок справа). Вид «выключатель» или «тумблер» — references/input-fields.md.

radio: path, radioButtonType (Auto / RadioButtons / Tumbler), columnsCount, choiceList:

{ "radio": "СпособКурса", "path": "Объект.СпособУстановкиКурса", "radioButtonType": "Tumbler",
  "choiceList": [
    { "value": "Enum.СпособыКурса.EnumValue.Авто",   "presentation": "Автоматически" },
    { "value": "Enum.СпособыКурса.EnumValue.Ручной", "presentation": { "ru": "Вручную", "en": "Manual" } }
  ] }

value — строка, число, булево или значение перечисления "Enum.Тип.EnumValue.Значение"; presentation — текст варианта.

Надпись (label) и поле-надпись (labelField)

label: title — текст (поддерживает разметку, см. references/tooltips-text.md), hyperlink: true — ссылка. labelField: path, hyperlink: true — значение как ссылка.

Группа (group)

Ключ	Описание
`behavior`	`collapsible` — сворачиваемая, `popup` — всплывающая; не указан — обычная
`showTitle: true`	Показывать заголовок (без ключа у обычной группы показан, если задан `title` или `titleDataPath`, иначе скрыт; у сворачиваемой и всплывающей — показан)
`representation`	`none` / `normal` / `weak` / `strong` — рамка группы
`united: false`	Выравнивать поля только внутри группы, а не вместе с соседними
`children`	Вложенные элементы

Свёрнутая при открытии группа, интервалы, заголовок из данных — references/groups-pages.md.

Таблица (table)

Таблица привязывается к реквизиту-таблице (ValueTable, табличная часть объекта, динамический список) — см. «Связка элемент + реквизит».

Ключ	Описание
`path`	Путь к реквизиту-таблице
`columns`	Колонки — элементы (`input`, `check`, `labelField`, `picField`, `columnGroup`); путь колонки — путь таблицы плюс имя колонки: `Объект.Товары.Сумма`, `Данные.Сумма`
`changeRowSet: true` / `changeRowOrder: true`	Разрешить добавлять/удалять / перемещать строки
`header: false`	Без шапки
`heightInTableRows`	Высота в строках
`commandBar`	Кнопки командной панели таблицы — сюда команды строк («Отметить все», «Снять отметки», «Заполнить», «Подбор»), а не в панель формы или группу на форме: `[ { "button": "ЦеныОтметитьВсе", "command": "ОтметитьВсе" } ]` (`references/buttons-commands.md`)
`commandBarLocation`	`None` / `Top` / `Bottom` / `Auto`
`searchStringLocation`	`None` / `Top` / `Bottom` / `CommandBar` / `Auto`
`choiceMode: true`	Таблица выбора (форма выбора)

Подвал с итогами, дерево, выделение, закрепление колонок, перетаскивание — references/table-advanced.md.

columnGroup группирует колонки: title, showInHeader, children; inCell — несколько колонок в одной ячейке:

{ "table": "Список", "path": "Список", "columns": [
    { "columnGroup": "horizontal", "name": "ГруппаСрок", "title": "Срок", "children": [
        { "input": "ДатаНачала", "path": "Список.ДатаНачала" },
        { "input": "ДатаОкончания", "path": "Список.ДатаОкончания" } ] },
    { "input": "Комментарий", "path": "Список.Комментарий" }
] }

Страницы (pages + page)

pages: pagesRepresentation (TabsOnTop / TabsOnBottom / None — без закладок), children — массив page. page: title, group (ориентация содержимого), children.

Кнопки и командные панели

Ключ (button)	Описание
`command`	Команда формы → `Form.Command.Имя`
`stdCommand`	Стандартная: `"Close"`; с точкой — команда элемента: `"Товары.Add"`
`defaultButton: true`	Кнопка по умолчанию
`type`	`usual` / `hyperlink`
`representation`	`Auto` / `Text` / `Picture` / `PictureAndText`
`locationInCommandBar`	`InCommandBar` / `InAdditionalSubmenu`

autoCmdBar — командная панель формы, сюда помещают основные действия:

{ "autoCmdBar": "ФормаКоманднаяПанель", "children": [
    { "button": "Загрузить", "command": "Загрузить", "defaultButton": true },
    { "popup": "Печать", "title": "Печать", "children": [
        { "button": "ПечатьСчета", "command": "ПечатьСчета" } ] },
    { "buttonGroup": "ГруппаНавигация", "children": [
        { "button": "Назад", "command": "Назад" },
        { "button": "Далее", "command": "Далее" } ] }
] }

popup — подменю: title, children.
buttonGroup — кнопки, объединённые в группу: title, children.
cmdBar — отдельная панель в раскладке формы: autofill, children.
autoCmdBar: autofill: false — без стандартных команд, horizontalAlign — выравнивание.

Картинки кнопок, кнопки-переключатели, команды таблицы в группе кнопок, своё контекстное меню у элемента — references/buttons-commands.md.

Картинка (picture) и поле-картинка (picField)

picture: src — "StdPicture.X" / "CommonPicture.X", width, height. picField: path; для булева или числа — valuesPicture (иначе значок не рисуется). Подробнее — references/pictures.md.

