Ready to supercharge your AI agents?

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

Schadenfall-Guide & Entscheidungslogik · thomasmoreai | DecimalAI

Legalby thomasmoreai

Schadenfall-Guide & Entscheidungslogik

Schadenfall-Guide und Entscheidungslogik. Leitet Schritt fuer Schritt durch jeden Schadenfall (Unfall, Krankheit, Haftpflicht, Hausrat, Auto, Rechtsschutz, Todesfall, Invaliditaet). Liefert Self-Service-Checklisten, klaert wann und wie melden, welche Nachweise noetig sind, und wie Fristen und Kommunikation laufen. Schweizer Kontext als Standard. Triggert bei Fragen zu Schadenfall, Schadenmeldung, Unfall melden, Versicherung melden, was tun bei Schaden, Schadenformular, Versicherungsfall, Schaden

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

50%77%of test cases passed +27 pts

Without skill11 of 22

With skill17 of 22

7 fixed10 passed either way4 still failing1 broke

Measured on gemini-3.6-flash8/5/2026v1

Track record

Agent runs: 18; All time

See one task, with and without the skill

One test taskEin Rohrbruch in der Decke hat meine Küche überschwemmt. Die Leuchte ist voller Wasser gelaufen. Ein Kollege riet mir, abzuwarten, bis die Hausverwaltung in 2 Wochen einen Handwerker schickt, und solange nichts zu tun. Entsteht mir dadurch ein Problem mit der Versicherung?

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 thomasmoreai-claims-guide
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("thomasmoreai-claims-guide")
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 thomasmoreai-claims-guide

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/thomasmoreai-claims-guide/SKILL.md https://app.decimal.ai/s/thomasmoreai-claims-guide/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/thomasmoreai-claims-guide/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/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/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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("thomasmoreai-claims-guide")
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/thomasmoreai-claims-guide/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/thomasmoreai-claims-guide/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 1 other file is 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 thomasmoreai-claims-guide

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/thomasmoreai-claims-guide/SKILL.md https://app.decimal.ai/s/thomasmoreai-claims-guide/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-claims-guide/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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/thomasmoreai-claims-guide/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/thomasmoreai-claims-guide.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/5/2026
Source: thomasmoreai/legal-skills-open ↗
License: Apache-2.0

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

Schadenfall-Guide & Entscheidungslogik

Overview

Dieser Skill ist ein interaktiver Notfallbegleiter fuer Versicherungsfaelle. Er fuehrt den Nutzer Schritt fuer Schritt durch den Schadenprozess — von der ersten Minute nach dem Ereignis bis zur abgeschlossenen Regulierung. Der Fokus liegt auf klaren Entscheidungsbaeumen: Was tun? Wem melden? Welche Nachweise? Welche Fristen?

Standardkontext: Schweiz (VVG, KVG, UVG, OR). Bei anderen Laendern werden die Referenzdaten entsprechend angepasst.

Companion Skills:

insurance-gap-analysis: Zeigt nach dem Schadenfall, ob Deckungsluecken bestehen.
policy-check: Hilft bei der Optimierung der Policen nach einem Schadenfall-Erlebnis.
scenario-stress-test: Modelliert die finanziellen Auswirkungen laengerer Schadenfaelle.

Wichtig: Dieser Skill ersetzt keine Rechtsberatung. Bei komplexen oder strittigen Faellen immer einen Anwalt oder den Ombudsman der Privatversicherung einschalten. Bei Personenschaeden oder Strafrecht: Rechtsschutzversicherung aktivieren.

Workflow

Dieser Skill hat einen anderen Aufbau als die uebrigen Finance-Skills. Statt 5 linearer Phasen arbeitet er mit einem Entscheidungsbaum: Der Nutzer beschreibt den Schadenfall, und der Skill leitet ihn durch die passende Route.

Schritt 1 — Schadenfall identifizieren

Ziel: Art des Schadenfalls bestimmen und den richtigen Prozess einleiten.

Frage den Nutzer: Was ist passiert?

