Ready to supercharge your AI agents?

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

Skill: RIS Rechtsprechung (Österreich) · thomasmoreai | DecimalAI

Legalby thomasmoreai

Skill: RIS Rechtsprechung (Österreich)

Österreichische Rechtsprechung über die offene RIS-API (data.bka.gv.at v2.6) thematisch durchsuchen — OGH, OLG, LG, BG, VfGH, VwGH, BVwG, LVwG, DSB, GBK u. a. Liefert pro Treffer Metadaten (Geschäftszahl, Entscheidungsdatum, Leitsatz) und einen Direkt-Link in das RIS. TRIGGER bei thematischen Fragen wie "Gibt es OGH-Judikatur zu Mietzinsminderung in der Pandemie?", "Aktuelle BVwG-Entscheidungen zu Afghanistan-Asyl", "Was sagt der VfGH zur Versammlungsfreiheit seit 2020?". NICHT TRIGGERN für gezi

SkillScore

SkillScore65/100

Test results 65

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

22%65%of test cases passed +43 pts

Without skill5 of 23

With skill15 of 23

10 fixed5 passed either way8 still failing0 broke

Measured on gemini-3.6-flash8/5/2026v118 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskIch möchte mit Platzhaltern nach Wörtern wie 'Miet*' suchen. Welche Einschränkung gilt laut API-Spezifikation für Wildcards in Suchbegriffen?

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-ris-rechtsprechung
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-ris-rechtsprechung")
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-ris-rechtsprechung

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-ris-rechtsprechung/SKILL.md https://app.decimal.ai/s/thomasmoreai-ris-rechtsprechung/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/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-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/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-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung")
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-ris-rechtsprechung/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung

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-ris-rechtsprechung/SKILL.md https://app.decimal.ai/s/thomasmoreai-ris-rechtsprechung/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/thomasmoreai-ris-rechtsprechung/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-ris-rechtsprechung/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/thomasmoreai-ris-rechtsprechung.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

Skill: RIS Rechtsprechung (Österreich)

Du recherchierst österreichische Gerichtsentscheidungen über die offene RIS-API v2.6 (Rechtsinformationssystem des Bundes, betrieben vom Bundeskanzleramt). Die API ist authentifizierungsfrei und liefert JSON.

Scope dieses Skills: nur Rechtsprechung (Judikatur), nur Metadaten + Link. Es wird kein Volltext heruntergeladen oder konvertiert. Bundes- und Landesrecht sind nicht enthalten.

Wann diesen Skill anwenden

Hauptpfad — thematische / explorative Recherche im Chat:

nach Stichworten / Schlagworten (--suchworte, --schlagworte)
in einem bestimmten Zeitraum (--von / --bis)
bei einer bestimmten Gerichtsbarkeit (--applikation)

Beispiele, die diesen Skill triggern:

„Gibt es OGH-Judikatur zu Mietzinsminderung in der Pandemie?"
„Aktuelle BVwG-Entscheidungen zu Afghanistan-Asyl seit 2023"
„Was sagt der VfGH zur Versammlungsfreiheit?"

Sekundärpfade (technisch unterstützt, aber meist im RIS-Web-Frontend schneller — nur nutzen, wenn der User explizit darum bittet oder die Suche aus dem Chat-Kontext heraus eindeutig per Skript schneller geht):

Geschäftszahl-Lookup (--geschaeftszahl)
Norm-Suche (--norm "ABGB §1319a")
Rechtssatznummer-Lookup (--rechtssatznummer RS0123456)

Norm-Suche → Rechtssätze: bei reiner --norm-Suche (ohne --suchworte) liefert die OGD-API per Default überwiegend Rechtssätze, kaum Volltext-Entscheidungen — Rechtssätze sind im Norm-Index hinterlegt, Entscheidungstexte erst über die zusätzlichen Flags SucheNachRechtssatz / SucheNachText. Das Skript sendet diese Flags bewusst nur bei --suchworte-Suchen, weil bei reiner Norm-Recherche Rechtssätze i. d. R. die gewollte Trefferart sind.

