Ready to supercharge your AI agents?

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

Change Verification · leoyeai | DecimalAI

DevOpsby leoyeai

Change Verification

Pre/post change verification with baseline capture, diff analysis, and rollback decision guidance across Cisco IOS-XE/NX-OS, Juniper JunOS, and Arista EOS. Structured around a single change event lifecycle — before, during, and after — with impact classification and rollback criteria.

Never made a case worse

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

35%91%of test cases passed +57 pts

Without skill8 of 23

With skill21 of 23

13 fixed8 passed either way2 still failing0 broke

Measured on gemini-3.6-flash8/6/2026v122 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskFor ticket CHG-1290 on Cisco IOS, we archived our pre-change config to flash:pre-change-CHG-1290-20250330.cfg. What exact Cisco CLI command performs a structured diff comparison between the archived pre-change baseline and the active running configuration?

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-change-verification
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-change-verification")
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-change-verification

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-change-verification/SKILL.md https://app.decimal.ai/s/leoyeai-change-verification/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-change-verification/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-change-verification

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-change-verification")
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-change-verification/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-change-verification/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-change-verification

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-change-verification")
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-change-verification/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-change-verification/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-change-verification

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-change-verification")
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-change-verification/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-change-verification/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-change-verification

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-change-verification")
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-change-verification/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-change-verification/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-change-verification

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-change-verification")
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-change-verification/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-change-verification/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-change-verification

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-change-verification")
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-change-verification/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-change-verification/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-change-verification

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-change-verification")
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-change-verification/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-change-verification

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-change-verification")
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-change-verification/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-change-verification/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-change-verification

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-change-verification")
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-change-verification/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-change-verification/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-change-verification

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-change-verification")
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-change-verification/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-change-verification/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-change-verification

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-change-verification")
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-change-verification/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-change-verification/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-change-verification

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-change-verification")
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-change-verification/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-change-verification/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-change-verification

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-change-verification/SKILL.md https://app.decimal.ai/s/leoyeai-change-verification/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-change-verification/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-change-verification/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-change-verification.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 8/6/2026
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

Change Verification

Event-driven change verification skill for structured change windows. Guides baseline capture before a change, provides change execution safety patterns, performs post-change diff analysis, and supports rollback decision-making when unexpected deviations are detected.

This skill covers a single change event lifecycle (before → during → after). For ongoing configuration drift detection and compliance auditing, use the config-management skill instead.

Commands are labeled [Cisco], [JunOS], or [EOS] where syntax diverges. Unlabeled statements apply to all three vendors.

Safety Note — Read-Write Operations: This skill includes procedures that modify device state during change execution and rollback phases. Steps that write to devices are marked with ⚠️ WRITE. Always confirm authorization, change ticket approval, and maintenance window status before executing write operations. Baseline capture and post-change verification steps are read-only and safe to run at any time.

When to Use

Planned maintenance window requiring structured pre/post verification
Configuration change (routing policy, ACLs, interface config) with rollback plan
Software upgrade or patch requiring before/after state comparison
Hardware replacement (linecard, SFP, PSU) with service validation
Circuit turn-up or decommission with adjacency and traffic verification
Emergency change requiring rapid baseline capture and rollback readiness
Post-change soak period with periodic re-verification against baselines

Prerequisites

SSH or console access to all devices in the change scope (read-only for baselines; enable/configure privilege for change execution and rollback)
Approved change ticket with documented scope, expected impact, and rollback plan including timing criteria
Pre-identified list of devices and interfaces in the change scope
Knowledge of expected state changes: which routes will move, which interfaces will bounce, which adjacencies will flap
Access to a file store (flash, SCP server, or local disk) for baseline archival
Contact information for escalation if rollback criteria are met
See references/checklist-templates.md for per-change-type prerequisites

Procedure

Follow these steps sequentially for each change event. Steps 1–2 are always read-only. Steps 3–4 include write operations. Steps 5–6 are analytical and drive the rollback decision.

Step 1: Pre-Change Baseline Capture

Capture device state snapshots before any changes. Store outputs with timestamps for post-change comparison.