Ordne den Fall einer Kategorie zu:

#	Kategorie	Beispiele
A	Unfall (Person)	Sturz, Verkehrsunfall, Sportunfall, Arbeitsunfall
B	Krankheit / Arbeitsunfaehigkeit	Langzeitkrankheit, psychische Erkrankung, Operation
C	Haftpflichtschaden (verursacht)	Du hast Drittperson/Sache beschaedigt
D	Haftpflichtschaden (erlitten)	Drittperson hat dich/deine Sache beschaedigt
E	Hausrat / Gebaeudeschaden	Einbruch, Wasserschaden, Feuer, Sturm, Diebstahl
F	Autounfall / Fahrzeugschaden	Kollision, Parkschaden, Diebstahl, Wildtier, Hagel
G	Rechtsstreit	Arbeitsrecht, Mietrecht, Kaufrecht, Nachbarrecht
H	Todesfall	Verstorbener Angehoeriger (Versicherungsansprueche)
I	Invaliditaet	Dauerhafte Einschraenkung nach Unfall oder Krankheit
J	Reise	Annullierung, Gepaeckverlust, Erkrankung im Ausland
K	Anderer Schadenfall	Cyber-Betrug, Identitaetsdiebstahl, Naturereignis

Lade references/swiss-claims-reference.md als Referenz.

Frage anschliessend:

Wann ist es passiert? (Datum, Uhrzeit)
Wo ist es passiert? (Ort, Land)
Wer ist beteiligt? (Personen, Zeugen)
Welche Versicherungen koennten betroffen sein?
Wurde bereits etwas unternommen? (Polizei, Arzt, Meldung)

Schritt 2 — Sofortmassnahmen-Checkliste

Ziel: Sicherstellen, dass alle dringenden Schritte erledigt sind.

Liefere eine massgeschneiderte Sofortmassnahmen-Checkliste basierend auf der Kategorie:

A) Unfall (Person):

SOFORT (erste Stunde):
□ Erste Hilfe / Notruf 144 (Notfall) oder Hausarzt
□ Bei Arbeitsunfall: Arbeitgeber informieren
□ Bei Verkehrsunfall: Polizei 117 (bei Personenschaden Pflicht)
□ Unfallstelle sichern / dokumentieren
□ Fotos: Unfallstelle, Verletzungen, Schaeden
□ Zeugen: Namen und Kontaktdaten notieren
□ Europaeisches Unfallprotokoll ausfuellen (bei Autounfall)

INNERT 24 STUNDEN:
□ Arztbesuch (auch bei vermeintlich leichten Verletzungen!)
□ Arbeitsunfaehigkeits-Zeugnis ausstellen lassen
□ Arbeitgeber: Unfallmeldung (UVG-Formular)

INNERT 5 TAGEN:
□ Versicherungsmeldung: UVG (via Arbeitgeber), ev. KTG
□ Schadenmeldung an Haftpflicht (wenn Drittperson beteiligt)
□ Alle Belege sammeln (Arzt, Apotheke, Transport)

B) Krankheit / Arbeitsunfaehigkeit:

SOFORT:
□ Arztbesuch, Diagnose und Arbeitsunfaehigkeits-Zeugnis
□ Arbeitgeber informieren (sofort, gemaess Arbeitsvertrag)

INNERT 3 TAGEN:
□ AUF-Zeugnis an Arbeitgeber senden
□ KTG-Meldung pruefen (Arbeitgeber meldet, oder selbst bei Einzel-KTG)

BEI LAENGERER DAUER (>30 Tage):
□ Regelmaessige Arztbesuche und AUF-Verlaengerungen
□ Case Management (AG oder Versicherung) kooperieren
□ Bei >6 Monaten: IV-Frueherkennung pruefen
□ Bei >12 Monaten: IV-Anmeldung pruefen

C) Haftpflicht (verursacht):

SOFORT:
□ Entschuldigung (menschlich), KEIN Schuldanerkenntnis!
□ Geschaedigte Person: Kontaktdaten austauschen
□ Schaden dokumentieren (Fotos, Zeugen)
□ NICHTS unterschreiben, KEINE Zahlungen leisten

INNERT 48 STUNDEN:
□ Eigene Haftpflichtversicherung melden
□ Schadenhergang schriftlich festhalten (eigene Erinnerung)
□ Fotos und Zeugenangaben der Versicherung senden

WICHTIG:
□ Versicherung regelt den Fall — nicht selbst verhandeln
□ Versicherung prueft: Besteht Haftpflicht? Hoehe des Schadens?
□ Versicherung wehrt auch unberechtigte Forderungen ab (passiver RS)

D) Haftpflicht (erlitten):

