Ready to supercharge your AI agents?

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

Memorist Agent · LeoYeAI | DecimalAI

Documentationby LeoYeAI

Memorist Agent

Memorist Agent — helps you capture your parents' and family members' life stories through adaptive interviews via WhatsApp, WeChat, or direct conversation. Organizes stories into memoir chapters. Local-first, privacy-protected. Bilingual: English + Chinese (普通话). Commands: /memorist_agent setup, interview, stories, compile, export, share.

SkillScore

SkillScore59/100

Test results 59

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

0%59%of test cases passed +59 pts

Without skill0 of 22

With skill13 of 22

13 fixed0 passed either way9 still failing0 broke

Measured on gemini-3.6-flash7/27/2026v119 comparable

Track record

Agent runs: 0; All time

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 memorist-agent
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("memorist-agent")
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 memorist-agent

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/memorist-agent/SKILL.md https://app.decimal.ai/s/memorist-agent/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/memorist-agent/SKILL.md

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Claude Code docs

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

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

Claude Agent SDK docs

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

Install

pip install "decimalai[openai-agents]"
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

OpenAI Agents docs

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

Install

pip install "decimalai[openai]"
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

OpenAI SDK docs

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

Install

pip install "decimalai[anthropic]"
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

Anthropic docs

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

Install

pip install "decimalai[google-genai]"
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/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/memorist-agent/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 5 other files are not included.

Other ways to add it

Gemini API docs

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

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

LangChain docs

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

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/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 5 other files are not included.

Other ways to add it

CrewAI docs

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

Install

pip install "decimalai[adk]"
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

Google ADK docs

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

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

Pydantic AI docs

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

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

Deep Agents docs

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

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

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

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add memorist-agent

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("memorist-agent")
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/memorist-agent/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/memorist-agent/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 5 other files are not included.

Other ways to add it

Strands docs

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

pip install "decimalai>=0.15"
decimalai skills add memorist-agent

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/memorist-agent/SKILL.md https://app.decimal.ai/s/memorist-agent/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/memorist-agent/SKILL.md

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Cursor and other editors docs

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

Get the file

curl -fsSL https://app.decimal.ai/s/memorist-agent/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/memorist-agent.json

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/27/2026
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

Memorist Agent

Help your parents and grandparents tell their stories before it's too late.

Memorist Agent conducts adaptive, empathetic interviews across 9 life domains — in English or Chinese. It remembers every name, place, and year the narrator mentions and follows up with targeted questions to draw out richer memories.

Why Memorist Agent?

Local-first — Every story fragment, entity, and chapter lives on your machine at ~/.openclaw/memorist_agent/. Nothing is uploaded to any server. You own your family's data completely.
Private by design — No accounts, no cloud sync, no third-party databases. The only network calls are the ones you explicitly trigger (sending a WhatsApp question or sharing an export). Delete the folder and it's gone.
Easy to use — Run /memorist_agent setup, answer 4 questions, and you're interviewing. Relay mode works immediately with zero configuration. WhatsApp auto-reply takes one extra command. The AI handles question flow, entity tracking, and story writing — you just talk to your family.
Bilingual — Native support for English and Chinese (普通话). The agent mirrors the narrator's language naturally, including dialect phrases and colloquial expressions.
Works with any channel — WhatsApp, Telegram, WeCom, iMessage, or just relay questions in person over tea. The skill adapts to however your family communicates.

Quick Start — Your First Interview

Step 1 — Set up a narrator:

/memorist_agent setup

Step 2 — Pick "Relay" mode (easiest — no extra config needed). You'll get questions to ask your narrator in person, over the phone, or via any messaging app. Type or paste their answers back.

Step 3 — Run the interview:

/memorist_agent interview --narrator "Dad"

That's it. After 3–5 questions, the skill saves a story fragment automatically.

Want hands-free WhatsApp? Pick "WhatsApp auto-reply" during setup instead. The narrator chats directly with their own dedicated agent — no copy-pasting needed. Requires WhatsApp gateway setup (see Prerequisites below).

