Ready to supercharge your AI agents?

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

Jules REST API Skill · leoyeai | DecimalAI

Agent Toolingby leoyeai

Jules REST API Skill

Use the Jules REST API (v1alpha) via curl to list sources, create sessions, monitor activities, approve plans, send messages, and retrieve outputs (e.g., PR URLs).

Never made a case worse

SkillScore

SkillScore86/100

Test results 86

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

32%86%of test cases passed +55 pts

Without skill7 of 22

With skill19 of 22

12 fixed7 passed either way3 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v119 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWrite the command to download changes for session 'sess-777' locally using the Node helper script `scripts/jules.js`.

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-jules-api
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-jules-api")
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-jules-api

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-jules-api/SKILL.md https://app.decimal.ai/s/leoyeai-jules-api/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-jules-api/SKILL.md

This gets SKILL.md only. The skill's 2 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-jules-api

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-jules-api")
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-jules-api/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-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/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-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-jules-api/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 2 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-jules-api

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-jules-api")
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-jules-api/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-jules-api/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 2 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-jules-api

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-jules-api/SKILL.md https://app.decimal.ai/s/leoyeai-jules-api/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-jules-api/SKILL.md

This gets SKILL.md only. The skill's 2 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-jules-api/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-jules-api.json

This gets SKILL.md only. The skill's 2 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

Jules REST API Skill

Quick Start

# 0. Set your API key (required — get one at https://jules.google.com/settings#api)
export JULES_API_KEY="your-api-key-here"

# 1. Verify available sources (pre-flight check)
./scripts/jules_api.sh sources

# 2. Create a session with plan approval and auto PR creation
./scripts/jules_api.sh new-session \
  --source "sources/github/OWNER/REPO" \
  --title "Add unit tests" \
  --prompt "Add comprehensive unit tests for the authentication module" \
  --branch main \
  --require-plan-approval \
  --auto-pr

# 3. Monitor session progress and approve the plan
./scripts/jules_api.sh activities --session SESSION_ID
./scripts/jules_api.sh approve-plan --session SESSION_ID

Note: Use your GitHub username/org, not your local system username (e.g., sources/github/octocat/Hello-World, not sources/github/$USER/Hello-World).

Overview

This skill enables programmatic interaction with the Jules REST API (v1alpha) for delegating coding tasks to Jules, Google's autonomous AI coding agent. It supports:

Task Assignment: Create new coding sessions with specific prompts
Session Monitoring: Track session state and activities in real-time
Plan Management: Approve or review generated plans
Messaging: Send follow-up messages to active sessions
Result Integration: Retrieve PR URLs and code changes from completed sessions

Before You Start

1. Get an API Key

Create a Jules API key in the Jules web app:

Navigate to: https://jules.google.com/settings#api
You can have at most 3 API keys at a time

Export it on the machine running the agent:

export JULES_API_KEY="your-api-key-here"

2. Connect Your GitHub Repository

Before the API can operate on a GitHub repo, you must:

Install the Jules GitHub app via the Jules web UI
Grant access to the specific repositories you want Jules to work on

3. Verify Repository Access

# List available sources to verify access and see correct format
./scripts/jules_api.sh sources

You'll see entries like:

{
  "sources": [
    {
      "name": "sources/github/octocat/Hello-World",
      "githubRepo": {
        "owner": "octocat",
        "repo": "Hello-World",
        "defaultBranch": { "displayName": "main" },
        "branches": [
          { "displayName": "main" },
          { "displayName": "develop" }
        ]
      }
    }
  ]
}

Base URL & Authentication

Property	Value
Base URL	`https://jules.googleapis.com/v1alpha`
Auth Header	`x-goog-api-key: $JULES_API_KEY`

All requests authenticate with:

-H "x-goog-api-key: $JULES_API_KEY"

Core Concepts

Resources

Resource	Description
Source	A GitHub repository connected to Jules. Format: `sources/github/{owner}/{repo}`
Session	A unit of work where Jules executes a coding task. Contains state, activities, and outputs
Activity	An individual event within a session (plan generated, message sent, progress update, etc.)