SOFORT:
□ Schaden dokumentieren (Fotos, Videos, Zeugen)
□ Kontaktdaten des Verursachers aufnehmen
□ Polizei bei grossen Schaeden oder Streitigkeiten

INNERT 7 TAGEN:
□ Schaden schriftlich beim Verursacher geltend machen
□ Frist setzen (14-30 Tage)
□ Haftpflichtversicherung des Verursachers erfragen
□ Eigene Rechtsschutzversicherung informieren (falls vorhanden)

NACHWEISE SAMMELN:
□ Kostenvoranschlaege / Rechnungen fuer Reparatur
□ Fotos vorher/nachher (falls vorhanden)
□ Wertbelege (Kaufquittungen, Schaetzungen)
□ Aerztliche Zeugnisse (bei Personenschaden)

E) Hausrat / Gebaeuedeschaden:

SOFORT:
□ Notdienst bei akuter Gefahr (Feuerwehr 118, Wasserschaden stoppen)
□ Schaden begrenzen (Schadenminderungspflicht!)
□ NICHTS wegraumen oder reparieren vor Dokumentation
□ Fotos und Videos von ALLEM (uebersicht + Details)
□ Bei Einbruch/Diebstahl: Polizei 117 (Pflicht fuer Versicherung!)

INNERT 24-48 STUNDEN:
□ Versicherung melden (Hausrat und/oder Gebaeudeversicherung)
□ Schadenprotokoll erstellen (was, wann, wie, Wert)
□ Gestohlene/beschaedigte Gegenstaende auflisten

NACHWEISE:
□ Polizeirapport (bei Einbruch/Diebstahl)
□ Kaufbelege / Garantiescheine (falls vorhanden)
□ Fotos der beschaedigten Gegenstaende
□ Kostenvoranschlaege fuer Reparatur/Ersatz

F) Autounfall / Fahrzeugschaden:

SOFORT:
□ Warnblinkanlage, Pannendreieck aufstellen
□ Verletzte versorgen / Notruf 144
□ Polizei 117 bei Personenschaden (Pflicht), Sachschaden (>CHF 2'000 empfohlen)
□ Europaeisches Unfallprotokoll ausfuellen und unterschreiben
□ Kontaktdaten + Versicherung des Gegners aufnehmen
□ Fotos: Unfallstelle, Fahrzeuge, Schaeden, Kennzeichen, Uebersicht
□ Zeugen notieren

INNERT 48 STUNDEN:
□ Eigene Autoversicherung melden
□ Bei Fremdverschulden: Haftpflicht des Gegners kontaktieren
□ Werkstatt-Kostenvoranschlag einholen
□ Mietwagen-Bedarf abklaeren (Nutzungsausfall)

ENTSCHEIDUNG:
□ Eigenverschulden → Kaskoversicherung (falls vorhanden)
□ Fremdverschulden → Haftpflicht des Gegners
□ Parkschaden (unbekannt) → Kasko + Polizeimeldung
□ Wildtier → Teilkasko + Polizei/Wildhut
□ Hagel/Naturereignis → Teilkasko

G) Rechtsstreit:

SOFORT:
□ KEINE Unterschriften, KEINE Anerkennung von Forderungen
□ Fristen in Briefen/Verfuegungen notieren (Einsprachefrist!)
□ Rechtsschutzversicherung anrufen BEVOR eigener Anwalt

INNERT 7 TAGEN:
□ Rechtsschutz-Schadenmeldung
□ Versicherung prueft Deckung und weist Anwalt zu
□ Alle Dokumente chronologisch sammeln

WICHTIG:
□ Rechtsschutzversicherung MUSS vor Anwaltsbeauftragung zustimmen
□ Sonst: Kostenubernahme gefaehrdet
□ Wartefrist bei neuen Policen beachten (90 Tage)

H) Todesfall:

SOFORT (Tag 1-2):
□ Arzt rufen (Todesbescheinigung)
□ Bestattungsunternehmen
□ Zivilstandsamt informieren (Gemeinde)

INNERT 1 WOCHE:
□ Arbeitgeber des Verstorbenen informieren
□ Pensionskasse: Hinterlassenenleistungen anmelden
□ AHV-Zweigstelle: Witwen-/Waisenrente beantragen
□ Lebensversicherungen: Todesfall melden
□ Banken informieren