Routing state:

[Cisco]

show ip route summary
show ip bgp summary
show ip ospf neighbor

[JunOS]

show route summary
show bgp summary
show ospf neighbor

[EOS]

show ip route summary
show ip bgp summary
show ip ospf neighbor

Interface and adjacency state:

All vendors — capture interface status, error counters, and neighbor tables:

[Cisco]

show interfaces summary
show cdp neighbors
show ip arp

[JunOS]

show interfaces terse
show lldp neighbors
show arp no-resolve

[EOS]

show interfaces status
show lldp neighbors
show ip arp

Configuration and hardware:

[Cisco]

show running-config
show environment all
show inventory

[JunOS]

show configuration
show chassis environment
show chassis hardware

[EOS]

show running-config
show environment all
show inventory

⚠️ WRITE — Archive baseline config to persistent storage:

[Cisco] copy running-config flash:pre-change-[ticket]-[date].cfg [JunOS] request system configuration save /var/tmp/pre-change-[ticket].conf [EOS] copy running-config flash:pre-change-[ticket]-[date].cfg

Record baseline metrics for comparison: total route count, BGP peer count (Established), OSPF neighbor count (Full), interface error counters, and hardware sensor readings.

Step 2: Change Scope Documentation

Before executing any changes, document:

Change description — what configuration lines are being added, modified, or removed
Expected impact — which peers will flap, which routes will shift, which interfaces will bounce, expected duration of disruption
Rollback trigger criteria — specific thresholds that mandate rollback (see Threshold Tables below)
Rollback procedure — exact commands to revert (see references/cli-reference.md for vendor-specific rollback commands)
Success criteria — what "done" looks like: all baselines restored, intended changes visible, no unexpected deviations
Soak period — how long to monitor after change before declaring success

Step 3: Change Execution

⚠️ WRITE — Apply changes using commit-confirm patterns when available.

[Cisco] — No native commit-confirm. Apply changes in config mode and immediately verify. For bulk changes, use configure replace with a prepared config file.

[JunOS] — Use commit confirmed [minutes] to auto-rollback if not confirmed within the timer window. Confirm with commit after verification.

configure
# ... apply changes ...
commit confirmed 5
# ... verify ...
commit

[EOS] — Use configure session for atomic staged changes. Review before committing.

configure session change-[ticket]
# ... apply changes ...
show session-config
commit

Staged rollout for multi-device changes: Apply to one device first, verify post-change state (Step 4), then proceed to remaining devices only after the first device passes all checks.

Step 4: Post-Change Verification

Re-capture all baseline metrics from Step 1 using identical commands. Perform a structured diff against pre-change baselines.

Key comparisons:

Metric	Compare Against	Expected Outcome
Route count	Pre-change summary	Within deviation threshold
BGP peers Established	Pre-change peer list	All peers restored (or changed per plan)
OSPF neighbors Full	Pre-change neighbor list	All adjacencies restored
Interface errors	Pre-change counters	No new sustained errors
Config diff	Archived pre-change config	Only intended lines changed

Config diff verification:

[Cisco]

show archive config differences flash:pre-change-[ticket]-[date].cfg system:running-config

[JunOS]

show | compare rollback 1

[EOS]

diff running-config flash:pre-change-[ticket]-[date].cfg

Review every line in the diff output. Classify each changed line as expected (directly part of the change plan) or unexpected (not in the change scope).

Step 5: Impact Assessment

Classify all deviations from baseline into categories:

Expected — Intended: Changes that are the direct goal of the change window (e.g., new BGP peer appearing, old ACL removed). No action needed.
Expected — Side Effect: Changes caused by the intended change but not the primary goal (e.g., route count increase because a new peer is now advertising). Verify they are benign.
Unexpected — Minor: Deviations not related to the change scope but low severity (e.g., a single interface counter increment). Investigate but do not necessarily roll back.
Unexpected — Critical: Deviations indicating collateral damage (e.g., adjacency loss on an unrelated interface, route withdrawal not in change scope). Evaluate rollback immediately.

If any deviation is classified as Unexpected — Critical, proceed directly to Step 6 rollback evaluation.

Step 6: Rollback Decision

Evaluate whether to accept the change or roll back using the criteria below.