Реквизиты (attributes)

{ "name": "Объект", "type": "DataProcessorObject.Загрузка", "main": true }
{ "name": "Итого", "type": "decimal(15,2)", "title": "Итого" }
{ "name": "Таблица", "type": "ValueTable", "columns": [
    { "name": "Номенклатура", "type": "CatalogRef.Номенклатура" },
    { "name": "Количество", "type": "decimal(10,3)" } ] }
{ "name": "Список", "type": "DynamicList", "main": true,
  "settings": { "mainTable": "Catalog.Номенклатура" } }

main: true — основной реквизит формы (объект, набор записей, динамический список)
savedData: true — сохраняемые данные (у основного реквизита-объекта ставится само)
columns — колонки ValueTable / ValueTree
settings — настройки динамического списка (references/dynamic-list.md)

Сохранение в настройках, проверка заполнения, функциональные опции — references/attributes-advanced.md.

Команды (commands) и параметры (parameters)

"commands": [ { "name": "Загрузить", "action": "ЗагрузитьОбработка", "title": "Загрузить", "shortcut": "Ctrl+Enter", "picture": "StdPicture.Refresh" } ]
"parameters": [ { "name": "Основание", "type": "DocumentRef.Заказ" } ]

Команды: name, action (процедура-обработчик), title, shortcut, picture. Параметры: name, type, key: true — ключевой.

Система типов

DSL	Тип
`string` / `string(100)`	Строка (неограниченная / длины 100)
`decimal(15,2)` / `decimal(10,0,nonneg)`	Число / неотрицательное
`boolean`	Булево
`date` / `dateTime` / `time`	Дата / дата и время / время
`CatalogRef.X` / `DocumentRef.X` / `EnumRef.X` / …	Ссылки
`CatalogObject.X` / `DocumentObject.X` / `DataProcessorObject.X` / `ReportObject.X`	Объекты (основной реквизит)
`InformationRegisterRecordSet.X` / `AccumulationRegisterRecordSet.X`	Наборы записей
`ValueTable` / `ValueTree` / `ValueList`	Таблица / дерево / список значений
`DynamicList`	Динамический список
`TypeDescription`, `UUID`, `FormattedString`, `Picture`, `Color`, `Font`, `DataCompositionSettings`, `StandardPeriod`, `mxl:SpreadsheetDocument`	Платформенные
`Тип1 \| Тип2`	Составной

Также ChartOfAccountsRef/Object, ChartOfCharacteristicTypesRef/Object, ChartOfCalculationTypesRef/Object, ExchangePlanRef/Object, BusinessProcessRef/Object, TaskRef/Object, AccountingRegisterRecordSet, InformationRegisterRecordManager, ConstantsSet. Наборы типов — references/type-system-advanced.md.

FormDataStructure, FormDataCollection, FormDataTree — не типы реквизита (ошибка при загрузке). Вместо них — объектный тип (DocumentObject.X…), ValueTable, ValueTree.

Связка элемент + реквизит

Элемент показывает данные реквизита через path.

Табличная часть основного реквизита — путь Объект.<ТЧ>, колонки — Объект.<ТЧ>.<Реквизит>:

{ "table": "Товары", "path": "Объект.Товары", "columns": [
    { "input": "ТоварыНоменклатура", "path": "Объект.Товары.Номенклатура" },
    { "input": "ТоварыКоличество", "path": "Объект.Товары.Количество" } ] }

Таблица на реквизите формы — реквизит ValueTable с колонками:

{
  "elements": [
    { "table": "Данные", "path": "Данные", "changeRowSet": true, "columns": [
        { "input": "ДанныеДата", "path": "Данные.Дата" },
        { "input": "ДанныеСумма", "path": "Данные.Сумма" } ] }
  ],
  "attributes": [
    { "name": "Данные", "type": "ValueTable", "columns": [
        { "name": "Дата", "type": "date" },
        { "name": "Сумма", "type": "decimal(15,2)" } ] }
  ]
}

Пример: диалог загрузки

{
  "title": "Загрузка из файла",
  "elements": [
    { "autoCmdBar": "ФормаКоманднаяПанель", "children": [
      { "button": "Загрузить", "command": "Загрузить", "defaultButton": true },
      { "button": "Закрыть", "stdCommand": "Close" }
    ]},
    { "group": "horizontal", "name": "ГруппаФайл", "children": [
      { "input": "ИмяФайла", "path": "ИмяФайла", "title": "Файл", "inputHint": "Выберите файл...",
        "choiceButton": true, "events": { "StartChoice": "ИмяФайлаНачалоВыбора" } },
      { "check": "ПерваяСтрокаЗаголовок", "path": "ПерваяСтрокаЗаголовок" }
    ]},
    { "input": "Результат", "path": "Результат", "multiLine": true, "height": 8, "readOnly": true, "title": "Лог" }
  ],
  "attributes": [
    { "name": "Объект", "type": "ExternalDataProcessorObject.ЗагрузкаИзФайла", "main": true },
    { "name": "ИмяФайла", "type": "string" },
    { "name": "ПерваяСтрокаЗаголовок", "type": "boolean" },
    { "name": "Результат", "type": "string" }
  ],
  "commands": [
    { "name": "Загрузить", "action": "ЗагрузитьОбработка", "shortcut": "Ctrl+Enter" }
  ]
}

Служебные узлы элементов (контекстное меню, расширенная подсказка, панели таблицы) и идентификаторы создаются сами. Неизвестный ключ — предупреждение в выводе.