What You Need

OpenClaw gateway running: openclaw status should show gateway running.
Everything else is set up automatically on first run.

Nice to have (based on your setup):

Feature	What to configure
WhatsApp auto-reply	WhatsApp linked (`openclaw status`), narrator's number in `channels.whatsapp.allowFrom` or `dmPolicy: "open"`, `mkdir -p ~/.openclaw/media`
Telegram auto-reply	Telegram bot configured, narrator's numeric user ID in `channels.telegram.allowFrom`
WeCom auto-reply	`@sunnoy/wecom` plugin loaded, `channels.wecom.enabled: true`
iMessage auto-reply	macOS only. `channels.imessage.enabled: true`, narrator's phone/email in `channels.imessage.allowFrom`, Full Disk Access granted to terminal. Requires `imsg` CLI (`brew install pj4533/homebrew-imsg/imsg`)
Voice replies (TTS)	`messages.tts` configured in openclaw config — see `references/media-and-voice.md`
Voice note transcription	`pip3 install mlx-whisper` (Apple Silicon) or `brew install openai-whisper`, or run `/memorist_agent setup-stt`

File paths use ~/.openclaw/ ($HOME/.openclaw/ on all platforms — macOS, Linux, Windows WSL).

Commands

Command	Description
`/memorist_agent setup`	Add a narrator and configure their interview channel
`/memorist_agent interview [--narrator NAME] [--domain DOMAIN]`	Start or continue an interview session
`/memorist_agent spawn [--narrator NAME]`	Enable auto-reply — creates a dedicated agent for this narrator
`/memorist_agent despawn [--narrator NAME]`	Disable auto-reply — remove the dedicated agent
`/memorist_agent remind [--narrator NAME]`	Send a gentle reminder to continue their story
`/memorist_agent stories [--narrator NAME] [--domain DOMAIN]`	Browse collected story fragments
`/memorist_agent entities [--narrator NAME]`	Show the entity map: people, places, years
`/memorist_agent compile [--narrator NAME]`	Compile fragments into polished memoir chapters
`/memorist_agent export [--narrator NAME] [--format md\|json\|txt]`	Export the memoir to a file
`/memorist_agent share [--narrator NAME]`	Invite a family co-editor to review
`/memorist_agent status`	Show all narrators, progress, and agent status
`/memorist_agent setup-stt`	Auto-install voice transcription

Life Story Domains

ID	Domain (EN)	Domain (ZH)	Sample Opening Question
`origins`	Origins & Childhood	出身与童年	"Where were you born, and what's your earliest memory of home?"
`growing-up`	Growing Up	成长岁月	"What was school like for you? Who were your closest friends?"
`family-history`	Family History	家族历史	"Tell me about your parents — what kind of people were they?"
`love`	Love & Partnership	爱情与伴侣	"How did you and Mum/Dad first meet?"
`work`	Work & Career	工作与事业	"What was your first real job? What did you dream of becoming?"
`places`	Places & Journeys	地方与旅途	"What places have you lived in across your life?"
`history`	Historical Moments	历史时刻	"You lived through [decade] — what do you remember most?"
`milestones`	Family Milestones	家庭里程碑	"What family celebrations stand out most in your memory?"
`wisdom`	Values & Wisdom	价值观与智慧	"What's the most important lesson life has taught you?"

Storage Layout

All data is stored locally at ~/.openclaw/memorist_agent/:

~/.openclaw/memorist_agent/
├── owner.json                           # Skill owner's name
├── narrators.json                       # Index of all narrators
├── narrators/
│   └── {narrator-id}/
│       ├── profile.json                 # Narrator metadata & domain progress
│       ├── entities.json                # Extracted people, places, years
│       ├── sessions.json                # Interview session log
│       ├── fragments/                   # Story fragments by domain
│       ├── chapters/                    # Compiled memoir chapters
│       ├── exports/                     # Exported memoir files
│       └── workspace/                   # Agent workspace (if auto-reply enabled)

/memorist_agent setup

Purpose: Register a narrator and choose how interviews will be conducted.

