Ready to supercharge your AI agents?

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

Comment-to-DM Funnel — Upload-Post API · leoyeai | DecimalAI

Marketingby leoyeai

Comment-to-DM Funnel — Upload-Post API

Automate Instagram comment-to-DM funnels using the Upload-Post API. Auto-reply to Instagram comments with private DMs, build lead capture funnels, and set up keyword-triggered DM automation (ManyChat alternative). Send automated direct messages to commenters on Instagram Reels and posts. Features 24/7 comment monitoring, smart AI semantic filtering, and scalable Instagram DM outreach campaigns via the official Meta Private Replies API. Perfect for comment automation, auto DMs, and lead magnets.

Never made a case worse

SkillScore

SkillScore96/100

Test results 96

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

28%96%of test cases passed +68 pts

Without skill7 of 25

With skill24 of 25

17 fixed7 passed either way1 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhat authentication header format must be sent with every request to api.upload-post.com?

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-comment-funnel
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-comment-funnel")
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-comment-funnel

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-comment-funnel/SKILL.md https://app.decimal.ai/s/leoyeai-comment-funnel/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-comment-funnel/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/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-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/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-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel")
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-comment-funnel/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-comment-funnel/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 1 other file is 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-comment-funnel

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-comment-funnel/SKILL.md https://app.decimal.ai/s/leoyeai-comment-funnel/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-comment-funnel/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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-comment-funnel/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-comment-funnel.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Use this skill

SKILL.md

Comment-to-DM Funnel — Upload-Post API

Turn Instagram comments into conversations. This skill lets you monitor comments on a post, detect trigger keywords (semantically, not just exact match), and send personalized private DMs to each commenter automatically.

This is the same mechanism ManyChat, Inro, and every major DM automation tool uses — the official Instagram Private Replies API. Fully compliant with Meta's terms.

Documentation

Full API docs: https://docs.upload-post.com
LLM-friendly reference: https://docs.upload-post.com/llm.txt

Authentication

All requests require an API key:

Authorization: Apikey YOUR_API_KEY

Base URL: https://api.upload-post.com/api

The user parameter is the profile name (not username) from the Upload-Post dashboard.

How the Funnel Works

The typical flow a creator wants:

They post a Reel saying "Comment GUIDE to get my free PDF"
People comment "GUIDE", "quiero la guía", "send me the guide", etc.
Each commenter receives a personalized DM with the link
If someone replies to the DM, the conversation continues
The creator gets a summary of how many DMs were sent

Your job as an agent is to orchestrate this. There are two modes:

One-shot: Scan comments right now and send DMs to everyone who already commented. Good for processing a backlog.
Persistent monitor: Start a background monitor that checks for new comments every X minutes and auto-sends DMs 24/7. This is the "set it and forget it" mode — like ManyChat.

Choose based on what the user asks. If they say "set up a funnel" or "activate monitoring", use persistent. If they say "check comments" or "send DMs to whoever commented", use one-shot.

Endpoints

Persistent Monitor Endpoints

These start a background process on Upload-Post's servers that monitors comments and sends DMs automatically. No need for the agent to stay running.

Start Monitor

curl -X POST "https://api.upload-post.com/api/uploadposts/autodms/start" \
  -H "Authorization: Apikey YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "post_url": "https://www.instagram.com/p/ABC123/",
    "reply_message": "Hey! Here is your guide: https://example.com/guide",
    "profile_username": "PROFILE",
    "monitoring_interval": 15,
    "trigger_keywords": ["guide", "link"]
  }'

Parameters:

post_url (required): The Instagram post URL to monitor
reply_message (required): The DM message to send to matching commenters
profile_username (required): Upload-Post profile name with Instagram connected
monitoring_interval (optional): Minutes between checks. Default: 15. Minimum: 15 (values below 15 are auto-clamped)
trigger_keywords (optional): Array of keywords to filter comments. Only comments containing at least one keyword receive a DM. Case-insensitive and accent-insensitive ("guía" matches "guia"). If omitted, ALL commenters receive a DM.

Returns a monitor_id you'll need for managing the monitor.