Задача → справочник

Описанного выше хватает для большинства форм. Под задачу подгрузите файл из references/:

Задача	Справочник
Раскладка формы, не заданной в задаче: архетипы документа, списка, обработки, диалога, мастера; имена групп и элементов; ширины полей	`layout-patterns.md`
Список выбора, быстрый выбор, своя форма выбора, маска, формат числа, пароль, выключатель/тумблер, кнопки открытия и создания, поле составного типа	`input-fields.md`
Ограничить выбор отбором, связать поле с другим полем, связь по типу	`choice-params.md`
Свёрнутая группа, интервалы и ширины колонок в группе, заголовок группы или страницы из данных, значок закладки, мастер по шагам (страницы без закладок)	`groups-pages.md`
Итоги в подвале таблицы, дерево, выделение нескольких строк, закрепление колонок, поиск, перетаскивание, убрать стандартные команды таблицы	`table-advanced.md`
Форма списка: источник данных, запрос, отбор, сортировка, группировка, иерархия	`dynamic-list.md`
Кнопка с картинкой, переключатель в панели, команды таблицы в группе кнопок, своё контекстное меню или панель у поля, команда для текущей строки таблицы	`buttons-commands.md`
Подсветить цветом, шрифт, рамка, условное оформление (в форме списка — `dynamic-list.md`)	`appearance.md`
Расширенная подсказка под полем, текст с выделением или ссылкой	`tooltips-text.md`
Картинка, значок в колонке, иконка по значению	`pictures.md`
Печатная форма или отчёт на форме (табличный документ)	`spreadsheet.md`
HTML, текстовый документ, индикатор, ползунок, календарь, период	`special-fields.md`
Диаграмма, диаграмма Ганта, планировщик	`charts.md`
Модальность, размер, прокрутка, Enter, свойства формы документа (время, проведение)	`form-properties.md`
Форма отчёта (СКД)	`report-form.md`
Сохранить значение в настройках, проверка заполнения, функциональные опции, тип элементов списка значений	`attributes-advanced.md`
Видимость и доступ по ролям	`roles-access.md`
Командный интерфейс формы (переходы, важные команды)	`command-interface.md`
Выравнивание, предел размера, фокус по умолчанию, узкие экраны	`layout-advanced.md`
Какие события есть у элемента или формы, имена обработчиков, с какой платформы	`events.md`
Наборы и составные типы	`type-system-advanced.md`
Изменить, как `-FromObject` раскладывает формы во всём проекте (стиль проекта)	`../presets/README.md`

Workflow

Каркас: /form-add создаёт метаданные формы, Module.bsl и регистрирует форму у объекта.
Компиляция: /form-compile наполняет Form.xml; для обработчиков событий и команд, которых ещё нет в модуле, добавляет в Module.bsl пустые процедуры с нужной сигнатурой — остаётся написать тело.
Проверка: /form-validate, /form-info.

Внешние обработки (EPF)

Основной реквизит: ExternalDataProcessorObject.ИмяОбработки (не DataProcessorObject)
Пути данных: реквизиты формы (ИмяРеквизита), а не Объект.ИмяРеквизита — у внешней обработки нет реквизитов объекта в метаданных
Ссылочные типы (CatalogRef.XXX и т.п.) допустимы, но для сборки EPF нужна база с целевой конфигурацией (см. /epf-build)

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 11/9/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

nikolay-shirokov / cc-1c-skills

.claude/skills/form-compile/SKILL.md

View on GitHub ↗

License MITImported 11/9/2026Version v5Bundled 21 files

Illustrative Want to see what nikolay-shirokov/form-compile would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Related skills

Skills that do similar work, with their headline benchmark lift.

nikolay-shirokov/form-editДобавление элементов, реквизитов и команд в существующую управляемую форму 1С. Используй когда нужно точечно модифицировать готовую форму+55 pts pass-rate lift

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

/form-compile — Генерация Form.xml

С чего начать

Параметры

Команда

JSON DSL

Структура

Элементы (ключ определяет тип)

Общие свойства элементов

События

Поле ввода (input)

Флажок (check) и переключатель (radio)

Надпись (label) и поле-надпись (labelField)

Группа (group)

Таблица (table)

Страницы (pages + page)

Кнопки и командные панели

Картинка (picture) и поле-картинка (picField)

Реквизиты (attributes)

Команды (commands) и параметры (parameters)

Система типов

Связка элемент + реквизит

Пример: диалог загрузки

Задача → справочник

Workflow

Внешние обработки (EPF)

SkillSafety

Source

Related skills

More in the registry