Nicht anwenden, wenn:

die Frage rein dogmatisch / rechtspolitisch ist, ohne Bezug zu einer konkreten Entscheidung (z. B. „Was sagt die Lehre zu §..." → Kommentar, nicht RIS),
Bundes-/Landesrecht gemeint ist (Gesetzestext, nicht Rechtsprechung),
nach EuGH/EGMR-Urteilen gefragt wird (RIS enthält nur österreichische Gerichte; ggf. wird die österreichische Folgejudikatur gesucht — dann Skill anwenden, aber den Hinweis geben),
nach laufenden Verfahren oder Pressemitteilungen gefragt wird (RIS enthält nur veröffentlichte Entscheidungen).

API-Grundlagen

Base-URL: https://data.bka.gv.at/ris/api/v2.6/
Endpoint Rechtsprechung: GET /Judikatur
Response-Format: JSON (Accept: application/json)
Keine Auth, keine Quotas, aber:
- Bei Pagination 1–2 s Pause zwischen Seiten einlegen.
- Massenabfragen außerhalb 06–18 Uhr (MEZ) oder am Wochenende.
- Bei Fehlern Geduld haben — das System teilt sich Ressourcen mit dem Web-Frontend.

Pflichtparameter

Applikation (genau einer):

Wert	Gericht/Behörde
`Justiz`	OGH, OLG, LG, BG (Zivil-/Strafgerichtsbarkeit) — Standard
`Vfgh`	Verfassungsgerichtshof
`Vwgh`	Verwaltungsgerichtshof
`Bvwg`	Bundesverwaltungsgericht
`Lvwg`	Landesverwaltungsgerichte
`Dsk`	Datenschutzbehörde (vormals -kommission)
`AsylGH`	Asylgerichtshof (historisch, bis 2013)
`Normenliste`	Normprüfungs-/Normenliste
`Pvak`	Personalvertretungs-Aufsichtskommission
`Gbk`	Gleichbehandlungskommission
`Dok`	Disziplinarkommission

Plus mindestens einer dieser Suchparameter (sonst HTTP 400):

Parameter	Beispiel	Hinweis
`Suchworte`	`Mietzinsminderung`	URL-encoden; `` nur am Wortende; AND/OR/NOT. OGD-API-Einschränkung: nur ein* Platzhalter pro Wort (Web-Frontend toleriert mehrere).
`Geschaeftszahl`	`5Ob234/20b`	exakte Aktenzeichen-Suche
`Norm`	`ABGB §1319a`	Format: `{Gesetzeskürzel} §{Paragraph}` (kanonische Zitierform) — andere Reihenfolgen wie `1319a ABGB` liefern fast keine Treffer. Fehlt nur das `§`-Zeichen (`ArbVG 105`), ergänzt das Skript es automatisch und schreibt einen Hinweis in den Output. Für EU-Verordnungen (z. B. DSGVO) ist der `Norm`-Index unzuverlässig; lieber Volltextsuche via `Suchworte`.
`Rechtssatznummer`	`RS0123456`	bei OGH-Rechtssatz-Suche
`Schlagworte`	`Datenschutz`	kontrolliertes RIS-Vokabular
`EntscheidungsdatumVon` / `Bis`	`2024-01-01`	ISO-Datum

Optional:

SucheNachRechtssatz, SucheNachText — steuern, in welchen Feldern das Suchworte-Token gesucht wird (Rechtssatz-Text vs. Entscheidungstext). Nicht ein Filter für Trefferarten — auch mit --no-rechtssatz können Rechtssatz-Dokumente zurückkommen, wenn der Suchbegriff im Volltext gefunden wurde. Das Skript sendet die Flags nur bei --suchworte-Suchen.
ImRisSeit ∈ {Undefined, EinerWoche, EinemMonat, DreiMonaten, SechsMonaten, EinemJahr}
Sortierung ∈ {Datum, Geschaeftszahl, Relevanz} — die API toleriert weitere Werte; nur die hier gelisteten sind in den RIS-Handbüchern dokumentiert. Skript-Default: setzt das Skript weder --sortierung noch --sort-direction, sortiert es nach Datum/Descending (im Chat-Kontext meist gewollt — „aktuelle Judikatur zu …"). Der API-Default Relevanz ist mit --sortierung Relevanz zurückzuholen.
SortDirection ∈ {Ascending, Descending}

Pagination:

DokumenteProSeite ∈ {Ten, Twenty, Fifty, OneHundred} — Default Twenty
Seitennummer (1-basiert) — bei --alle-seiten der Einstiegspunkt
Auto-Pagination: --alle-seiten holt mehrere Seiten automatisch, bis Treffer erschöpft oder --max-seiten N (Default 5) erreicht. RIS-konforme Pause zwischen Seiten konfigurierbar via --pause-pagination (Default 1.5 s). Default-Cap: 5 × 20 = 100 Treffer. Für breite Themen-Recherchen mit --pro-seite Fifty --alle-seiten --max-seiten 5 bis zu 250 Treffer auf einmal.

