Ready to supercharge your AI agents?

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

NextCloud AIO OpenClaw Skill · leoyeai | DecimalAI

Productivityby leoyeai

NextCloud AIO OpenClaw Skill

Reliable Nextcloud integration for Notes, Tasks, Calendar, Files, and Contacts (CardDAV-safe vCard handling with robust contact create/update).

SkillScore

SkillScore57/100

Test results 57

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

13%57%of test cases passed +43 pts

Without skill3 of 23

With skill13 of 23

10 fixed3 passed either way10 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v114 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskFind all task-capable calendars available on my Nextcloud account.

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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw
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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md https://app.decimal.ai/s/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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("leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw")
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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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 leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw

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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md https://app.decimal.ai/s/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/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/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-nextcloud-aio-oc-nextcloud-aio-openclaw.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 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Use this skill

SKILL.md

NextCloud AIO OpenClaw Skill

This skill connects OpenClaw to Nextcloud for:

Notes API
CalDAV Tasks and Events
WebDAV Files
CardDAV Contacts

Primary goal: Predictable, loss-resistant Nextcloud reads/writes.

This skill is validated against:

Nextcloud Hub 25 Autumn (32.0.6)
OpenClaw (2026.3.2)

Required Configuration

Set these environment variables:

NEXTCLOUD_URL (example: https://cloud.example.com)
NEXTCLOUD_USER
NEXTCLOUD_TOKEN (App Password strongly preferred)
NEXTCLOUD_TIMEZONE (recommended, IANA timezone like America/Los_Angeles; used for timezone-less date/time inputs)

Runtime and Metadata Contract

This section is the source of truth for registry metadata parity.

Required binary: node (Node.js 20+)
Required environment variables: NEXTCLOUD_URL, NEXTCLOUD_USER, NEXTCLOUD_TOKEN
Optional environment variable: NEXTCLOUD_TIMEZONE
Required network target: the host defined by NEXTCLOUD_URL (plus normal redirects from that host)

If a registry entry says "no required binaries" or "no required env vars", treat it as stale metadata and fix before publishing.

Preflight Audit Gate

Before first execution in any new environment:

Complete the bundled script review checklist below.
Confirm no unexpected endpoints or privileged system calls are present.
If checks are incomplete, do not run the skill.
Prefer sandbox/container validation and least-privilege app credentials first.

Security and Publish Safety

Never hardcode credentials in SKILL.md, scripts, examples, commit messages, or changelog text.
Store secrets only in environment variables or local secret stores.
Use dedicated app passwords for integrations; rotate if leaked or shared.
Keep local .env files out of git (see .gitignore).
Before publishing, run a quick scan for obvious secrets and remove any accidental values.

Bundled Script Review Checklist (Before First Use)

The skill ships two scripts: scripts/nextcloud.js (Node.js, text operations) and scripts/files_binary.py (Python 3, binary file transfers). Review both before running in new environments:

Confirm runtime requirements:
- node --version (must be 20+)
Check obvious outbound endpoints:
- rg -n "https?://" scripts/nextcloud.js
Check sensitive capability usage:
- rg -n "child_process|spawn\$|exec\\(|require\\(\"fs\"\$|require\$'fs'\$|fs\\." scripts/nextcloud.js
Verify credentials are env-driven only:
- rg -n "NEXTCLOUD_URL|NEXTCLOUD_USER|NEXTCLOUD_TOKEN|NEXTCLOUD_TIMEZONE" scripts/nextcloud.js
Run in low-risk mode first:
- Use a dedicated low-privilege Nextcloud app password
- Test against non-production data when possible

If review confidence is low, do not run until code is reviewed by a trusted maintainer.

Static audit snapshot (current bundle)

Quick grep-style checks on scripts/nextcloud.js should currently show:

Config is read from process.env.NEXTCLOUD_URL|USER|TOKEN|TIMEZONE.
Request path is built as ${CONFIG.url}${endpoint} and uses fetch(...).
No obvious child_process or fs usage in the bundle entry path.

Quick checks on scripts/files_binary.py:

Config is read from os.environ.get("NEXTCLOUD_URL|USER|TOKEN").
DAV URL is built as {url}/remote.php/dav/files/{user}/{path}.
Uses only stdlib (urllib, base64, xml.etree); no third-party deps.

This is not a full security audit. Re-run checks after every bundle update.