INNERT 1-3 MONATE:
□ UVG-Hinterlassenenleistung (falls Arbeitsunfall)
□ Saele 3a: Auszahlung an Beguenstigte
□ Erbschein beantragen (beim Bezirksgericht)
□ Steuerverwaltung: Steuererklarung des Verstorbenen

I) Invaliditaet:

FRUEHERKENNUNG (ab 30 Tage Arbeitsunfaehigkeit):
□ Arbeitgeber / IV-Stelle: Frueherfassung melden
□ KTG-Leistungen sicherstellen

IV-ANMELDUNG (ab 6-12 Monate):
□ Anmeldeformular bei kantonaler IV-Stelle
□ Aerztliche Berichte sammeln
□ Arbeitgeber-Bericht
□ Geduld: IV-Verfahren dauert 12-24 Monate

WAEHREND IV-VERFAHREN:
□ KTG laeuft weiter (max. 720 Tage)
□ Eingliederungsmassnahmen der IV mitwirken
□ Regelmaessig Arztbesuche dokumentieren

BEI IV-ENTSCHEID:
□ Verfuegung pruefen (IV-Grad, Rentenhoehe)
□ Bei Ablehnung: Einsprache innert 30 Tagen
□ BVG-Invalidenrente separat bei PK anmelden
□ IV-Zusatzversicherung aktivieren (falls vorhanden)

J) Reise:

ANNULLIERUNG:
□ Reiseveranstalter sofort informieren
□ Arztzeugnis einholen (bei Krankheit als Grund)
□ Reiseversicherung melden mit Belegen

GEPAECKVERLUST:
□ Am Flughafen: PIR-Formular (Property Irregularity Report)
□ Airline-Reklamation innert 21 Tagen (Montrealer Abkommen)
□ Reise-/Hausratversicherung melden

ERKRANKUNG IM AUSLAND:
□ Notfall-Nummer der Krankenversicherung anrufen
□ Arzt aufsuchen, Belege aufbewahren
□ Kostengutsprache bei grosseren Behandlungen
□ Ruecktransport mit Versicherung absprechen

Schritt 3 — Schadenmeldung erstellen

Ziel: Den Nutzer beim Erstellen einer vollstaendigen Schadenmeldung unterstuetzen.

3.1 Universelle Schadenmeldung:

Hilf dem Nutzer, folgende Informationen zusammenzustellen:

SCHADENMELDUNG
==============
Policen-Nr.:        ...
Versicherungsnehmer: ...
Datum/Uhrzeit:       ...
Ort:                 ...

SCHADENHERGANG:
[Chronologische Beschreibung: Was ist passiert, wie ist es passiert,
wer war beteiligt. Sachlich, keine Spekulationen, keine Schuldzuweisung.]

BETEILIGTE PERSONEN:
Name, Adresse, Telefon, Versicherung (falls bekannt)

ZEUGEN:
Name, Adresse, Telefon

SCHADENHOEHE (geschaetzt):
- Sachschaden: CHF ...
- Personenschaden: [Beschreibung]
- Folgekosten: CHF ...

BEILAGEN:
□ Fotos (Anzahl: ...)
□ Polizeirapport (Nr.: ...)
□ Arztzeugnis
□ Kostenvoranschlaege
□ Kaufbelege
□ Europaeisches Unfallprotokoll
□ Weitere: ...

DATUM, UNTERSCHRIFT

3.2 Kommunikationsregeln:

DO:
✓ Sachlich und chronologisch beschreiben
✓ Nur Fakten, keine Vermutungen
✓ Vollstaendig — nichts weglassen
✓ Fristen einhalten
✓ Alles schriftlich (E-Mail oder Brief)
✓ Kopien aller Korrespondenz behalten

DON'T:
✗ Schuldanerkenntnis abgeben
✗ Voreilig Zahlungen leisten
✗ Schadenhoehe aufblaehen (Versicherungsbetrug!)
✗ Schaden verharmlosen
✗ Muendliche Abmachungen ohne schriftliche Bestaetigung
✗ Anwalt beauftragen ohne Rechtsschutz zu informieren

Schritt 4 — Regulierungsprozess begleiten

Ziel: Den Nutzer durch den Regulierungsprozess begleiten und bei Problemen helfen.