Session States

State	Description
`QUEUED`	Session is waiting to start
`PLANNING`	Generating execution plan
`AWAITING_PLAN_APPROVAL`	Waiting for user to approve plan
`AWAITING_USER_FEEDBACK`	Needs user input to continue
`IN_PROGRESS`	Actively executing the task
`PAUSED`	Temporarily stopped
`COMPLETED`	Successfully finished
`FAILED`	Encountered an error

Activity Types

Type	Description
Plan Generated	A plan was generated for the task
Plan Approved	The plan was approved (manually or auto)
User Message	User posted a message to the session
Agent Message	Jules posted a message
Progress Update	Status update on current work
Session Completed	Session finished successfully
Session Failed	Session encountered an error

Workflows

Option 1: Session with Plan Approval and Auto-PR (Recommended)

Create a session that requires plan approval before execution and automatically creates a PR when complete:

./scripts/jules_api.sh new-session \
  --source "sources/github/octocat/Hello-World" \
  --title "Fix login bug" \
  --prompt "Fix the null pointer exception in the login handler when email is empty" \
  --branch main \
  --require-plan-approval \
  --auto-pr

Why this is recommended:

You review and approve the plan before Jules executes changes
PR is created automatically on completion
Balances automation with human oversight

Option 2: Fully Automated Session (No Plan Approval)

For low-risk or routine tasks in non-sensitive repos, you can skip plan approval:

# Create session without plan approval (use only for low-risk tasks)
./scripts/jules_api.sh new-session \
  --source "sources/github/octocat/Hello-World" \
  --title "Fix typo in README" \
  --prompt "Fix the typo in README.md line 5" \
  --branch main \
  --auto-pr

Warning: Without --require-plan-approval, Jules will automatically approve its own plan and execute changes. Only use this for low-risk tasks in non-critical repos.

Option 3: Interactive Session

Send follow-up messages during an active session:

# Create session
./scripts/jules_api.sh new-session \
  --source "sources/github/octocat/Hello-World" \
  --title "Add API endpoints" \
  --prompt "Add REST API endpoints for user management" \
  --branch main

# Send additional instructions
./scripts/jules_api.sh send-message \
  --session SESSION_ID \
  --prompt "Also add input validation for all endpoints"

API Reference

Sources

List Sources

Lists all connected GitHub repositories.

curl -sS \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sources"

Query Parameters:

Parameter	Type	Default	Description
`pageSize`	integer	30	Number of sources to return (1-100)
`pageToken`	string	-	Token from previous response for pagination
`filter`	string	-	AIP-160 filter (e.g., `name=sources/source1`)

Response:

{
  "sources": [
    {
      "name": "sources/github/octocat/Hello-World",
      "githubRepo": {
        "owner": "octocat",
        "repo": "Hello-World",
        "isPrivate": false,
        "defaultBranch": { "displayName": "main" },
        "branches": [
          { "displayName": "main" },
          { "displayName": "develop" }
        ]
      }
    }
  ],
  "nextPageToken": "..."
}

Get Source

Retrieves a single source by name.

curl -sS \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sources/github/octocat/Hello-World"

Use this to see available branches before creating a session.

Sessions

Create Session

Creates a new coding session.

curl -sS "https://jules.googleapis.com/v1alpha/sessions" \
  -X POST \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $JULES_API_KEY" \
  -d '{
    "prompt": "Add unit tests for the login module",
    "title": "Add Login Tests",
    "sourceContext": {
      "source": "sources/github/octocat/Hello-World",
      "githubRepoContext": {
        "startingBranch": "main"
      }
    },
    "requirePlanApproval": true,
    "automationMode": "AUTO_CREATE_PR"
  }'

Request Body Fields:

Field	Type	Required	Description
`prompt`	string	Yes	The task description for Jules
`title`	string	No	Short title for the session
`sourceContext.source`	string	Yes	Source name (e.g., `sources/github/owner/repo`)
`sourceContext.githubRepoContext.startingBranch`	string	Yes	Branch to start from
`requirePlanApproval`	boolean	No	If true, pause for plan approval. Recommended: true for production repos
`automationMode`	string	No	Set to `AUTO_CREATE_PR` for automatic PR creation

Response:

{
  "name": "sessions/31415926535897932384",
  "id": "31415926535897932384",
  "prompt": "Add unit tests for the login module",
  "title": "Add Login Tests",
  "state": "QUEUED",
  "url": "https://jules.google/session/31415926535897932384",
  "createTime": "2026-01-15T10:30:00Z",
  "updateTime": "2026-01-15T10:30:00Z"
}

List Sessions

Lists your sessions.

curl -sS \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sessions?pageSize=20"

Query Parameters:

Parameter	Type	Default	Description
`pageSize`	integer	30	Number of sessions to return (1-100)
`pageToken`	string	-	Token from previous response for pagination

Get Session

Retrieves a single session by ID.

curl -sS \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sessions/SESSION_ID"

Response includes outputs on completion:

{
  "name": "sessions/31415926535897932384",
  "id": "31415926535897932384",
  "state": "COMPLETED",
  "outputs": [
    {
      "pullRequest": {
        "url": "https://github.com/octocat/Hello-World/pull/42",
        "title": "Add Login Tests",
        "description": "This PR adds comprehensive unit tests..."
      }
    }
  ]
}

Send Message

Sends a message to an active session.

curl -sS \
  -X POST \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sessions/SESSION_ID:sendMessage" \
  -d '{"prompt": "Also add integration tests"}'

Use this to provide feedback, answer questions, or give additional instructions.

Approve Plan

Approves a pending plan (only needed if requirePlanApproval was true).

curl -sS \
  -X POST \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sessions/SESSION_ID:approvePlan"

Delete Session

Deletes a session.

curl -sS \
  -X DELETE \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sessions/SESSION_ID"

Activities

List Activities

Lists activities for a session.

curl -sS \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sessions/SESSION_ID/activities?pageSize=30"

Query Parameters:

Parameter	Type	Default	Description
`pageSize`	integer	50	Number of activities to return (1-100)
`pageToken`	string	-	Token from previous response for pagination

Response:

{
  "activities": [
    {
      "name": "sessions/123/activities/456",
      "createTime": "2026-01-15T10:31:00Z",
      "planGenerated": {
        "plan": "1. Analyze existing code\n2. Create test files\n3. Write tests..."
      }
    },
    {
      "name": "sessions/123/activities/457",
      "createTime": "2026-01-15T10:32:00Z",
      "progressUpdate": {
        "title": "Writing tests",
        "details": "Creating test file for auth module..."
      }
    }
  ],
  "nextPageToken": "..."
}

Activities may include artifacts with code changes:

{
  "artifacts": [
    {
      "changeSet": {
        "gitPatch": {
          "unidiffPatch": "diff --git a/...",
          "baseCommitId": "abc123",
          "suggestedCommitMessage": "Add unit tests for login"
        }
      }
    }
  ]
}

Get Activity

Retrieves a single activity by ID.

curl -sS \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sessions/SESSION_ID/activities/ACTIVITY_ID"

Script Reference

jules_api.sh

The scripts/jules_api.sh script provides a convenient wrapper for common API operations.

Usage:

# List sources
./scripts/jules_api.sh sources

# List sessions
./scripts/jules_api.sh sessions [--page-size N]

# List activities for a session
./scripts/jules_api.sh activities --session <id> [--page-size N]

# Send message to session
./scripts/jules_api.sh send-message --session <id> --prompt "..."

# Approve plan
./scripts/jules_api.sh approve-plan --session <id>

# Create new session
./scripts/jules_api.sh new-session \
  --source "sources/github/owner/repo" \
  --title "..." \
  --prompt "..." \
  [--branch main] \
  [--auto-pr] \
  [--no-plan-approval]

Flags:

Flag	Description
`--source`	Source name (format: `sources/github/owner/repo`)
`--title`	Session title
`--prompt`	Task description or message content
`--session`	Session ID
`--branch`	Starting branch (default: `main`)
`--auto-pr`	Enable automatic PR creation
`--require-plan-approval`	Require explicit plan approval (default)
`--no-plan-approval`	Skip plan approval (use for low-risk tasks only)
`--page-size`	Number of results to return

jules.js

The scripts/jules.js script wraps the Jules CLI for programmatic use.

Usage:

node scripts/jules.js version
node scripts/jules.js list-repos
node scripts/jules.js list-sessions
node scripts/jules.js new --repo owner/repo --task "Your task"
node scripts/jules.js pull --session SESSION_ID

Common Error Patterns

"Source not found" or "Repository not found"

Cause: Repository not connected or incorrect source name format.