Run

node scripts/nextcloud.js <command> <subcommand> [options]

Commands

Notes

notes list
notes get --id <id>
notes create --title <title> --content <content> [--category <category>]
notes edit --id <id> [--title <title>] [--content <content>] [--category <category>]
notes delete --id <id>

Tasks

tasks list [--calendar <calendar-name>]
tasks create --title <title> [--calendar <calendar-name>] [--due <iso>] [--priority <0-9>] [--description <text>] [--timezone <IANA>]
tasks edit --uid <uid> [--calendar <calendar-name>] [--title <title>] [--due <iso>] [--priority <0-9>] [--description <text>] [--timezone <IANA>]
tasks delete --uid <uid> [--calendar <calendar-name>]
tasks complete --uid <uid> [--calendar <calendar-name>]

Calendar Events

calendar list [--from <iso>] [--to <iso>] (default: next 7 days)
calendar create --summary <summary> --start <iso-or-date> --end <iso-or-date> [--calendar <calendar-name>] [--description <text>] [--timezone <IANA>] [--all-day]
calendar edit --uid <uid> [--calendar <calendar-name>] [--summary <summary>] [--start <iso-or-date>] [--end <iso-or-date>] [--description <text>] [--timezone <IANA>] [--all-day]
calendar delete --uid <uid> [--calendar <calendar-name>]

Important:

In many setups, Contact birthdays appears as an events calendar but is read-only.
Birthdays must be managed through contacts create/edit --birthday ..., not through calendar create/edit.
calendar list returns event summary, start, end, and may include location and description when present.

Calendar Discovery

calendars list [--type <tasks|events>]

Files (text)

files list [--path <path>]
files search --query <query> (supports natural-language input; ranks by filename/path token relevance)
files get --path <path> (accepts relative user path or full DAV href)
files upload --path <path> --content <content>
files delete --path <path>

Files (binary) — ODT, DOCX, PDF, images, etc.

nextcloud.js passes file content as text strings, which corrupts binary formats. Use the companion Python script for any binary file:

python3 scripts/files_binary.py download <nc_path> <local_path>
python3 scripts/files_binary.py upload   <local_path> <nc_path>
python3 scripts/files_binary.py exists   <nc_path>
python3 scripts/files_binary.py list     [<nc_path>]

Reads the same NEXTCLOUD_URL, NEXTCLOUD_USER, NEXTCLOUD_TOKEN env vars. Auto-detects MIME type from file extension (ODT, DOCX, XLSX, PDF, PNG, JPG, and more).

When to use which:

Situation	Command
Plain text files (`.md`, `.txt`, `.csv`)	`node scripts/nextcloud.js files get/upload`
Binary files (`.odt`, `.docx`, `.pdf`, images)	`python3 scripts/files_binary.py download/upload`

Contacts

contacts list [--addressbook <name>]
contacts get --uid <uid> [--addressbook <name>]
contacts search --query <query> [--addressbook <name>]
contacts create [--name <full-name>] [--first-name <given>] [--last-name <family>] [--middle-name <middle>] [--prefix <prefix>] [--suffix <suffix>] [--addressbook <name>] [--email <single>] [--emails <csv>] [--phone <single>] [--phones <csv>] [--organization <org>] [--title <title>] [--note <note>] [--birthday <YYYY-MM-DD|YYYYMMDD|--MM-DD|--MMDD>]
contacts edit --uid <uid> [--addressbook <name>] [--name <full-name>] [--first-name <given>] [--last-name <family>] [--middle-name <middle>] [--prefix <prefix>] [--suffix <suffix>] [--email <single>] [--emails <csv>] [--phone <single>] [--phones <csv>] [--organization <org>] [--title <title>] [--note <note>] [--birthday <YYYY-MM-DD|YYYYMMDD|--MM-DD|--MMDD>]
contacts delete --uid <uid> [--addressbook <name>]

Address Book Discovery

addressbooks list

Contact Data Contract (Important)

Use fullName and structuredName as canonical name fields.

Contact output includes:

uid
addressBook
fullName
structuredName with:
- familyName
- givenName
- additionalNames
- honorificPrefixes
- honorificSuffixes
nameRaw (raw N value for diagnostics only; do not display to users by default)
emails array or null
phones array or null
organization, title, note
birthday normalized for readability (YYYY-MM-DD or --MM-DD when possible)
birthdayRaw (raw CardDAV value)

Reliability Rules (Quick Reference)

Apply these on every write to prevent corruption and confusion:

Identity and naming

Never infer UID from URL; always use payload uid.
Use fullName and structuredName for user-facing names; keep nameRaw diagnostic-only.