4.1 Typischer Ablauf:

ZEITLEISTE SCHADENREGULIERUNG
==============================
Tag 0:    Schadenfall tritt ein
Tag 0-2:  Sofortmassnahmen + Dokumentation
Tag 1-5:  Schadenmeldung an Versicherung
Tag 5-10: Eingangsbestaetigung der Versicherung
Tag 10-30: Schadenprüfung durch Versicherung
           (Ev. Besichtigung durch Experten/Schadensinspektor)
Tag 30-90: Leistungsentscheid
           → Leistung oder (Teil-)Ablehnung

BEI ABLEHNUNG:
Tag 0-30:  Einsprache/Widerspruch (Frist beachten!)
Tag 30-90: Pruefung der Einsprache
           → Ev. Ombudsman einschalten
           → Ev. Rechtsschutz aktivieren (Klage)

4.2 Entscheidungsbaum bei Problemen:

VERSICHERUNG REAGIERT NICHT?
├── Eingangsbestaetigung fehlt (>10 Tage)
│   → Nachfassen per E-Mail + Frist setzen (14 Tage)
├── Keine Antwort auf Nachfrage
│   → Einschreiben mit Frist (14 Tage)
└── Weiterhin keine Antwort
    → Ombudsman oder FINMA-Beschwerde

LEISTUNG ABGELEHNT?
├── Begruendung nachvollziehbar?
│   ├── Ja → Akzeptieren (oder Deckung war tatsaechlich nicht gegeben)
│   └── Nein → Einsprache (schriftlich, mit Begruendung)
├── Leistung zu tief?
│   → Eigene Schaetzung/Gutachten einholen
│   → Differenz begruenden und nachfordern
└── Teilablehnung?
    → Akzeptierten Teil auszahlen lassen
    → Abgelehnten Teil separat anfechten

EINSPRACHE ABGELEHNT?
├── Ombudsman der Privatversicherung einschalten (kostenlos)
├── Rechtsschutzversicherung aktivieren
└── Klage (letztes Mittel)
    → Friedensrichter (bis CHF 2'000 obligatorisch)
    → Bezirksgericht (ab CHF 2'000)
    → Schlichtungsverfahren (Arbeits-/Mietrecht)

VERDACHT AUF UNFAIRE BEHANDLUNG?
├── Allgemeine Versicherungsbedingungen (AVB) selbst lesen
├── Ombudsman konsultieren (neutral, kostenlos)
├── FINMA-Beschwerde (bei systematischem Fehlverhalten)
└── Medien (Kassensturz, Espresso) als letztes Mittel

4.3 Fristen-Uebersicht:

Erstelle fuer den konkreten Fall eine Fristen-Checkliste:

Frist	Beschreibung	Datum	Status
Schadenmeldung	Innert X Tagen nach Ereignis	...	□
Einsprache bei Ablehnung	30 Tage nach Verfuegung (VVG)	...	□
Einsprache IV/UVG	30 Tage nach Verfuegung	...	□
Verjaehrung Forderung	2 Jahre (VVG) / 5 Jahre (OR)	...	□
...	...	...	□

Schritt 5 — Schadenfall-Dossier Ausgabe

Erstelle ein Schadenfall-Dossier als Markdown:

# Schadenfall-Dossier — {Kurzbeschreibung}
*Erstellt am {Datum}*

## Disclaimer
Dieses Dossier ersetzt keine Rechtsberatung. Bei strittigen Faellen,
Personenschaeden oder hohen Streitwerten einen Anwalt oder den
Ombudsman der Privatversicherung einschalten.

## 1. Schadenfall

| Merkmal | Details |
|---------|---------|
| Kategorie | {A-K} |
| Datum/Uhrzeit | ... |
| Ort | ... |
| Beschreibung | ... |
| Beteiligte | ... |
| Zeugen | ... |
| Geschaetzte Schadenhoehe | CHF ... |

## 2. Sofortmassnahmen

| # | Massnahme | Status | Erledigt am |
|---|-----------|--------|------------|
| 1 | ... | □ Offen / ✓ Erledigt | ... |

## 3. Betroffene Versicherungen

| Versicherung | Anbieter | Policen-Nr. | Meldung am | Status |
|-------------|----------|------------|-----------|--------|
| ... | ... | ... | ... | ... |

## 4. Nachweise

| # | Nachweis | Vorhanden | Bemerkung |
|---|---------|-----------|----------|
| 1 | Fotos | □ | ... |
| 2 | Polizeirapport | □ | ... |
| 3 | Arztzeugnis | □ | ... |
| 4 | Kostenvoranschlag | □ | ... |
| 5 | Kaufbelege | □ | ... |