Rollback if ANY of these conditions are true:

Service-affecting outage on interfaces/peers outside the change scope
Route count deviation exceeds threshold AND routes are not accounted for in the change plan
Adjacency loss persists beyond the expected convergence window
Hardware errors (PSU, fan, temperature) emerged that were not present in baseline
The change did not achieve its intended effect (success criteria from Step 2 not met)

Accept if ALL of these conditions are true:

All success criteria from Step 2 are met
Config diff contains only expected change lines
All baseline metrics are within acceptable deviation thresholds
No unexpected critical deviations detected
Soak period has elapsed without regression

⚠️ WRITE — If rolling back:

[Cisco] configure replace flash:pre-change-[ticket]-[date].cfg force [JunOS] rollback 1 then commit [EOS] configure replace flash:pre-change-[ticket]-[date].cfg

After rollback, re-run Step 4 post-change verification to confirm the device has returned to its pre-change state.

Threshold Tables

Acceptable Deviation Thresholds

Metric	Normal Deviation	Warning	Rollback Trigger
IPv4 route count	±2% of baseline	±5% of baseline	>10% or unplanned loss
IPv6 route count	±2% of baseline	±5% of baseline	>10% or unplanned loss
BGP Established peers	0 lost (unless planned)	1 lost (if in scope)	≥1 lost outside scope
OSPF Full adjacencies	0 lost (unless planned)	Flap then recover <2 min	Lost >2 min
Interface errors (new)	0 new CRC/input errors	<10 in first 5 min	Sustained >10/min
Interface flaps	0 (unless planned bounce)	1 flap on in-scope intf	Any flap outside scope

Rollback Timing Thresholds

Phase	Maximum Duration	Action if Exceeded
Change execution	Per change ticket	Pause and escalate
Post-change convergence	5 minutes	Begin rollback assessment
Adjacency re-establishment	2 minutes per peer	Escalate if critical peer
Route table stabilization	3 minutes	Check for route oscillation
Soak period (minor change)	15 minutes	Declare success or investigate
Soak period (major change)	60 minutes	Declare success or investigate
Rollback execution	5 minutes	Escalate to senior engineer

Decision Trees

Post-Change Diff Contains Unexpected Lines

Config diff shows unexpected changes
├── Lines are in sections RELATED to change scope
│   ├── Side effect of intended change (e.g., auto-generated route-map sequence)
│   │   └── Classify as Expected — Side Effect → Document and accept
│   └── Unintended consequence (e.g., wrong interface affected)
│       └── Classify as Unexpected — Critical → Evaluate rollback
└── Lines are in sections UNRELATED to change scope
    ├── Timestamps, counters, or cosmetic changes (e.g., "Last configuration change")
    │   └── Classify as Expected — Side Effect → Ignore
    └── Substantive config changes (e.g., ACL modified, route-map added)
        └── Classify as Unexpected — Critical → Immediate rollback

Adjacency Loss Detected Post-Change

Neighbor/peer no longer in expected state
├── Device IS in the change scope
│   ├── Interface was intentionally bounced per change plan
│   │   ├── Adjacency recovers within timing threshold
│   │   │   └── Expected — document recovery time
│   │   └── Adjacency does NOT recover within threshold
│   │       └── Investigate → Check interface state, cable, peer config
│   └── Interface was NOT intentionally bounced
│       └── Unexpected — Critical → Check for config error → Rollback if unresolved
└── Device is NOT in the change scope
    ├── Peer is on a device that IS in scope (far-end impact)
    │   └── Expected side effect → Verify peer recovers within threshold
    └── Peer is on a device NOT in scope (unrelated)
        └── Unexpected — Critical → Unrelated failure, separate investigation

Route Count Deviation Outside Normal Threshold

Route count differs from baseline beyond ±2%
├── Change plan includes prefix addition or removal
│   ├── Deviation direction matches plan (added routes = count increase)
│   │   └── Expected — verify exact prefix matches plan
│   └── Deviation direction opposes plan (planned addition but count decreased)
│       └── Unexpected — Critical → Check BGP/OSPF process, peer state
├── Change plan does NOT include routing changes
│   ├── Deviation is <5% and routes are from in-scope device peers
│   │   └── Warning — likely convergence artifact → Monitor for 3 min
│   └── Deviation is >5% OR routes from out-of-scope sources
│       └── Unexpected — Critical → Evaluate rollback
└── Route oscillation detected (count fluctuating)
    └── Unexpected — Critical → Routing loop or flapping → Immediate rollback

Report Template

# Change Verification Report — [Ticket ID]

## Change Summary
- **Ticket:** [ID]
- **Date/Time:** [Start] — [End]
- **Devices:** [list]
- **Change Type:** [routing | switching | security | upgrade | other]
- **Executed By:** [name/team]