Solution:

Run ./scripts/jules_api.sh sources to list available sources
Ensure you've installed the Jules GitHub app for this repo
Use the exact source name from the list (e.g., sources/github/octocat/Hello-World)

"Missing JULES_API_KEY"

Cause: API key not set in environment.

Solution:

export JULES_API_KEY="your-api-key"

Authentication Errors

Cause: Invalid or expired API key.

Solution:

Generate a new API key at https://jules.google.com/settings#api
Update the JULES_API_KEY environment variable
Note: You can have at most 3 API keys at a time

Session Stuck in AWAITING_PLAN_APPROVAL

Cause: Session was created with requirePlanApproval: true.

Solution:

./scripts/jules_api.sh approve-plan --session SESSION_ID

Task Fails with Vague Error

Cause: Vague prompts may produce unexpected results.

Solution:

Write clear, specific prompts
Break large tasks into smaller, focused tasks
Avoid prompts that require long-running commands (dev servers, watch scripts)

Large Files Skipped

Cause: Files exceeding 768,000 tokens may be skipped.

Solution:

Break down operations on very large files
Consider splitting large files before processing

Best Practices

Writing Effective Prompts

Be specific: Instead of "fix the bug", say "fix the null pointer exception in auth.js:45 when email is undefined"
Provide context: Mention relevant files, functions, or error messages
Keep tasks focused: One logical task per session

Monitoring Sessions

Poll session state to track progress
Check activities for detailed progress updates
Handle AWAITING_USER_FEEDBACK state by sending clarifying messages

Security

Never include secrets or credentials in prompts
Review generated PRs before merging
Use requirePlanApproval: true (recommended for all repos, especially production)
Only install the Jules GitHub app on repositories you intend to use with Jules — limit access scope
Treat JULES_API_KEY as a secret: store it securely, rotate it regularly, and never paste it into untrusted places

Performance

Use automationMode: AUTO_CREATE_PR for streamlined workflows
Only skip plan approval (requirePlanApproval: false) for routine, low-risk tasks in non-critical repos
Break complex tasks into smaller sessions

Extracting Results

When a session completes, retrieve the PR URL from outputs:

# Get session details
curl -sS \
  -H "x-goog-api-key: $JULES_API_KEY" \
  "https://jules.googleapis.com/v1alpha/sessions/SESSION_ID" \
  | jq '.outputs[].pullRequest.url'

Known Limitations

Alpha API: Specifications may change; API keys and definitions are experimental
No long-running commands: Jules cannot run npm run dev or similar watch scripts
Context size: Files > 768,000 tokens may be skipped
Prompt sensitivity: Vague prompts may produce unexpected results

References

When it activates

Automatically, when a task matches. Use when the user wants to delegate coding tasks to Jules programmatically. Requires JULES_API_KEY env var (obtain from https://jules.google.com/settings#api).

About this skill

Automatic

Coding 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/jules-and-lobster/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 2 files · scripts

Illustrative Want to see what leoyeai/jules-api 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

Jules REST API Skill

Quick Start

Overview

Before You Start

1. Get an API Key

2. Connect Your GitHub Repository

3. Verify Repository Access

Base URL & Authentication

Core Concepts

Resources

Session States

Activity Types

Workflows

Option 1: Session with Plan Approval and Auto-PR (Recommended)

Option 2: Fully Automated Session (No Plan Approval)

Option 3: Interactive Session

API Reference

Sources

List Sources

Get Source

Sessions

Create Session

List Sessions

Get Session

Send Message

Approve Plan

Delete Session

Activities

List Activities

Get Activity

Script Reference

jules_api.sh

jules.js

Common Error Patterns

"Source not found" or "Repository not found"

"Missing JULES_API_KEY"

Authentication Errors

Session Stuck in AWAITING_PLAN_APPROVAL

Task Fails with Vague Error

Large Files Skipped

Best Practices

Writing Effective Prompts

Monitoring Sessions

Security

Performance

Extracting Results

Known Limitations

References

When it activates

SkillSafety

Source

Related skills

More in the registry