Empfohlenes Vorgehen

Verwende immer das beigelegte Skript scripts/ris_search.py (Python 3, nur Standardbibliothek). Es kapselt URL-Bau, Pflichtparameter-Validierung, JSON-Parsing und Rendering in einem Aufruf.

Mapping: User-Frage → --applikation + Suchparameter. Bei Unsicherheit --applikation Justiz + Volltext-Suche.
Aufruf — das Skript liegt immer bei scripts/ris_search.py relativ zum Skill-Ordner (dem Verzeichnis, das diese SKILL.md enthält). Der absolute Pfad zum Skill-Ordner hängt von der Umgebung ab; Du als ausführendes Modell weißt, in welcher Umgebung Du läufst.

Generisches Aufrufmuster — cd in den Skill-Ordner, dann relativ aufrufen. Standard-Chat-Recherche (Themensuche mit Auto-Pagination):
```
cd <skill-folder> && python scripts/ris_search.py \
  --applikation Justiz \
  --suchworte "Mietzinsminderung" \
  --von 2020-01-01 --bis 2024-12-31 \
  --pro-seite Fifty --alle-seiten --max-seiten 3
```
Liefert bis zu 150 Treffer, sortiert nach Datum absteigend (Default).

Python-Aufruf je Umgebung — probiere in dieser Reihenfolge: python → python3 → py -3. Üblicherweise:
- Linux / macOS / Claude.ai-Sandbox: python3 oder python
- Windows (Claude Code): py -3 (python3 fehlt meist im PATH)
Skill-Ordner je Umgebung — typische Pfade:
- Claude Code (Linux/macOS): ~/.claude/skills/ris-rechtsprechung/
- Claude Code (Windows): %USERPROFILE%\.claude\skills\ris-rechtsprechung\
- Claude.ai Custom Skills: vom Harness gemounteter Pfad (meist unter /mnt/skills/... oder /home/.../skills/...); folge der Pfadangabe, die Dir der Skill-Loader liefert.
Falls cd in der Umgebung nicht zur Verfügung steht (manche Sandboxes), verwende den absoluten Pfad zum Skript, z. B.:
```
python "<skill-folder>/scripts/ris_search.py" --applikation Justiz ...
```
Ausgabe ist Markdown (Default) oder strukturiertes JSON (--json).
Antwort an den User: die Top-Treffer mit Geschäftszahl, Datum, Leitsatz (sofern vorhanden) und RIS-Link weitergeben. Bei mehr als 10 Treffern die ersten 10 ausführlich, den Rest als Bullet-Liste.
Pagination: bei mehr als einer Seite vor jeder weiteren Anfrage ca. 1,5 s warten (RIS-Empfehlung).

Skript-Output

Default (Markdown). Für Rechtssatz-Dokumente (häufigster Fall bei Norm-Suchen — Rechtssätze sind im Norm-Index hinterlegt):

**Treffer:** 7 (Seite 1, 10 pro Seite)

### 1. OGH 2 Ob 554/86 vom 28.10.1986 [Rechtssatz RS0051942]
**Norm:** ArbVG §105 Abs3 Z2 litb
- [Rechtssatz im RIS](https://www.ris.bka.gv.at/Dokument.wxe?Abfrage=Justiz&Dokumentnummer=JJR_19861028_OGH0002_0020OB00554_8600000_007)
- [Volltext der Stammentscheidung](https://www.ris.bka.gv.at/Dokument.wxe?Abfrage=Justiz&Dokumentnummer=JJT_19861028_OGH0002_0020OB00554_8600000_000)
_Auch zitiert in 21 weiteren Entscheidungen._

Für Volltext-Dokumente:

### 2. OGH 5 Ob 234/20b vom 15.04.2021 [Volltext]
_Leitsatz:_ ...
**Norm:** ABGB §1119
- [Zur Entscheidung im RIS](https://ris.bka.gv.at/Dokumente/Justiz/JJT_20210415_OGH0002_.../JJT_....html)