## Pre-Change Baseline
- Route count (IPv4/IPv6): [count]
- BGP peers Established: [count]
- OSPF adjacencies Full: [count]
- Interface errors (notable): [any]
- Config archived to: [location]

## Change Execution
- Method: [manual | commit-confirm | session | replace]
- Duration: [minutes]
- Issues during execution: [none | description]

## Post-Change Verification
- Route count (IPv4/IPv6): [count] (Δ [change])
- BGP peers Established: [count] (Δ [change])
- OSPF adjacencies Full: [count] (Δ [change])
- Interface errors (new): [count]
- Config diff lines: [expected: N, unexpected: N]

## Impact Assessment
- Expected — Intended: [list]
- Expected — Side Effect: [list]
- Unexpected — Minor: [list or none]
- Unexpected — Critical: [list or none]

## Decision
- **Result:** [ACCEPTED | ROLLED BACK | ESCALATED]
- **Rationale:** [reason]
- **Soak period:** [duration, outcome]

## Action Items
- [ ] [any follow-up tasks]

Troubleshooting

Baseline capture commands fail or return incomplete output

Verify SSH session stability — long command outputs may be truncated by terminal buffer limits. Use terminal length 0 [Cisco/EOS] or set cli screen-length 0 [JunOS] before capture.
Check device CPU — high CPU may cause CLI timeouts. Run show processes cpu [Cisco] / show system processes extensive [JunOS] / show processes top [EOS] to verify.
If archival to remote storage fails, save to local flash as fallback and note the location for later retrieval.

Config diff shows excessive noise

Filter out timestamp and comment lines that change on every config display (e.g., ! Last configuration change at ...).
On [JunOS], show | compare rollback 1 gives clean structured diffs. On [Cisco], show archive config differences may include line-order differences that are not real changes — focus on substantive config lines.
Use references/checklist-templates.md checklists to focus verification on change-relevant sections rather than full config comparison.

Adjacency does not recover after expected bounce

Check interface state: show interfaces [intf] — look for down/down vs up/down to distinguish physical vs protocol issues.
Verify the peer device accepted the change — a mismatched configuration on both sides of a link (e.g., mismatched OSPF area, BGP ASN) will prevent adjacency formation.
Check for hold-timer expiry: OSPF default dead interval is 40s; BGP default hold time is 180s. Wait at least one full timer cycle before escalating.

Rollback command fails or produces unexpected state

[Cisco] configure replace requires the IOS archive feature to be enabled. If unavailable, manually reverse the config changes line by line.
[JunOS] rollback N may fail if the commit history has been cleared or the device has rebooted since the baseline commit. Use show system commit to verify available rollback points.
[EOS] configure replace requires the replacement file to be a complete config, not a partial fragment. Verify the archived file is a full show running-config capture.
After any rollback, re-run the full post-change verification (Step 4) to confirm the device has returned to its pre-change state.

Change window time exceeded before verification completes

Prioritize critical services: check routing adjacencies and interface states first, defer detailed config diff analysis to after the window if services are healthy.
If the soak period must be shortened, document the reduced observation window and schedule a follow-up verification at the next opportunity.
Escalate if service impact is detected and the change window has closed — do not delay rollback due to window constraints if there is active service degradation.

About this skill

Automatic

DevOps & SRE pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 10/22/2026

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/change-verification/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/2/2026Version v1Bundled 2 files

Illustrative Want to see what leoyeai/change-verification 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

Change Verification

When to Use

Prerequisites

Procedure

Step 1: Pre-Change Baseline Capture

Step 2: Change Scope Documentation

Step 3: Change Execution

Step 4: Post-Change Verification

Step 5: Impact Assessment

Step 6: Rollback Decision

Threshold Tables

Acceptable Deviation Thresholds

Rollback Timing Thresholds

Decision Trees

Post-Change Diff Contains Unexpected Lines

Adjacency Loss Detected Post-Change

Route Count Deviation Outside Normal Threshold

Report Template

Troubleshooting

Baseline capture commands fail or return incomplete output

Config diff shows excessive noise

Adjacency does not recover after expected bounce

Rollback command fails or produces unexpected state

Change window time exceeded before verification completes

SkillSafety

Source

Related skills

More in the registry