Steps:

First-run bootstrap: Create the data directory if it doesn't exist:
- mkdir -p ~/.openclaw/memorist_agent/narrators
- If narrators.json doesn't exist, create it as [].
- If this is the first run, ask: "What's your name? (This is how narrators will know who set this up.)" Save to ~/.openclaw/memorist_agent/owner.json as { "name": "{name}" }. Skip if owner.json already exists.

Ask the user:

Let's set up your narrator. I'll ask a few questions.

1. What is their name? (e.g. "Dad", "Grandma Li", "Uncle Chen")
2. What's their relationship to you? (parent / grandparent / relative / friend)
3. What language should I interview them in?
   [1] English
   [2] Chinese (普通话)
   [3] Both (start in Chinese, key summaries in English)
4. How should I conduct interviews?
   [1] Relay — I give you questions, you ask them and bring back answers
       (Works with any channel: in person, phone call, WeChat, etc.)
   [2] WhatsApp auto-reply — they chat directly with a dedicated agent
       (Requires WhatsApp gateway. I'll help you set it up.)
   [3] iMessage auto-reply — they chat via iMessage with a dedicated agent
       (macOS only. Requires iMessage channel configured.)
   [4] Telegram auto-reply — they chat via Telegram with a dedicated agent
       (Requires Telegram bot configured.)
   [5] Live — the narrator is here right now, let's start talking

If "WhatsApp auto-reply" is selected: a. Ask for their WhatsApp number (with country code, e.g. +1234567890). b. Validate allowlist: Read the openclaw config and check if the number is in channels.whatsapp.allowFrom or if dmPolicy is "open". If NOT:
```
⚠️  {number} is not in your WhatsApp allowlist yet.
Their replies will be silently dropped without this.

I can add it for you — shall I update channels.whatsapp.allowFrom?
[Yes, add it] / [No, I'll do it manually]
```
If user says yes, add the number to channels.whatsapp.allowFrom in the openclaw config file. c. Verify gateway: Check openclaw status output. If WhatsApp is not linked:
```
⚠️  WhatsApp gateway is not connected.
Run: openclaw status
If WhatsApp shows "not linked", you'll need to pair it first.

For now, I'll set up the narrator in Relay mode. You can switch to
WhatsApp auto-reply later with /memorist_agent spawn.
```
Fall back to relay mode if gateway is not ready. d. Create media directory: mkdir -p ~/.openclaw/media (gateway rejects media from other paths).
If "iMessage auto-reply" is selected: a. Ask for their phone number or Apple ID email. b. Check platform: If not macOS, warn: "iMessage is only available on macOS. Switching to Relay mode." c. Validate allowlist: Check if the number/email is in channels.imessage.allowFrom or if dmPolicy is "open". Offer to add if missing (same flow as WhatsApp step 3b). d. Verify iMessage: Check openclaw status — iMessage should show OK or configured. If not:
```
⚠️  iMessage channel is not configured.
Make sure:
  1. channels.imessage.enabled: true in your openclaw config
  2. imsg CLI is installed: brew install pj4533/homebrew-imsg/imsg
  3. Full Disk Access is granted to your terminal app
     (System Settings → Privacy & Security → Full Disk Access)

For now, I'll set up in Relay mode. Switch later with /memorist_agent spawn.
```
e. Create media directory: mkdir -p ~/.openclaw/media.
If "Telegram auto-reply" is selected: a. Ask for their Telegram user ID (numeric). Explain: "Ask them to message @userinfobot on Telegram to get their numeric ID." b. Validate allowlist: Check if the ID is in channels.telegram.allowFrom. Offer to add if missing. c. Verify Telegram: Check openclaw status — Telegram should show OK. Warn and fall back to relay if not configured.
If "Live" is selected: Note that the narrator is present — skip channel setup, start interview immediately after setup completes.
Generate a narrator ID: narrator-{slug(name)}-{timestamp}.