Contact and birthday integrity

Birthday input formats: YYYY-MM-DD, YYYYMMDD, --MM-DD, --MMDD.
Never add trailing semicolons to BDAY.
Birthdays are contact fields: use contacts create/edit --birthday ...; never edit birthday-derived calendar entries directly.

Intent-preserving updates

Modify only fields explicitly requested by the user.
To clear a value, pass explicit empty values.
Respect explicit --addressbook; otherwise use remembered default or ask once.

Calendar and task validation

Validate date/datetime inputs before sending; require end > start for timed events.
Escape ICS text fields (SUMMARY, DESCRIPTION).
Validate task priority range (0..9).
For timezone-less timed input, use --timezone or NEXTCLOUD_TIMEZONE.
For all-day events, use VALUE=DATE semantics with exclusive DTEND.

Capability and safety checks

Do not assume listed event calendars are writable.
Treat Contact birthdays as read-only/system calendar.
If no writable event calendar exists, explain event mutation is unavailable until writable access exists.
Some calendars are multi-component (VEVENT + VTODO); keep them eligible for both event/task flows.

Files and post-write verification

Require non-empty file paths for files upload/get/delete.
Escape XML filter/search values for CardDAV/WebDAV operations.
After mutations (create, edit, complete, delete), verify with follow-up read/list when practical.
For propagation delay, retry around 0.5s, 1s, 2s before declaring failure.

Known Nextcloud/CardDAV Behaviors

Servers/clients may negotiate or normalize vCard versions (3.0 vs 4.0) and content on write/read.
FN and N should each appear once in valid contacts.
BDAY failures are often malformed input (for example stray delimiters), not server instability.
Folded vCard lines must be unfolded before parsing.

Error to Action Map (Fast)

HTTP 403 on calendar create/edit/delete -> likely read-only/system calendar or missing permission; switch to writable events calendar.
HTTP 501 on files search -> WebDAV SEARCH unsupported; fallback to recursive PROPFIND + client-side filter.
HTTP 415 on task/event update -> malformed ICS payload; normalize formatting and retry once.
Contact write succeeded but UI still stale -> run verification retry cycle before reporting failure.

Agent Behavior: Default Calendar Selection

When user creates tasks/events without explicit calendar:

Run calendars list --type tasks or calendars list --type events.
For events, filter out likely read-only calendars first (Contact birthdays, Holidays, names containing read only or readonly).
If at least one writable calendar remains, ask for selection.
Ask whether to remember as default.
Store in memory.
If no writable events calendar remains, explain why event mutation is unavailable and suggest creating a writable calendar in Nextcloud Calendar.

Memory keys:

default_task_calendar
default_event_calendar

Agent Behavior: Default Address Book Selection

When user creates contacts without explicit address book:

Run addressbooks list.
Ask for selection.
Ask whether to remember default.
Store in memory.

Memory key:

default_addressbook

Agent Behavior Playbooks (Condensed)

These playbooks are execution shortcuts. Reliability and safety rules above still apply.

Contacts and Birthdays

Resolve address book (--addressbook or remembered default).
For create/edit, pass only user-requested fields; use explicit empty values when user wants fields cleared.
Use --name for full-name input; use structured-name flags for split-name input.
Pass multiple emails/phones as CSV values.
Birthday changes always go through contacts (contacts create/edit --birthday ...), never calendar mutation commands.
Verify birthday/name-sensitive writes with contacts get --uid ... when confidence is important.

Tasks

Resolve task calendar when omitted.
Validate due and priority (0..9) before write.
After create/edit/complete/delete, verify via focused list/get when practical.

Calendar Events

Resolve writable events calendar; treat Contact birthdays and system calendars as read-only.
Validate start/end and require end > start for timed events.
For timezone-less date-times, pass --timezone or use NEXTCLOUD_TIMEZONE.
For all-day intent, use --all-day with date values (not timed midnight ranges).
Re-list in a focused window after mutation when confidence is important.

All-day end-date normalization behavior:

start=YYYY-MM-DD, end=YYYY-MM-DD -> inclusive single-day input, normalized.
start=YYYY-MM-DD, end=next-day -> already-exclusive single-day input.
Multi-day inclusive ranges -> normalized to canonical exclusive DTEND.

