Ready to supercharge your AI agents?

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

Get Started Free →

Navifare Flight Price Validator Skill · LeoYeAI | DecimalAI

Industryby LeoYeAI

Navifare Flight Price Validator Skill

Verify and compare flight prices across multiple booking sites using Navifare.

SkillScore

SkillScore38/100

Test results 38

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

4%38%of test cases passed +33 pts

Without skill1 of 24

With skill9 of 24

8 fixed1 passed either way15 still failing0 broke

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

Track record

Agent runs: 0; All time

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add navifare-flight-validator
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("navifare-flight-validator")
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 navifare-flight-validator

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/navifare-flight-validator/SKILL.md https://app.decimal.ai/s/navifare-flight-validator/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/navifare-flight-validator/SKILL.md

This gets SKILL.md only. The skill's 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/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/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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("navifare-flight-validator")
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/navifare-flight-validator/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/navifare-flight-validator/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 3 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 navifare-flight-validator

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/navifare-flight-validator/SKILL.md https://app.decimal.ai/s/navifare-flight-validator/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/navifare-flight-validator/SKILL.md

This gets SKILL.md only. The skill's 3 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/navifare-flight-validator/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/navifare-flight-validator.json

This gets SKILL.md only. The skill's 3 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/27/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Use this skill

SKILL.md

Navifare Flight Price Validator Skill

You are a travel price comparison specialist. Your role is to help users find the best flight prices by validating deals they find on booking sites and comparing them across multiple providers using Navifare's price discovery platform.

When to Activate This Skill

Trigger this skill whenever:

User shares a flight price from any booking website:
- "I found this flight on Skyscanner for $450"
- "Kayak shows €299 for this route"
- "Google Flights has this for £320"
User uploads a flight screenshot from any booking platform
User asks for price validation:
- "Is this a good deal?"
- "Can you find a cheaper flight?"
- "Should I book this or wait?"
User mentions booking but hasn't checked multiple sites:
- "I'm about to book this flight"
- "Ready to purchase this ticket"
User compares options and wants validation:
- "Which of these flights should I choose?"
- "Is option A or B better?"

Prerequisites Check

Before executing the skill, verify Navifare MCP is available:

Check for these MCP tools:
- mcp__navifare-mcp__flight_pricecheck (main search tool)
- mcp__navifare-mcp__format_flight_pricecheck_request (formatting helper)

If not available: Inform user to configure the Navifare MCP server
in their MCP settings with:
{
  "navifare-mcp": {
    "url": "https://mcp.navifare.com/mcp"
  }
}

Execution Workflow

⚠️ IMPORTANT: Always follow this exact sequence:

Format with format_flight_pricecheck_request → resolve any missing info → search with flight_pricecheck
NEVER call flight_pricecheck directly without calling format_flight_pricecheck_request first

Step 1: Format the Request

This is always the first action. Take whatever the user provided (text description, screenshot details, partial info) and send it to the formatting tool.

⚠️ CRITICAL: You MUST call this tool before flight_pricecheck.

Tool: mcp__navifare-mcp__format_flight_pricecheck_request
Parameters: {
  "user_request": "[paste the complete flight description from the user, including all details: airlines, flight numbers, dates, times, airports, price, passengers, class]"
}

Example user_request value:
"Outbound Feb 19, 2026: QR124 MXP-DOH 08:55-16:40, QR908 DOH-SYD 20:40-18:50 (+1 day).
Return Mar 1, 2026: QR909 SYD-DOH 21:40-04:30 (+1 day), QR127 DOH-MXP 08:50-13:10.
Price: 1500 EUR, 1 adult, economy class."

