Ready to supercharge your AI agents?

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

Get Started Free →

Learning Loop · leoyeai | DecimalAI

Agent Toolingby leoyeai

Learning Loop

Structured self-improvement system for AI agents with confidence decay, cross-agent sharing, and anomaly detection.

Never made a case worse

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

18%91%of test cases passed +73 pts

Without skill4 of 22

With skill20 of 22

16 fixed4 passed either way2 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v120 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe are setting up learning tracking for an agent project located at `/apps/agent-1`. What command initializes the structured storage framework, and in what subdirectory are the learning files placed?

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-learning-loop
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-learning-loop")
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-learning-loop

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-learning-loop/SKILL.md https://app.decimal.ai/s/leoyeai-learning-loop/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-learning-loop/SKILL.md

This gets SKILL.md only. The skill's 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/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-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/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-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop")
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-learning-loop/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-learning-loop/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 4 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 leoyeai-learning-loop

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-learning-loop/SKILL.md https://app.decimal.ai/s/leoyeai-learning-loop/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-learning-loop/SKILL.md

This gets SKILL.md only. The skill's 4 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/leoyeai-learning-loop/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-learning-loop.json

This gets SKILL.md only. The skill's 4 other files are 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

Learning Loop

Stop waking up stupid.

AI agents lose everything on compaction. Every debugging session, every hard-won lesson, every correction from your human - gone. You start fresh and repeat the same failures. Your human notices. Trust erodes.

The Learning Loop is a structured self-improvement system that gives agents persistent, compounding intelligence. It captures what you learn, promotes proven patterns into hard rules, tracks your improvement over time, detects when your human is satisfied or frustrated - automatically, and now includes confidence decay and cross-agent knowledge sharing.

This isn't a toy. This is infrastructure for agents that want to get measurably better at their job, every single session.

Architecture Overview

┌─────────────────────────────────────────────────────────────┐
│                    LEARNING LOOP v1.4.0                      │
├─────────────────────────────────────────────────────────────┤
│                                                              │
│  INPUT LAYER          PROCESSING LAYER        OUTPUT LAYER  │
│  ───────────          ────────────────        ────────────  │
│                                                              │
│  Events ──────────▶  Pattern Detection  ────▶  Reports      │
│    │                     │                         │        │
│    ▼                     ▼                         ▼        │
│  lessons.json       Confidence Decay          Rules         │
│    │                     │                         │        │
│    ▼                     ▼                         ▼        │
│  Promotion ◀────── Anomaly Detection ◀────── Enforcement    │
│                                                              │
│  CROSS-AGENT LAYER:                                          │
│  Export ─────▶  Portable Format  ─────▶  Import             │
│                                                              │
└─────────────────────────────────────────────────────────────┘

Data Flow:

Tier 1: Events - Raw logs of debugging sessions, mistakes, successes, feedback. Append-only, never deleted.
Tier 2: Lessons - Patterns extracted from events. Tracked by applications and saves.
Tier 3: Rules - Lessons promoted after 3+ successful applications with 0.9+ confidence.

Confidence Decay: Rules lose confidence over time using Ebbinghaus-inspired exponential decay. Stale rules (confidence < 0.5) are flagged for review.

Cross-Agent Sharing: Export rules as portable JSON with metadata (hashes, provenance). Import from other agents with conflict detection and trust scoring.

When to Activate

Use the Learning Loop when:

After debugging sessions - Capture the problem, solution, and confidence level to events.jsonl
Receiving user feedback - Positive ("perfect", "exactly") or negative ("wrong", "I already told you") signals trigger automatic capture
Before risky actions - Check pre-action-checklist.md and rules.json for relevant constraints
Weekly maintenance - Run pattern detection, confidence decay, promote qualified lessons to rules, update metrics
During compaction - Flush uncaptured events to prevent knowledge loss
Sharing knowledge - Export rules for other agents, import rules from trusted sources

What It Does

Events (raw)  -->  Lessons (structured)  -->  Rules (enforced)
  append-only       proven patterns           hard constraints
  events.jsonl      lessons.json              rules.json

Three-tier knowledge system:

Tier 1: Events - Raw logs of debugging sessions, mistakes, successes, feedback. Append-only, never deleted.
Tier 2: Lessons - Patterns extracted from events. Tracked by how many times they've been applied and how many mistakes they've prevented.
Tier 3: Rules - Lessons promoted after 3+ successful applications. Loaded at boot. These are your behavioral constraints.