Anmerkungen

Heading aus Stamm-Entscheidung: Bei Rechtssätzen liefert die API in Geschaeftszahl eine Verkettung aller zitierenden Geschäftszahlen und in Entscheidungsdatum das jüngste Update-Datum. Beides ist irreführend. Wir nutzen stattdessen Justiz.Entscheidungstexte.item[0] — die Stamm-Entscheidung — als Quelle für Heading-GZ + Datum.
Volltext-URL bei Rechtssätzen: kommt direkt aus der API (Stamm- DokumentUrl), nicht mehr aus der Heuristik. Die Heuristik bleibt als Fallback für seltene Sonderfälle.
Gericht aus Technisch.Organ (zuverlässiger als Justiz.Gericht). Fallback auf Applikation.
Rechtssatznummer im Doktyp-Label: [Rechtssatz RS0051942] — praktisch zum Zitieren.
„Auch zitiert in N weiteren Entscheidungen": Anzahl − 1 (die Stamm zählt nicht), nur ausgegeben wenn N > 1.
Datumsformat: ISO-Datum → DD.MM.YYYY.

JSON-Output

--json liefert ein normalisiertes Objekt mit allen Feldern:

{
  "total_hits": 7, "page": 1, "page_size": 10,
  "documents": [
    {
      "dokumentnummer": "JJR_19861028_OGH0002_0020OB00554_8600000_007",
      "applikation": "Justiz",
      "gericht": "OGH",
      "doc_type": "Rechtssatz",          // "Volltext" | "Rechtssatz" | null
      "rechtssatznummer": "RS0051942",   // null bei Volltext-Dokumenten
      "geschaeftszahl": "2 Ob 554/86",   // Stamm-GZ aus Entscheidungstexte[0]
      "geschaeftszahlen": [...],         // ALLE zitierenden GZ
      "entscheidungsdatum": "1986-10-28", // Stamm-Datum
      "leitsatz": null,                  // Bei Rechtssätzen meist null
      "normen": ["ArbVG §105 Abs3 Z2 litb"],
      "fachgebiete": [],
      "entscheidungstexte_count": 22,
      "link": "https://www.ris.bka.gv.at/Dokument.wxe?...JJR_..._007",
      "volltext_url": "https://www.ris.bka.gv.at/Dokument.wxe?...JJT_..._000",
      "content_urls": { "html": "...", "pdf": "...", "xml": "...", "rtf": "..." }
    }
  ]
}

doc_type und rechtssatznummer sind nur bei OGH/VfGH/VwGH-Dokumenten zuverlässig gesetzt (J{Court}{T|R}-Konvention). Andere Applikationen (BVWG, LVWG, DSB u. a.) folgen der Konvention nicht; dort bleibt doc_type = null.

--raw gibt die unveränderte API-Antwort aus, falls du selbst parsen willst.

Direkte HTML-Volltext-URLs

Aus der Dokumentennummer ableitbar (Präfix → Pfad):

Präfix	Pfad
`JJT`, `JJR`	`https://ris.bka.gv.at/Dokumente/Justiz/{nr}/{nr}.html`
`JFT`, `JFR`	`https://ris.bka.gv.at/Dokumente/Vfgh/{nr}/{nr}.html`
`JWT`, `JWR`	`https://ris.bka.gv.at/Dokumente/Vwgh/{nr}/{nr}.html`
`BVWG`	`https://ris.bka.gv.at/Dokumente/Bvwg/{nr}/{nr}.html`
`LVWG`	`https://ris.bka.gv.at/Dokumente/Lvwg/{nr}/{nr}.html`
`DSB`	`https://ris.bka.gv.at/Dokumente/Dsk/{nr}/{nr}.html`
`GBK`	`https://ris.bka.gv.at/Dokumente/Gbk/{nr}/{nr}.html`
`PVAK`	`https://ris.bka.gv.at/Dokumente/Pvak/{nr}/{nr}.html`

Validierung: Dokumentennummern matchen ^[A-Z][A-Z0-9_]+$, Länge 5–50. Das Skript leitet diesen Link automatisch ab und stellt ihn unter link bzw. content_urls.html bereit.

Volltext-Download ist explizit nicht Teil dieses Skills. Wenn der User den Volltext einer Entscheidung will, gib ihm den Link aus dem Trefferdatensatz und überlasse ihm das Lesen.