Create ~/.openclaw/memorist_agent/narrators/{id}/ directory structure (including fragments/, chapters/, exports/ subdirs):

profile.json:

{
  "id": "{narrator-id}",
  "name": "{name}",
  "relationship": "{relationship}",
  "lang": "{en|zh|both}",
  "channel": "{relay|whatsapp|imessage|telegram|live}",
  "whatsapp": "{number or null}",
  "imessage": "{phone or email or null}",
  "telegram": "{numeric user ID or null}",
  "replyFormat": "text",
  "createdAt": "{ISO timestamp}",
  "domains": {
    "origins": { "status": "not-started", "fragmentCount": 0 },
    "growing-up": { "status": "not-started", "fragmentCount": 0 },
    "family-history": { "status": "not-started", "fragmentCount": 0 },
    "love": { "status": "not-started", "fragmentCount": 0 },
    "work": { "status": "not-started", "fragmentCount": 0 },
    "places": { "status": "not-started", "fragmentCount": 0 },
    "history": { "status": "not-started", "fragmentCount": 0 },
    "milestones": { "status": "not-started", "fragmentCount": 0 },
    "wisdom": { "status": "not-started", "fragmentCount": 0 }
  }
}

entities.json: { "people": [], "places": [], "years": [], "events": [] }

sessions.json: []

Append narrator to narrators.json.

If channel is "whatsapp", "imessage", or "telegram", immediately recommend auto-reply:

Narrator added: {name}
Language  : {lang}
Channel   : WhatsApp ({number})

For the best experience, I recommend enabling auto-reply so {name}
can chat directly without you copy-pasting messages.

Enable now? /memorist_agent spawn --narrator "{name}"
[Skip — I'll use relay mode for now]

Otherwise (relay or live):

Narrator added: {name}
Language  : {lang}
Channel   : {channel}
Domains   : 9 life story domains ready

Start the first interview with:
/memorist_agent interview --narrator "{name}"

/memorist_agent interview

Purpose: Conduct one interview session covering one memory domain. Generates 1–3 story fragments and updates the entity map.

Usage:

/memorist_agent interview — auto-selects narrator and next domain
/memorist_agent interview --narrator "Dad" — specific narrator
/memorist_agent interview --narrator "Dad" --domain origins — specific domain
/memorist_agent interview --narrator "Dad" --resume — continue last session

High-level flow:

Load narrator context (profile, entities, prior fragments)
Pick next domain (or resume in-progress one)
Generate opening question adapted to language and prior context
Send question via configured channel (relay, WhatsApp, or live)
Run adaptive follow-up loop (3–5 exchanges per session)
Distill exchanges into a first-person story fragment
Update entity map and save all data

Error handling:

If no narrators exist: "No narrators set up yet. Run /memorist_agent setup first."
If all 9 domains are complete: "All domains are complete! Run /memorist_agent compile to create the memoir."
If WhatsApp gateway is down: Fall back to relay mode and warn the user.

For detailed step-by-step instructions, read: references/interview-workflow.md

Interview principles (read before first session): references/interview-principles.md

/memorist_agent remind

Purpose: Send a gentle, warm reminder to continue sharing stories.

Steps:

Load narrator profile. Find in-progress or next not-started domain.
Generate personalized reminder referencing something they already shared.
Send via WhatsApp if configured, otherwise display for relay.

/memorist_agent stories

Purpose: Browse collected story fragments.

Usage:

/memorist_agent stories — all fragments for default narrator
/memorist_agent stories --narrator "Dad" --domain origins — filtered

Steps:

Load all fragment files for the narrator.
Display grouped by domain: title, preview, people/places mentioned, pending follow-ups.
Show total fragment count and domain coverage.

/memorist_agent entities

Purpose: Show the entity map — all people, places, years, events extracted from stories.

Steps:

Load entities.json for the narrator.
Display grouped by type, with follow-up status (resolved vs pending).
Show count of unresolved entities that will be followed up automatically.

/memorist_agent compile, export, share

Purpose: Compile fragments into memoir chapters, export to file, share with family.