Limits:

Maximum 2 new monitors per profile per day
No duplicate monitors on the same post URL
Monitors auto-stop after 15 days
Daily DM limits apply per plan (free: 10 DMs/day, paid: 500 DMs/day). When the limit is reached, the monitor pauses and resumes the next day.

Important: This monitor sends a fixed reply_message — it does not do semantic filtering or personalization. If trigger_keywords is set, it only replies to comments containing those words (case and accent insensitive). If omitted, it replies to ALL commenters. For smart semantic filtering, use one-shot mode instead.

Check Monitor Status

curl "https://api.upload-post.com/api/uploadposts/autodms/status" \
  -H "Authorization: Apikey YOUR_KEY"

Returns all active monitors with their status: running, paused, or stopped.

Get Monitor Logs

curl "https://api.upload-post.com/api/uploadposts/autodms/logs?monitor_id=MONITOR_ID" \
  -H "Authorization: Apikey YOUR_KEY"

Returns activity logs: when the monitor started, how many DMs sent, any errors.

Pause / Resume / Stop / Delete Monitor

# Pause (keeps config, stops checking)
curl -X POST "https://api.upload-post.com/api/uploadposts/autodms/pause" \
  -H "Authorization: Apikey YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"monitor_id": "MONITOR_ID"}'

# Resume a paused monitor
curl -X POST "https://api.upload-post.com/api/uploadposts/autodms/resume" \
  -H "Authorization: Apikey YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"monitor_id": "MONITOR_ID"}'

# Stop (deactivates)
curl -X POST "https://api.upload-post.com/api/uploadposts/autodms/stop" \
  -H "Authorization: Apikey YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"monitor_id": "MONITOR_ID"}'

# Delete (permanent)
curl -X POST "https://api.upload-post.com/api/uploadposts/autodms/delete" \
  -H "Authorization: Apikey YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"monitor_id": "MONITOR_ID"}'

One-Shot Endpoints

These are for scanning comments on-demand and sending DMs with AI-powered semantic matching and personalization.

1. Get Recent Posts

Find the post to monitor.

curl "https://api.upload-post.com/api/uploadposts/media?platform=instagram&user=PROFILE" \
  -H "Authorization: Apikey YOUR_KEY"

Returns an array of recent posts with id, caption, permalink, timestamp, and media_type. Use the id field as post_id in subsequent calls.

2. Read Comments

curl "https://api.upload-post.com/api/uploadposts/comments?platform=instagram&user=PROFILE&post_id=POST_ID" \
  -H "Authorization: Apikey YOUR_KEY"

You can also use post_url instead of post_id:

curl "https://api.upload-post.com/api/uploadposts/comments?platform=instagram&user=PROFILE&post_url=https://www.instagram.com/p/ABC123/" \
  -H "Authorization: Apikey YOUR_KEY"

Rate limit: Once per 10 minutes per post. Plan your polling accordingly — don't call this in a tight loop.

Each comment includes id, text, username, and timestamp.

3. Send Private Reply (the DM)

This is the core action. It sends a DM to the person who wrote the comment, using Meta's official Private Replies API.

curl -X POST "https://api.upload-post.com/api/uploadposts/comments/reply" \
  -H "Authorization: Apikey YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "platform": "instagram",
    "user": "PROFILE",
    "comment_id": "COMMENT_ID",
    "message": "Hey! Here is your guide: https://example.com/guide"
  }'

Constraints you must respect:

One reply per comment — if you already replied to a comment, the API will reject a second attempt
The comment must be less than 7 days old
The post must belong to the authenticated account
Daily DM limits apply (varies by plan)

4. List DM Conversations

Check for replies to your DMs.

curl "https://api.upload-post.com/api/uploadposts/dms/conversations?platform=instagram&user=PROFILE" \
  -H "Authorization: Apikey YOUR_KEY"

Returns conversation threads with participant_id, messages, and metadata.