Appointment briefing workflow (high priority intent)

Use this when user asks for appointment details, address, or "what is my appointment today":

Determine "today" in NEXTCLOUD_TIMEZONE (or ask if timezone is unclear).
Run calendar list --from <start-of-day-iso> --to <end-of-day-iso>.
Filter events by user terms (for example dermatology, doctor, provider name).
For the selected event, include summary, time window, location, and key lines from description.
If multiple events match, ask a quick disambiguation question.
If none match, clearly say none found for today and offer to check tomorrow or full week.
Provide a plain-text message suitable for SMS/chat (short lines, no markdown).

Files

Require explicit file path for mutating operations.
files get/upload/delete accept either a relative user path (for example /Share-Family/file.docx) or a full DAV href returned by search.
For binary files (ODT, DOCX, PDF, images), use python3 scripts/files_binary.py — never pass binary content through nextcloud.js files upload.
Use deterministic test paths for temporary validation files.
Read back uploaded content and then delete test files.
Use files search with user phrasing directly; it auto-normalizes query text and ranks likely matches.
On large instances, prefer narrower path-based listing before broad search to reduce load.

Notes

Create with explicit title/content.
Read back by id after create/edit.
Delete temporary test notes after verification.

Internal Smoke Test Protocol

When validating this skill in a live environment:

Contacts: create -> get -> edit -> get -> optional delete.
Notes: create -> get -> edit -> get -> delete.
Files: upload -> get -> search/list -> delete.
Tasks: create -> list/locate -> edit -> complete -> delete.
Calendar: create -> list/locate -> edit -> delete.

Use a unique timestamped suffix on all test data and clean up all temporary artifacts unless the user requests keeping them. Use least-privilege credentials for tests and monitor outbound traffic; the process should only communicate with NEXTCLOUD_URL.

Calendar exception handling:

If no writable event calendar exists, mark calendar mutation tests as intentionally skipped (environment limitation), and still run calendar list.
Do not treat this as a skill failure; treat it as a server capability/permission constraint.

Persistent Rules (Store These)

Persist these high-value rules in memory/rules:

Birthdays are contact fields: use contacts create/edit --birthday ...; never mutate Contact birthdays directly.
For all-day events, always use calendar create/edit --all-day with date values (avoid timed midnight ranges).
For timezone-less timed values, use --timezone or NEXTCLOUD_TIMEZONE; ask if timezone is unknown.
Prefer writable user calendars for event mutations; if 403, report likely read-only/permission issue.
Verify event/contact writes with a focused read/list before declaring final success.
Keep canonical all-day encoding (VALUE=DATE); avoid duplicate compatibility events unless explicitly requested.

Troubleshooting Playbook

Birthday was updated but not visible in Nextcloud UI yet:
- Run contacts get --uid ... immediately.
- If value is correct in API, advise short wait + UI refresh.
- Re-check after retry intervals before escalating.
contacts get and contacts search disagree briefly:
- Prefer retry cycle and then trust latest consistent result.
- Do not create duplicate contact entries while waiting.
Event creation keeps failing:
- Run calendars list --type events and verify at least one writable non-system calendar exists.
- If only birthday/system calendars exist, explain limitation and stop mutation attempts.

Output Envelope

All commands return JSON:

Success:

{
  "status": "success",
  "data": {}
}

Error:

{
  "status": "error",
  "message": "Error description"
}

About this skill

Automatic

Personal Assistant pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

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

LeoYeAI / openclaw-master-skills

skills/nextcloud-aio-oc/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 1 file · scripts

Illustrative Want to see what leoyeai/nextcloud-aio-oc (NextCloud AIO OpenClaw) 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

NextCloud AIO OpenClaw Skill

Required Configuration

Runtime and Metadata Contract

Preflight Audit Gate

Security and Publish Safety

Bundled Script Review Checklist (Before First Use)

Static audit snapshot (current bundle)

Run

Commands

Notes

Tasks

Calendar Events

Calendar Discovery

Files (text)

Files (binary) — ODT, DOCX, PDF, images, etc.

Contacts

Address Book Discovery

Contact Data Contract (Important)

Reliability Rules (Quick Reference)

Known Nextcloud/CardDAV Behaviors

Error to Action Map (Fast)

Agent Behavior: Default Calendar Selection

Agent Behavior: Default Address Book Selection

Agent Behavior Playbooks (Condensed)

Contacts and Birthdays

Tasks

Calendar Events

Appointment briefing workflow (high priority intent)

Files

Notes

Internal Smoke Test Protocol

Persistent Rules (Store These)

Troubleshooting Playbook

Output Envelope

SkillSafety

Source

Related skills

More in the registry