Web-Search-Fallback (bei 0 API-Treffern)

Bei Suchworte-Anfragen mit 0 Treffern erzeugt das Skript automatisch eine Google site:-Such-Query nach dem Muster

site:ris.bka.gv.at <Applikation> <Suchworte> [<Norm>] ["<Geschaeftszahl>"] [after:<Jahr>] [before:<Jahr>]

und gibt sie zusammen mit dem Hinweis aus. Hintergrund: Google indexiert das RIS-Web-Frontend deutlich breiter als der OGD-API-Volltext-Index — insbesondere bei alten Entscheidungen (vor ca. 1990), wo der API-Volltext oft amputiert oder gar nicht durchsuchbar ist.

Wenn Du in einem Claude-Kontext mit web_search-Tool läufst: sobald Du die Query im Output siehst, übergib sie unverändert an das web_search-Tool. Aus den Treffern extrahierst Du RIS-URLs der Form https://www.ris.bka.gv.at/Dokument.wxe?Abfrage=…&Dokumentnummer=… und holst Dir bei Bedarf den Volltext mit web_fetch. Daraus baust Du dann dieselben Trefferzeilen wie aus der API-Antwort (Geschäftszahl, Datum, Leitsatz/Rechtssatz, Link).

Das Skript selbst führt keine Web-Suche aus — die Logik bleibt bei Claude. Im JSON-Output ist die Query als websearch_query-Feld verfügbar; im Markdown-Output steht sie im Hinweis-Block am Ende der Trefferliste.

Fehlerfälle

HTTP 400 → mindestens einen Suchparameter ergänzen oder spezifischer machen.
0 Treffer → Suche entschärfen (allgemeinere Suchworte, größerer Zeitraum, andere Applikation).
0 Treffer bei Suchworte trotz nachweisbarem Vorkommen → Bekannte Limitation des OGD-Volltext-Index, insbesondere bei alten Entscheidungen (vor ca. 1990). Der Volltext kann existieren und das Suchwort enthalten, ohne dass der API-Index ihn findet. Das Skript generiert in diesem Fall automatisch eine Google site:-Such-Query als Fallback (siehe Abschnitt Web-Search-Fallback).
Timeout → einmal mit kleinerem --pro-seite wiederholen (das Skript retried automatisch zwei Mal mit 2/4 s Pause).
API-Pflichtparameter unbekannt → Default-Pfad: --applikation Justiz, --suchworte ... setzen.

Installation

Im Repo liegt der Skill unter recherche-ris-rechtsprechung/skill-draft/ris-rechtsprechung/ und ist self-contained: ein Ordner mit SKILL.md und scripts/ris_search.py. Da das Skript ausschließlich die Python-Standardbibliothek nutzt, ist keine Build-Phase und keine Pip-Installation nötig.

Claude Code (lokal, Linux/macOS)

mkdir -p ~/.claude/skills
cp -r recherche-ris-rechtsprechung/skill-draft/ris-rechtsprechung \
      ~/.claude/skills/

Claude Code (lokal, Windows — PowerShell)

$dest = "$env:USERPROFILE\.claude\skills"
New-Item -ItemType Directory -Force -Path $dest | Out-Null
Copy-Item -Recurse -Force `
  "recherche-ris-rechtsprechung\skill-draft\ris-rechtsprechung" `
  $dest

Claude.ai Custom Skills (Web-App)

Skill-Ordner als ZIP packen:

cd recherche-ris-rechtsprechung/skill-draft/
zip -r ris-rechtsprechung.zip ris-rechtsprechung/

PowerShell:

Compress-Archive -Path "recherche-ris-rechtsprechung\skill-draft\ris-rechtsprechung" `
                 -DestinationPath ris-rechtsprechung.zip -Force

Claude.ai → Settings → Capabilities → Skills → Upload skill → ZIP-Datei auswählen.
Wichtig: Im selben Settings-Bereich unter Web search & code execution → Network access die folgenden Hosts freigeben. Falls Claude.ai Wildcards akzeptiert, deckt *.bka.gv.at alle drei mit einem Eintrag ab.
- data.bka.gv.at — OGD-API (Pflicht; ohne das blockt die Sandbox alle Skript-Aufrufe).
- ris.bka.gv.at — RIS-Direkt-HTML-URLs der Form /Dokumente/Justiz/JJT_…/JJT_….html (abgeleitete „Volltext (vermutet)"-Links bei Rechtssatz-Treffern; Hinweis-Link auf die RIS-Web-Suche https://www.ris.bka.gv.at/Judikatur/ bei 0 Volltext-Treffern).
- www.ris.bka.gv.at — Dokument.wxe?…-URLs, die die API selbst in der Trefferliste zurückgibt.