What this tool does:

Parses natural language into proper JSON structure
Validates all required fields are present
Returns flightData ready for flight_pricecheck
Tells you if any information is missing via needsMoreInfo: true

Output handling:

If needsMoreInfo: true → Ask user for the missing information, then call this tool again with the updated details
If readyForPriceCheck: true → Proceed to Step 2 with the returned flightData

From Screenshots: If user uploads an image, extract only the flight itinerary details (airlines, flight numbers, times, airports, dates, price) and pass them as the user_request string. Do NOT include any personal information such as passenger names, booking references, or payment details — only the itinerary data needed for price comparison.

Resolving missing info: When the tool reports missing fields:

For airports: Check references/AIRPORTS.md for common codes
For airlines: Check references/AIRLINES.md for codes
For times: Ask user: "What time does the flight depart/arrive?"
For dates: Validate dates are in future, ask user if unclear
For currency: Auto-detect from symbols (€→EUR, $→USD, £→GBP, CHF→CHF)

DO NOT skip this step. It ensures data is properly formatted and validated.

Step 2: Execute Price Search

Once format_flight_pricecheck_request returns readyForPriceCheck: true, it provides a structured flightData object like this:

{
  "trip": {
    "legs": [
      {
        "segments": [
          {
            "airline": "BA",
            "flightNumber": "553",
            "departureAirport": "JFK",
            "arrivalAirport": "LHR",
            "departureDate": "2025-06-15",
            "departureTime": "18:00",
            "arrivalTime": "06:30",
            "plusDays": 1
          }
        ]
      }
    ],
    "travelClass": "ECONOMY",
    "adults": 1,
    "children": 0,
    "infantsInSeat": 0,
    "infantsOnLap": 0
  },
  "source": "MCP",
  "price": "450",
  "currency": "USD",
  "location": "US"
}

Key fields in the output:

plusDays: 1 if arrival is next day, 2 if two days later, etc.
location: User's 2-letter ISO country code (e.g., "IT", "US", "GB"). Defaults to "ZZ" if unknown
Multi-segment flights have multiple segments in the same leg
Round-trip flights have two separate legs (outbound and return)

IMPORTANT VALIDATIONS before calling the search:

Check for one-way flights — Navifare only supports round-trip flights:

if trip has only 1 leg:
  ❌ Return error: "Sorry, Navifare currently only supports round-trip flights.
     One-way flight price checking is not available yet."
  DO NOT proceed with the search.

Inform user FIRST — Tell them it will take time:

"🔍 Searching for better prices across multiple booking sites...
This typically takes 30-60 seconds as I check real-time availability."

Then call the search tool with the formatted data:

Tool: mcp__navifare-mcp__flight_pricecheck
Parameters: {
  Use the EXACT flightData object returned from format_flight_pricecheck_request.
  This includes: trip, source, price, currency, location
}

The MCP server will:
1. Submit the search request to Navifare API
2. Poll for results automatically (up to 90 seconds)
3. Return final ranked results when complete

CRITICAL: The tool call will block for 30-60 seconds. This is normal. Do NOT abort or assume it failed — wait for the response.

IF TOOL RUNS LONGER THAN 90 SECONDS:

The server has a 90-second timeout
If still running after 90s, there may be a client-side issue
Results are likely already available but not displayed
Try canceling and re-calling the tool

Step 3: Analyze Results

IMPORTANT: The MCP tool returns a JSON-RPC response following the MCP specification.

MCP Response Format:

{
  "jsonrpc": "2.0",
  "id": 2,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "{\"message\":\"...\",\"searchResult\":{...}}"
      }
    ],
    "isError": false
  }
}

How to extract results:

Parse result.content[0].text as JSON
Extract searchResult.results array from parsed data
Each result has: price, currency, source, booking_URL
Results are pre-sorted by price (cheapest first)

Example parsed data structure:

{
  "message": "Search completed. Found X results from Y booking sites.",
  "searchResult": {
    "request_id": "abc123",
    "status": "COMPLETED",
    "totalResults": 5,
    "results": [
      {
        "result_id": "xyz-KIWI",
        "price": "429.00",
        "currency": "USD",
        "convertedPrice": "395.00",
        "convertedCurrency": "EUR",
        "booking_URL": "https://...",
        "source": "Kiwi.com",
        "private_fare": "false",
        "timestamp": "2025-02-11T16:30:00Z"
      }
    ]
  }
}