5. Send Follow-Up DM

Continue a conversation with someone who replied.

curl -X POST "https://api.upload-post.com/api/uploadposts/dms/send" \
  -H "Authorization: Apikey YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "platform": "instagram",
    "user": "PROFILE",
    "recipient_id": "USER_ID",
    "message": "Glad you liked it! Let me know if you have questions."
  }'

24-hour window: You can only send follow-up DMs within 24 hours of the user's last reply. After that, the window closes and you cannot message them until they message you again.

Building the Funnel — Step by Step

When the user asks you to set up a comment funnel, follow these steps:

Step 1: Gather Requirements

Ask the user (if not already provided):

API key? (needed for all requests)
Profile name? (the user parameter — this is the Upload-Post profile name, not their Instagram username. If they don't know it, call GET /uploadposts/me to validate the key. If they have no profiles or no Instagram connected, direct them to https://app.upload-post.com/manage-users to create a profile and connect their Instagram Business account first)
Which post? (URL or they can say "my latest post")
What keywords trigger the DM? (e.g., "GUIDE", "INFO", "LINK")
What message to send? (the DM content)
Persistent or one-shot? (do they want 24/7 monitoring or a one-time scan?)

Step 2: Find the Post

Call GET /uploadposts/media to list recent posts. Match by URL, caption content, or just pick the latest. Confirm with the user which post to monitor.

Path A: Persistent Monitor (24/7)

Use this when the user wants continuous monitoring ("set up a funnel", "activate it", "keep it running").

Call POST /uploadposts/autodms/start with the post URL, reply message, profile, and interval
Save the returned monitor_id and tell the user
Confirm it's running with GET /uploadposts/autodms/status
Tell the user how to check results: "Ask me anytime to check the funnel status or logs"

The backend handles everything from here — checking comments, sending DMs, avoiding duplicates, respecting rate limits. The agent doesn't need to stay running.

To check on it later:

GET /uploadposts/autodms/status → is it running?
GET /uploadposts/autodms/logs?monitor_id=X → how many DMs sent?

To manage it:

POST /uploadposts/autodms/pause → pause without losing config
POST /uploadposts/autodms/resume → resume after pause
POST /uploadposts/autodms/stop → deactivate
POST /uploadposts/autodms/delete → remove permanently

Trade-off: The persistent monitor sends the same fixed message — no personalization per commenter. Use trigger_keywords to filter so only relevant comments get a DM. Without keywords, it replies to every new comment.

Path B: One-Shot with AI (Smart Filtering)

Use this when the user wants intelligent processing ("check my comments", "DM the ones who asked for the guide", or when the post gets mixed comments — some requesting, some just engaging).

Scan Comments

Call GET /uploadposts/comments with the post ID.

For each comment, decide if it matches the trigger. Use semantic matching, not just exact string comparison:

Comment	Trigger: "GUIDE"	Match?
"GUIDE"	Exact match	Yes
"guide please"	Contains keyword	Yes
"I want the guide!"	Semantic intent	Yes
"can you send me the guide?"	Semantic intent	Yes
"guía"	Translation	Yes
"great post!"	No intent	No
"nice guide on the topic"	Ambiguous — talking about the content, not requesting	No

The key question: is this person requesting the thing the creator offered? Use judgment, not regex.

Send DMs

For each matching comment that hasn't been replied to yet:

Personalize the message. Don't send identical copy-paste to everyone. Use their name or reference their comment:
- Generic: "Here's your guide: [link]"
- Better: "Hey @maria! You asked about the guide — here it is: [link]. Let me know if you have any questions!"
Call POST /uploadposts/comments/reply with the personalized message.
Track which comment IDs you've already replied to (keep a list in your working memory) to avoid duplicate attempts.

Report Results

After processing, tell the user:

Total comments scanned
How many matched the trigger
How many DMs sent successfully
Any errors (already replied, window expired, rate limit)

Monitor Replies (Optional)

If the user wants follow-up handling:

Call GET /uploadposts/dms/conversations to check for new replies
For each reply, generate a contextual response using the funnel's purpose
Call POST /uploadposts/dms/send to respond
Only send within the 24-hour messaging window

Combining Both Modes

A smart approach: start a persistent monitor for the baseline (everyone gets the DM), then periodically run one-shot scans to check DM conversations and do personalized follow-ups. Tell the user this option if it fits their use case.