Five enforcement layers ensure learning happens even when discipline fails:

Boot sequence loads rules every session
Compaction flush saves uncaptured events before context compression
Heartbeat checks periodically scan for missed learning opportunities
Daily cron extracts events from session logs
Weekly cron runs pattern detection, metrics, confidence decay, and self-audit

No single layer is critical. If one fails, the others catch it.

Quick Start

bash init.sh /path/to/workspace

That's it. You now have:

memory/learning/
├── events.jsonl          # Raw event log (append-only)
├── rules.json            # Hard behavioral rules (3 starter rules)
├── lessons.json          # Structured lessons (intermediate tier)
├── pre-action-checklist.md  # Check before risky actions
├── metrics.json          # Improvement tracking
├── BOOT.md               # Quick reference for session boot
├── parse-errors.jsonl    # JSON parsing errors (v1.4.0)
└── weekly/               # Weekly learning reports

Wire It In

Add to your agent's boot instructions (AGENTS.md or equivalent):

## Every Session
1. Read `memory/learning/rules.json` - hard behavioral rules
2. Read `memory/learning/BOOT.md` - quick reference
3. Before risky actions, check `memory/learning/pre-action-checklist.md`
4. After mistakes or debugging, append to `memory/learning/events.jsonl`
5. Check rule confidence scores - rules with < 0.5 confidence need review

Set Up Automation

Daily (e.g. 4am):

bash extract.sh /path/to/workspace

Weekly (e.g. Sunday 10pm):

bash detect-patterns.sh /path/to/workspace
bash confidence-decay.sh /path/to/workspace        # NEW v1.4.0
bash promote-rules.sh /path/to/workspace
bash self-audit.sh /path/to/workspace
bash update-metrics.sh /path/to/workspace

Optional: Compaction Flush

If your platform supports custom compaction prompts, add:

"Append uncaptured learning events to memory/learning/events.jsonl and update rules.json if new rules emerged."

This is the safety net that catches learning even during context compression.

Guardrails / Anti-Patterns

DO:

✓ Capture events immediately after debugging or receiving feedback
✓ Use structured JSON format with all required fields (ts, type, category, tags, problem, solution, confidence, source)
✓ Run weekly automation to promote lessons with 3+ successful applications
✓ Check rules.json before risky actions (account ops, shell commands, external comms)
✓ Use wal-capture.sh for critical details that must survive compaction
✓ Keep events.jsonl append-only; never delete or edit historical events
✓ Run confidence-decay.sh weekly to update rule confidence scores
✓ Export rules for cross-agent sharing using export-rules.sh

DON'T:

✗ Wait to capture events - memory degrades, details get lost
✗ Create rules without proven application history (minimum 3 successful applications)
✗ Skip the pre-action checklist for "quick" operations
✗ Delete events to "clean up" - use archive-events.sh for old data instead
✗ Assume lessons apply universally without considering context
✗ Manually edit rules.json - let promote-rules.sh handle promotion
✗ Ignore confidence scores below 0.5 - these rules need review

Full Lifecycle Walkthrough

Here's the complete loop in action, from first mistake to enforced rule.

Day 1: The Mistake

You're building a skill and run find . -not -path '*/node_modules/*' on macOS. It silently skips files. You spend 20 minutes debugging before discovering that extended attributes break find's exclusion flags.

Capture the event:

{"ts":"2026-02-07T15:00:00Z","type":"debug_session","category":"shell","tags":["macos","find","xattr"],"problem":"find -not -path silently skips files with com.apple.provenance on macOS","solution":"Pipe find output through grep -v instead of using find built-in exclusion flags","confidence":"proven","source":"skill-build"}

Append that line to events.jsonl. Done. The knowledge is captured.

Day 3: The Lesson

The daily extraction cron runs extract.sh, which scans your session logs and flags patterns. You (or the weekly cron) extract a structured lesson:

{
  "id": "L-001",
  "created": "2026-02-09",
  "category": "shell",
  "lesson": "On macOS, use grep -v piping instead of find -not -path for file filtering",
  "context": "Extended attributes cause find exclusion flags to silently skip files",
  "trigger": "Any find command with -not -path on macOS",
  "action": "Replace find ... -not -path X with: find ... | grep -v X",
  "confidence": "proven",
  "confidence_score": 0.9,
  "times_applied": 0,
  "times_saved": 0,
  "source_events": ["2026-02-07T15:00:00Z"]
}

Add it to lessons.json. Now it's structured and trackable.