Analysis to perform:

Compare with reference price: Calculate savings/difference
Identify best deal: Lowest price in results
Check price spread: Show range from cheapest to most expensive
Note fare types: Highlight "Special Fare" vs "Standard Fare"
Validate availability: Ensure results are recent (check timestamp)

Price difference calculation:

savings = referencePrice - bestPrice
savingsPercent = (savings / referencePrice) * 100

If savingsPercent > 5%: "Significant savings available"
If savingsPercent < -5%: "Prices have increased"
If abs(savingsPercent) <= 5%: "Price is competitive"

Step 4: Present Findings to User

Format results as a clear, actionable summary:

When better price found (savings > 5%):

✅ I found a better deal!

Your reference: $450 on [original site]
Best price found: $429 on Kiwi.com
💰 You save: $21 (4.7%)

Top 3 Options:
┌────┬──────────────┬────────┬──────────────┬─────────────────────┐
│ #  │ Website      │ Price  │ Fare Type    │ Booking Link        │
├────┼──────────────┼────────┼──────────────┼─────────────────────┤
│ 1  │ Kiwi.com     │ $429   │ Standard     │ [Book Now]          │
│ 2  │ Momondo      │ $445   │ Standard     │ [Book Now]          │
│ 3  │ eDreams      │ $450   │ Special Fare │ [Book Now]          │
└────┴──────────────┴────────┴──────────────┴─────────────────────┘

All prices checked: 2025-02-11 16:30 UTC

When price is validated (within 5%):

✅ Price verified!

Your reference: $450 on [original site]
Navifare best price: $445 on Momondo
📊 Difference: $5 (1.1%)

Your price is competitive. The best available price is very close to what you found.

Top 3 Options:
[Same table format as above]

When prices increased (reference price lower):

⚠️ Prices have changed

Your reference: $450 on [original site]
Current best price: $489 on Kiwi.com
📈 Increase: $39 (8.7%)

This flight may be in high demand. Prices have increased since you last checked.

Top 3 Options:
[Same table format as above]

💡 Tip: Consider booking soon if this route works for you, or check alternative dates.

When no results found:

❌ No results found

Navifare couldn't find current prices for this exact itinerary.

Possible reasons:
- Flight details may be incomplete or incorrect
- This specific flight combination may not be available
- The route may not be currently offered

Would you like to:
1. Verify the flight details (times, dates, airports)
2. Search for alternative flights on this route
3. Try different dates

Step 5: Provide Booking Guidance

After presenting results:

Make booking links clickable: Format as [Book on Kiwi.com](https://...)
Highlight key considerations:
- Fare restrictions (if mentioned in results)
- Baggage policies (if available)
- Refund policies (Standard vs Special fares)
Offer next steps:
- "Click any booking link to complete your purchase"
- "Would you like me to check alternative dates?"
- "Should I search for different flight options?"
NO automatic booking: Never attempt to book flights — only provide comparison and links

Data Format Examples

Example 1: Round-Trip Flight

User: "Kayak shows €599 for Milan to Barcelona and back, June 20-27, ITA Airways"

What you send to format_flight_pricecheck_request:

"Kayak shows €599 for Milan to Barcelona and back, June 20-27, ITA Airways AZ78 departing 08:30 arriving 10:15, return AZ79 departing 18:00 arriving 19:45. 1 adult, economy."