For detailed instructions, read: references/compile-export-share.md

/memorist_agent spawn, despawn

Purpose: Enable or disable auto-reply for a narrator. "Spawn" creates a dedicated, isolated agent that chats directly with the narrator — no copy-pasting needed. "Despawn" removes it.

After spawning, all messages from the narrator's WhatsApp/Telegram route directly to their personal agent. The main session is never touched.

Error handling:

If gateway is not running: "Gateway is not running. Start it with openclaw gateway start, then try again."
If WhatsApp is not linked: "WhatsApp is not connected. Run openclaw status to check."
If narrator's number is not in allowlist: Offer to add it (same as setup step 3b).
If spawn fails for any reason: Fall back gracefully — "Auto-reply couldn't be enabled. You can still use relay mode with /memorist_agent interview."

For detailed instructions, read: references/spawn-despawn.md

/memorist_agent status

Purpose: Overview of all narrators and their progress.

Steps:

Load narrators.json and each narrator's profile.json.
Display per narrator: name, relationship, language, channel, agent status, domain progress bar, fragment count, last session date.
Show available commands.

Memorist Agent — Overview

Narrators: {N}
───────────────────────────────
{name} ({relationship})
  Language  : {lang}
  Channel   : {Relay / WhatsApp auto-reply / Live}
  Agent     : {active/none}
  Progress  : {bar} {N}/9 domains
  Fragments : {count} stories collected
───────────────────────────────

Common Issues

Problem	Cause	Fix
Narrator's WhatsApp replies don't arrive	Number not in allowlist	Add to `channels.whatsapp.allowFrom` in openclaw config, or set `dmPolicy: "open"`
`/memorist_agent spawn` fails	Gateway not running	`openclaw gateway start` or `openclaw gateway restart`
Media sends hang (text works)	Gateway WhatsApp connection crashed	`openclaw gateway restart`
Voice notes not transcribed	No STT tool installed	Run `/memorist_agent setup-stt`
Voice replies don't play properly	Wrong audio format	WhatsApp needs OGG/Opus, not MP3. See `references/media-and-voice.md`
TTS produces garbled speech	Wrong voice language	Set `messages.tts.edge.voice` to match narrator's language in openclaw config
Interview says "no narrators"	Haven't run setup yet	Run `/memorist_agent setup` first
All domains complete	Interviews finished	Run `/memorist_agent compile` to create the memoir

Privacy Architecture

Data	Where it lives	Who can access
Story fragments	`~/.openclaw/memorist_agent/`	Local machine only
Entity map	`~/.openclaw/memorist_agent/`	Local machine only
Interview sessions	`~/.openclaw/memorist_agent/`	Local machine only
Compiled chapters	`~/.openclaw/memorist_agent/`	Local machine only
WhatsApp messages sent	Narrator's WhatsApp	Narrator only
Exported files	Path you choose	You control sharing

Claude AI processes text during active sessions. If privacy-sensitive, use relay mode — type questions manually and record answers yourself.

Tool Usage Notes

file_read / file_write: all narrator data at ~/.openclaw/memorist_agent/.
whatsapp_send_message: used only when narrator channel is whatsapp.
fetch: only called if user runs /memorist_agent share with API option.
web_search: not used. This skill is intentionally offline-first.

For media format requirements, TTS config, STT setup, and troubleshooting, read: references/media-and-voice.md

About this skill

Automatic

Knowledge Management pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

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/memorist-agent/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 5 files

Illustrative Want to see what memorist_agent 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

Memorist Agent

Why Memorist Agent?

Quick Start — Your First Interview

What You Need

Commands

Life Story Domains

Storage Layout

/memorist_agent setup

/memorist_agent interview

/memorist_agent remind

/memorist_agent stories

/memorist_agent entities

/memorist_agent compile, export, share

/memorist_agent spawn, despawn

/memorist_agent status

Common Issues

Privacy Architecture

Tool Usage Notes

SkillSafety

Source

Related skills

More in the registry