## 5. Schadenmeldung (Entwurf)

{Vorbereitete Schadenmeldung}

## 6. Fristen

| Frist | Beschreibung | Datum | Status |
|-------|-------------|-------|--------|
| ... | ... | ... | □ |

## 7. Regulierungs-Tracker

| Datum | Aktion | Von | Status |
|-------|--------|-----|--------|
| ... | Schadenmeldung gesendet | Ich | ✓ |
| ... | Eingangsbestaetigung | Versicherung | □ |
| ... | Leistungsentscheid | Versicherung | □ |

## 8. Naechste Schritte

1. {Naechste konkrete Aktion}
2. {Weitere Aktion}
3. {Frist beachten: ...}

Speichere als schadenfall-{kategorie}-{datum}.md.

Optional JSON-Export fuer maschinelle Weiterverarbeitung:

{
  "meta": {
    "erstellt": "YYYY-MM-DD",
    "version": "1.0",
    "typ": "claims-guide"
  },
  "schadenfall": {
    "kategorie": "A-K",
    "datum": "YYYY-MM-DD",
    "ort": "...",
    "beschreibung": "...",
    "schadenhoehe_geschaetzt": 0
  },
  "sofortmassnahmen": [
    {"massnahme": "...", "status": "offen|erledigt", "datum": null}
  ],
  "versicherungen": [
    {"art": "...", "anbieter": "...", "policen_nr": "...", "meldung_datum": null, "status": "offen|gemeldet|in_pruefung|entschieden"}
  ],
  "nachweise": [
    {"art": "fotos", "vorhanden": false, "bemerkung": "..."}
  ],
  "fristen": [
    {"beschreibung": "...", "datum": "YYYY-MM-DD", "status": "offen|erledigt"}
  ],
  "regulierung": [
    {"datum": "YYYY-MM-DD", "aktion": "...", "von": "ich|versicherung", "status": "offen|erledigt"}
  ]
}

Wichtige Hinweise

Keine Rechtsberatung: Dieser Skill ersetzt keinen Anwalt. Bei strittigen Faellen, Personenschaeden oder hohen Summen: Professionelle Hilfe holen.
Schadenminderungspflicht: Der Versicherungsnehmer MUSS den Schaden begrenzen (VVG Art. 61). Wer nichts unternimmt, riskiert Leistungskuerzung.
Kein Schuldanerkenntnis: Nie gegenueber Dritten die Schuld anerkennen — das ist Sache der Versicherung.
Dokumentation ist alles: Fotos, Zeugen, Belege — je mehr, desto besser. Lieber zu viel als zu wenig dokumentieren.
Fristen sind heilig: Versaeumte Fristen koennen zum Leistungsverlust fuehren. Im Zweifel sofort handeln.
Ombudsman ist kostenlos: Der Ombudsman der Privatversicherung (ombudsman-assurance.ch) vermittelt kostenlos und neutral.
Iterativ: Der Nutzer kann den Guide jederzeit fuer einen neuen Schadenfall starten.
Laenderanpassung: Bei Nutzern ausserhalb der Schweiz: Rechtliche Grundlagen und Fristen anpassen.
Datenschutz: Alle Daten bleiben lokal. Es werden keine Daten an externe Dienste gesendet.
Proaktiv: Weise den Nutzer auf leicht vergessene Schritte hin (z.B. UVG-Meldung bei Arbeitsunfall, Polizeimeldung bei Diebstahl, Frist fuer Einsprache).

About this skill

Automatic

Insurance Claims pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/7/2026

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

thomasmoreai / legal-skills-open

ch/insurance/skills/claims-guide/SKILL.md

View on GitHub ↗

License MITImported 10/7/2026Version v1Bundled 1 file

Illustrative Want to see what thomasmoreai/claims-guide 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.

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

Schadenfall-Guide & Entscheidungslogik

Overview

Workflow

Schritt 1 — Schadenfall identifizieren

Schritt 2 — Sofortmassnahmen-Checkliste

Schritt 3 — Schadenmeldung erstellen

Schritt 4 — Regulierungsprozess begleiten

Schritt 5 — Schadenfall-Dossier Ausgabe

Wichtige Hinweise

SkillSafety

Source

Related skills

More in the registry