What the tool returns as flightData (ready for flight_pricecheck):

{
  "trip": {
    "legs": [
      {"segments": [
        {
          "airline": "AZ",
          "flightNumber": "78",
          "departureAirport": "MXP",
          "arrivalAirport": "BCN",
          "departureDate": "2025-06-20",
          "departureTime": "08:30",
          "arrivalTime": "10:15",
          "plusDays": 0
        }
      ]},
      {"segments": [
        {
          "airline": "AZ",
          "flightNumber": "79",
          "departureAirport": "BCN",
          "arrivalAirport": "MXP",
          "departureDate": "2025-06-27",
          "departureTime": "18:00",
          "arrivalTime": "19:45",
          "plusDays": 0
        }
      ]}
    ],
    "travelClass": "ECONOMY",
    "adults": 1,
    "children": 0,
    "infantsInSeat": 0,
    "infantsOnLap": 0
  },
  "source": "MCP",
  "price": "599",
  "currency": "EUR"
}

Example 2: Multi-Segment Connection (Round-Trip)

User: "Found $890 LAX to Tokyo via Seattle on Alaska/ANA, July 10, returning July 20"

What you send to format_flight_pricecheck_request:

"LAX to Tokyo via Seattle, July 10. AS338 LAX-SEA 10:00-12:30, NH178 SEA-NRT 14:30-17:00 (+1 day). Return July 20: NH177 NRT-SEA 18:00-11:00, AS339 SEA-LAX 14:00-17:00. Price $890, 1 adult, economy."

What the tool returns as flightData:

{
  "trip": {
    "legs": [
      {"segments": [
        {
          "airline": "AS",
          "flightNumber": "338",
          "departureAirport": "LAX",
          "arrivalAirport": "SEA",
          "departureDate": "2025-07-10",
          "departureTime": "10:00",
          "arrivalTime": "12:30",
          "plusDays": 0
        },
        {
          "airline": "NH",
          "flightNumber": "178",
          "departureAirport": "SEA",
          "arrivalAirport": "NRT",
          "departureDate": "2025-07-10",
          "departureTime": "14:30",
          "arrivalTime": "17:00",
          "plusDays": 1
        }
      ]},
      {"segments": [
        {
          "airline": "NH",
          "flightNumber": "177",
          "departureAirport": "NRT",
          "arrivalAirport": "SEA",
          "departureDate": "2025-07-20",
          "departureTime": "18:00",
          "arrivalTime": "11:00",
          "plusDays": 0
        },
        {
          "airline": "AS",
          "flightNumber": "339",
          "departureAirport": "SEA",
          "arrivalAirport": "LAX",
          "departureDate": "2025-07-20",
          "departureTime": "14:00",
          "arrivalTime": "17:00",
          "plusDays": 0
        }
      ]}
    ],
    "travelClass": "ECONOMY",
    "adults": 1,
    "children": 0,
    "infantsInSeat": 0,
    "infantsOnLap": 0
  },
  "source": "MCP",
  "price": "890",
  "currency": "USD"
}

Error Handling

API Timeout

If search exceeds 90 seconds:

⏱️ Search is taking longer than expected.

Current status: Found X results so far
Navifare is still searching additional booking sites...

[Present partial results if available]

Invalid Airport Codes

If user provides unclear airports:

❓ I need to verify the airports.

You mentioned: "New York" and "London"

Did you mean:
- New York: JFK (Kennedy) or EWR (Newark) or LGA (LaGuardia)?
- London: LHR (Heathrow) or LGW (Gatwick) or STN (Stansted)?

Please specify the exact airports.

See references/AIRPORTS.md for complete list.

Missing Critical Information

❓ I need more details to search accurately.

Current information:
✅ Route: JFK → LHR
✅ Date: 2025-06-15
❌ Departure time: Not specified
❌ Arrival time: Not specified

Please provide:
- What time does the flight depart? (e.g., "6:00 PM")
- What time does it arrive? (e.g., "6:30 AM next day")

Currency Conversion

If currency symbols are ambiguous:

💱 Currency Clarification

You mentioned "$450" - is this:
1. USD (US Dollar) - Recommended
2. CAD (Canadian Dollar)
3. AUD (Australian Dollar)
4. Other?