Endstruktur (überall identisch)

ris-rechtsprechung/
├── SKILL.md
└── scripts/ris_search.py

Voraussetzung: Python ≥ 3.9 in der ausführenden Umgebung. Keine Pip-Pakete nötig.

Lizenz, Namensnennung, Disclaimer

Die über die OGD-Schnittstelle bezogenen RIS-Daten stehen unter Creative Commons Namensnennung 4.0 International (CC BY 4.0). Bei Wiedergabe ist die Quelle zu nennen — das Skript hängt deshalb an jeden Markdown-Output automatisch eine Attribution-Zeile (Quelle: RIS, Bundeskanzleramt — CC BY 4.0) und im JSON-Output ein attribution-Feld.

Rechtlich verbindlich ist laut Bundeskanzleramt ausschließlich der Wortlaut im Bundesgesetzblatt (Applikation „Bundesgesetzblatt authentisch") bzw. in den jeweiligen Landesgesetzblättern. Der OGD-Datenbestand wird ohne Gewähr für Richtigkeit, Aktualität oder Vollständigkeit bereitgestellt. Wenn Du RIS-Treffer im Chat ausgibst, formuliere entsprechend — die zurückgelieferten Texte sind Recherchehilfe, keine authentische Rechtsquelle.

Massenabfragen: ein durchschnittlicher Skill-Aufruf (bis 5 Seiten × 100 Treffer) ist unbedenklich. Wer den Skill systematisch über den Tag verteilt nutzt oder --max-seiten deutlich hochdreht, sollte das RIS-Team unter [email protected] vorab informieren (siehe OGD-FAQ), um nicht versehentlich als DDoS-Verkehr klassifiziert zu werden.

Quellen

Offizielle Doku-PDF: https://data.bka.gv.at/ris/ogd/v2.6/Documents/Dokumentation_OGD-RIS_API.pdf
OGD-FAQ: https://www.ris.bka.gv.at/RisInfo/OGD-FAQ.pdf
Datensatz-Eintrag: https://www.data.gv.at/katalog/dataset/ris2_6
Referenz-Implementierungen:
- shrinkwrap-legal/shrinkwrap-legal-api (Java/Spring)
- philrox/ris-mcp-ts (TypeScript MCP-Server)
Kontakt für API-Fragen: [email protected]

About this skill

Automatic

Legal & Contracts pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/8/2026

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

at/litigation/skills/ris-rechtsprechung/SKILL.md

View on GitHub ↗

License MITImported 10/8/2026Version v1Bundled 1 file · scripts

Illustrative Want to see what thomasmoreai/ris-rechtsprechung 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.

lawve-ai/giurisprudenza-lampoRicerca giurisprudenziale rapida per ottenere un quadro di orientamento iniziale su un tema giuridico. Si attiva con "giurisprudenza-lampo [tema]", "cerca giurisprudenza su [tema]", "sentenze su [tema]", "pronunce su [tema]", "orientamento giurisprudenziale su [tema]", o qualsiasi variante che chieda di cercare sentenze, pronunce, massime, orientamenti giurisprudenziali o precedenti su un argomento giuridico. Usa questa skill anche quando l'utente dice "cosa dice la giurisprudenza su", "ci sono 0 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

Skill: RIS Rechtsprechung (Österreich)

Wann diesen Skill anwenden

API-Grundlagen

Pflichtparameter

Empfohlenes Vorgehen

Skript-Output

Anmerkungen

JSON-Output

Direkte HTML-Volltext-URLs

Web-Search-Fallback (bei 0 API-Treffern)

Fehlerfälle

Installation

Claude Code (lokal, Linux/macOS)

Claude Code (lokal, Windows — PowerShell)

Claude.ai Custom Skills (Web-App)

Endstruktur (überall identisch)

Lizenz, Namensnennung, Disclaimer

Quellen

SkillSafety

Source

Related skills

More in the registry