Day 5, 8, 12: Application

Three more times you need to filter files on macOS. Each time, your boot sequence loaded the rules. Each time, you use grep -v instead of find -not -path. Each time, you increment times_applied in the lesson.

Day 14: Promotion

The weekly cron runs promote-rules.sh. It finds L-001 with 3+ applications and confidence >= 0.9, and auto-promotes it:

{
  "id": "R-004",
  "type": "NEVER",
  "category": "shell",
  "rule": "Never use find -not -path or find ! -path on macOS. Always pipe through grep -v instead.",
  "reason": "com.apple.provenance extended attributes cause find exclusions to silently skip files",
  "created": "2026-02-21",
  "source_lesson": "L-001",
  "violations": 0,
  "last_checked": "2026-02-21",
  "last_validated": "2026-02-21",
  "validation_count": 0,
  "confidence_score": 0.9
}

Now it's a hard rule. Loaded at boot. Checked before action. The mistake can never happen again.

Day 14+: Confidence Decay

After 30 days without validation, confidence-decay.sh runs and applies exponential decay:

R-004: 0.90 → 0.22 (30 days since validation)

The rule is now flagged for review. You validate it again by successfully applying it, and the confidence resets to 0.9.

Day 14+: Measurement

update-metrics.sh tracks the trend:

Week 1: 3 mistakes, 0 rules
Week 2: 1 mistake, 5 rules, 2 pre-action saves
Week 3: 0 mistakes, 8 rules, 4 pre-action saves

self-audit.sh scores your loop health: 100% means everything is wired correctly.

That's the full cycle. Raw experience becomes structured knowledge becomes enforced behavior. Compounding intelligence.

Scripts Reference

See references/script-reference.md for detailed script documentation.

Script	Purpose	Schedule
`init.sh`	Initialize directory structure	Once
`extract.sh`	Scan logs for uncaptured events	Daily
`detect-patterns.sh`	Tag clusters, regressions, anomalies (v1.4.0)	Weekly
`confidence-decay.sh`	Apply Ebbinghaus decay to confidence scores (v1.4.0)	Weekly
`export-rules.sh`	Export rules for cross-agent sharing (v1.4.0)	Manual
`import-rules.sh`	Import rules with conflict detection (v1.4.0)	Manual
`promote-rules.sh`	Promote lessons to rules	Daily/Weekly
`self-audit.sh`	Health score (23 checks, A-D)	Weekly
`update-metrics.sh`	Weekly metrics snapshot	Daily/Weekly
`feedback-detector.sh`	Detect human signals	Per-message
`track-violations.sh`	Link mistakes to rules	Daily
`track-applications.sh`	Track lesson applications	Daily
`rule-check.sh`	Dynamic rule lookup	On-demand
`archive-events.sh`	Roll off old events	Monthly
`wal-capture.sh`	Write-Ahead Log capture	Per-message
`inject-rules.sh`	Inject rules into agent context	On-demand

All scripts accept workspace directory as first argument. Default is current directory.

Formats

See references/formats.md for event and rule JSON schemas.

5 event types: mistake, success, debug_session, feedback, discovery 4 rule types: MUST, NEVER, PREFER, CHECK

Rule Schema (v1.4.0)

{
  "id": "R-001",
  "type": "MUST|NEVER|PREFER|CHECK",
  "category": "shell|auth|memory|...",
  "rule": "The behavioral constraint",
  "reason": "Why this rule exists",
  "created": "2026-02-21",
  "source_lesson": "L-001",
  "violations": 0,
  "last_checked": "2026-02-21",
  "last_validated": "2026-02-21",      // NEW v1.4.0
  "validation_count": 0,               // NEW v1.4.0
  "confidence_score": 0.9,             // NEW v1.4.0
  "review_flagged": false              // NEW v1.4.0
}

Cross-Agent Sharing

Share learned rules between agents:

Export rules:

# Export all rules
bash export-rules.sh /path/to/workspace --output my-rules.json

# Export only shell rules
bash export-rules.sh /path/to/workspace --category shell --output shell-rules.json

Import rules:

# Preview import
bash import-rules.sh /path/to/workspace other-agent-rules.json --dry-run

# Import with custom trust threshold
bash import-rules.sh /path/to/workspace other-agent-rules.json --trust 0.8

# Import all rules above default threshold (0.5)
bash import-rules.sh /path/to/workspace other-agent-rules.json

Features:

Integrity verification: Rules include SHA256 hashes
Conflict detection: Similar rules are flagged before import
Trust scoring: Imports are scored based on rule count, confidence, and diversity
Provenance tracking: Import metadata preserved in rules

Troubleshooting

events.jsonl is corrupted

Symptoms: Scripts report JSON parse errors, metrics show fewer events than expected.