Compliance Rules

These are Meta's rules. Breaking them gets the account restricted, not just rate-limited.

What's allowed (you're doing this):

Sending a private reply to someone who commented on YOUR post — this is the exact use case Meta built the Private Replies API for
Using the official Instagram Graph API through Upload-Post
Personalizing messages per commenter

Hard limits:

200 DMs per hour per Instagram account (Meta enforces this — the API returns 429)
1 private reply per comment (API rejects duplicates)
7-day window on comments (older comments can't receive private replies)
24-hour window on follow-up DMs (resets each time the user replies)

What would get the account banned (never do this):

Sending DMs to people who never interacted with the account
Ignoring rate limit errors and retrying aggressively
Sending identical spam messages to hundreds of people

Error Handling

Code	Meaning	What to Do
200	DM sent	Track as success
400	Bad request	Check parameters — likely missing comment_id or message
401	Invalid API key	Ask user to check their key
404	Comment not found	Comment may have been deleted
429	Rate limit / DM limit reached	Stop sending. Tell the user how many were sent and that the limit was hit
500	Server error	Retry once, then report to user

When you hit a 429, stop the entire batch. Don't keep trying. Report to the user: "Sent X DMs successfully. Hit the rate limit — the remaining Y commenters will need to be processed later."

Example Conversation

User: "In my latest Reel I told people to comment CURSO to get info about my course. Set up the funnel to DM them the enrollment link https://mycourse.com/enroll"

Agent workflow:

GET /uploadposts/media?platform=instagram&user=profilename → find latest Reel
GET /uploadposts/comments?platform=instagram&user=profilename&post_id=12345
Analyze each comment for intent to receive the course info
For each match: POST /uploadposts/comments/reply with personalized DM
Report: "Found 47 comments. 31 matched the trigger. Sent 31 DMs. 2 had already been replied to. Here's the breakdown..."

Platform Limitation

This skill works on Instagram only. The comments and DM endpoints in the Upload-Post API currently support Instagram exclusively. This is because Meta's Private Replies API is Instagram-specific, and other platforms (TikTok, LinkedIn, X, etc.) don't offer equivalent APIs for comment-to-DM automation.

This is not a limitation of Upload-Post — it's how the social platform APIs work. Instagram is where 90%+ of comment-to-DM funnels run commercially (ManyChat, Inro, etc. are all Instagram-first for this reason).

Tips for Better Funnels

Short DMs convert better: 1-3 sentences max. Link + brief context. Nobody reads paragraphs in DMs.
Personalize: Reference their comment or use their display name. "Hey! Here's what you asked for" beats "Dear valued follower."
One clear CTA: Don't overload the DM. One link, one action.
Timing matters: The sooner after commenting they get the DM, the higher the open rate. Process comments as soon as the rate limit allows.
Track what works: Compare DM response rates across different message styles. Iterate.

About this skill

Automatic

Marketing & Content pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/instagram-auto-reply-comments/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 1 file

Illustrative Want to see what leoyeai/comment-funnel 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

Comment-to-DM Funnel — Upload-Post API

Documentation

Authentication

How the Funnel Works

Endpoints

Persistent Monitor Endpoints

Start Monitor

Check Monitor Status

Get Monitor Logs

Pause / Resume / Stop / Delete Monitor

One-Shot Endpoints

1. Get Recent Posts

2. Read Comments

3. Send Private Reply (the DM)

4. List DM Conversations

5. Send Follow-Up DM

Building the Funnel — Step by Step

Step 1: Gather Requirements

Step 2: Find the Post

Path A: Persistent Monitor (24/7)

Path B: One-Shot with AI (Smart Filtering)

Scan Comments

Send DMs

Report Results

Monitor Replies (Optional)

Combining Both Modes

Compliance Rules

Error Handling

Example Conversation

Platform Limitation

Tips for Better Funnels

SkillSafety

Source

Related skills

More in the registry