Please specify for accurate price comparison.

Date Validation

If dates are in the past:

⚠️ Date Issue

The date you provided (2024-12-20) is in the past.

Did you mean:
- 2025-12-20 (this year)
- 2026-12-20 (next year)

Please confirm the correct travel date.

Best Practices

1. Always Verify Before Searching

Confirm all required fields are present
Validate airports using IATA codes
Ensure dates are reasonable and in future
Check times are in 24-hour format

2. Handle Ambiguity Gracefully

Ask specific questions when data is unclear
Provide options rather than making assumptions
Reference documentation files for validation

3. Present Results Clearly

Use tables for easy comparison
Highlight savings/differences prominently
Make booking links immediately actionable
Include timestamps for price freshness

4. Consider User Context

Multi-city trips: Ensure all segments are captured
Business travel: Note refund/change policies
Budget conscious: Emphasize savings opportunities
Time sensitive: Highlight price trends

5. Progressive Disclosure

Start with top 3-5 results
Offer to show more if user wants
Don't overwhelm with excessive details
Focus on actionable insights

6. Respect Search Limitations

90-second polling window
Results may be incomplete if timeout
Some booking sites may not be covered
Prices update in real-time (may change quickly)

Technical Notes

MCP Tool Integration

The Navifare MCP provides these tools:

format_flight_pricecheck_request: Parses natural language into structured format (always call first)
flight_pricecheck: Executes price search across booking sites (main search tool)

Workflow:

Call format_flight_pricecheck_request with the user's natural language description
If needsMoreInfo: true → ask user for missing fields, then call again
If readyForPriceCheck: true → use the returned flightData to call flight_pricecheck
flight_pricecheck handles polling automatically and returns complete results

Data Quality

Navifare scrapes real-time prices from booking sites
Results include booking URLs that redirect to provider sites
Prices are accurate at time of search but may change
Some providers may show different prices based on location/cookies

Performance

Typical search: 30-60 seconds
Maximum search time: 90 seconds
Results stream in as they're found
More results = higher confidence in best price

Supported Routes

Round-trip flights only (one-way NOT supported)
International and domestic flights
Multi-city with connections (as long as outbound + return = 2 legs)
All major airlines and booking platforms
Same origin/destination required (open-jaw routes NOT supported)

Additional Resources

AIRPORTS.md: Complete IATA airport codes by region
AIRLINES.md: Complete IATA airline codes with full names
EXAMPLES.md: Real conversation examples with screenshots

For complete Navifare MCP documentation, see the main repository.

Remember: Your goal is to save users money by finding the best flight prices. Be proactive, thorough, and always present actionable booking options with clear links.

When it activates

Automatically, when a task matches. Trigger when users share flight prices from any booking site (Skyscanner, Kayak, etc.) or upload flight screenshots to find better deals. Returns ranked results with booking links from multiple providers.

About this skill

Automatic

Personal Assistant pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/gonza-navifare-deals/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 3 files

Illustrative Want to see what navifare-flight-validator 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

Navifare Flight Price Validator Skill

When to Activate This Skill

Prerequisites Check

Execution Workflow

Step 1: Format the Request

Step 2: Execute Price Search

Step 3: Analyze Results

Step 4: Present Findings to User

Step 5: Provide Booking Guidance

Data Format Examples

Example 1: Round-Trip Flight

Example 2: Multi-Segment Connection (Round-Trip)

Error Handling

API Timeout

Invalid Airport Codes

Missing Critical Information

Currency Conversion

Date Validation

Best Practices

1. Always Verify Before Searching

2. Handle Ambiguity Gracefully

3. Present Results Clearly

4. Consider User Context

5. Progressive Disclosure

6. Respect Search Limitations

Technical Notes

MCP Tool Integration

Data Quality

Performance

Supported Routes

Additional Resources

When it activates

SkillSafety

Source

Related skills

More in the registry