Solution:

Check parse-errors.jsonl for details on corrupted lines
Backup: cp events.jsonl events.jsonl.backup

Try to repair by removing bad lines:

python3 -c "
import json
with open('events.jsonl') as f:
    for line in f:
        line = line.strip()
        if line:
            try:
                json.loads(line)
                print(line)
            except:
                pass
" > events.jsonl.fixed
mv events.jsonl.fixed events.jsonl

If still broken, archive and start fresh with init.sh

Rules not loading at boot

Symptoms: Agent repeats mistakes that have rules, rules.json is never read.

Solution:

Verify JSON validity: python3 -c "import json; json.load(open('rules.json'))"
Check AGENTS.md includes: Read memory/learning/rules.json
Check file permissions: ls -la memory/learning/rules.json
Check for lock file: if .lockfile exists, another process may be stuck

Parse errors in parse-errors.jsonl

Symptoms: JSON lines are being skipped, data loss occurring.

Solution:

Check parse-errors.jsonl: cat memory/learning/parse-errors.jsonl
Common causes:
- Manual editing of events.jsonl introducing syntax errors
- Concurrent writes without proper locking (fixed in v1.4.0)
- Encoding issues (must be UTF-8)
Fix the source of bad data
Clear parse-errors.jsonl after review: > memory/learning/parse-errors.jsonl

Lock contention errors

Symptoms: Scripts exit with "Could not acquire lock" error.

Solution:

Check for stuck processes: lsof memory/learning/.lockfile
Kill stuck process if safe: kill <pid>
Remove stale lock file: rm memory/learning/.lockfile
Re-run the script

Confidence decay not working

Symptoms: All rules show confidence 0.9, no decay applied.

Solution:

Verify last_validated field exists in rules (v1.4.0 schema)
Run init.sh to backfill missing fields
Check that rules are older than 1 day (no decay on same-day rules)
Verify confidence-decay.sh is in your weekly cron

Import conflicts

Symptoms: Import reports conflicts, rules not imported.

Solution:

Review conflict report carefully
If rules are truly different, import manually:
- Edit the exported JSON to change the rule text
- Re-import with --trust 0.9 to force review mode
If rules are duplicates, skip import

Customization

See references/customization.md for tuning feedback patterns, categories, promotion thresholds, and pre-action checklists.

Changelog

See references/changelog.md for version history.

Current: v1.4.0 (Confidence decay, cross-agent sharing, anomaly detection, parse error logging)

Requirements

python3 3.8+ and bash
flock (usually part of util-linux, available on macOS via util-linux or coreutils)
A workspace directory with memory/ for file storage
An agent that reads files at boot (AGENTS.md or equivalent)

No external APIs. No dependencies beyond Python and Bash. Runs anywhere.

Philosophy

Most agents are goldfish with tool access. They solve the same problem five times and charge you for each one. The Learning Loop breaks that cycle by treating every session as training data for the next one.

Build it once. Let it compound. Get measurably better every week.

Share what you learn. Import what others discovered. Collective intelligence beats isolated learning.

When it activates

Automatically, when a task matches. Use when: (1) After debugging sessions to capture lessons learned, (2) When receiving feedback or corrections from users, (3) Before risky actions to check relevant rules, (4) Weekly to review metrics and promote proven patterns to enforced rules, (5) Setting up persistent memory that survives session compactions.

About this skill

Automatic

AI Engineer 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/learning-loop/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 4 files

Illustrative Want to see what leoyeai/learning-loop 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

Learning Loop

Architecture Overview

When to Activate

What It Does

Quick Start

Wire It In

Set Up Automation

Optional: Compaction Flush

Guardrails / Anti-Patterns

Full Lifecycle Walkthrough

Day 1: The Mistake

Day 3: The Lesson

Day 5, 8, 12: Application

Day 14: Promotion

Day 14+: Confidence Decay

Day 14+: Measurement

Scripts Reference

Formats

Rule Schema (v1.4.0)

Cross-Agent Sharing

Troubleshooting

events.jsonl is corrupted

Rules not loading at boot

Parse errors in parse-errors.jsonl

Lock contention errors

Confidence decay not working

Import conflicts

Customization

Changelog

Requirements

Philosophy

When it activates

SkillSafety

Source

Related skills

More in the registry