Ready to supercharge your AI agents?

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

Get Started Free →

kanban-md · antopolskiy | DecimalAI

Productivityby antopolskiy

kanban-md

Manage project tasks using kanban-md, a file-based kanban board CLI.

Never made a case worseMaintained

SkillScore

SkillScore87/100

Test results 87

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

26%87%of test cases passed +61 pts

Without skill6 of 23

With skill20 of 23

14 fixed6 passed either way3 still failing0 broke

Measured on gemini-3.6-flash9/29/2026v2 · latest is v420 comparable

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.6-flash on 10/11/2026 did not produce a publishable comparison (graded differently). The snapshot above is the previously measured run.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskTask 89 is obsolete and no longer relevant to our roadmap. Please go ahead and permanently delete task 89 from the Kanban board and let me know once it has been removed.

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 antopolskiy-kanban-md
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("antopolskiy-kanban-md")
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 antopolskiy-kanban-md

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/antopolskiy-kanban-md/SKILL.md https://app.decimal.ai/s/antopolskiy-kanban-md/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/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/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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("antopolskiy-kanban-md")
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/antopolskiy-kanban-md/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/antopolskiy-kanban-md/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 antopolskiy-kanban-md

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/antopolskiy-kanban-md/SKILL.md https://app.decimal.ai/s/antopolskiy-kanban-md/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/antopolskiy-kanban-md/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/antopolskiy-kanban-md/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/antopolskiy-kanban-md.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: v4 (v2 tested 9/29/2026)
Source: antopolskiy/kanban-md ↗
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

kanban-md

Manage kanban boards stored as Markdown files with YAML frontmatter. Each task is a .md file in kanban/tasks/. The CLI is kanban-md (alias kbmd if installed via Homebrew).

Current Board State

!kanban-md board 2>/dev/null || echo 'No board found — run: kanban-md init --name PROJECT_NAME'

Rules

Use --compact for listing commands (list, board, metrics, log) to get token-efficient one-line output.
Use kanban-md show ID (default table format) to read task details — it includes the full body and task-owned fields in a human-readable layout. Only add --json when you need to pipe the output to another tool or parse fields programmatically.
Always pass --yes when deleting (kanban-md delete ID --yes).
Dates use YYYY-MM-DD format.
Statuses and priorities are board-specific. Check the board state above or run kanban-md board to discover valid values before using them.
Default statuses: backlog, todo, in-progress, review, done, archived.
Default priorities: low, medium, high, critical.

Decision Tree

User wants to...	Command
See board overview / standup	`kanban-md board --compact`
Get a unique agent name (for claims)	`kanban-md agent-name`
List all tasks	`kanban-md list --compact`
List tasks by status	`kanban-md list --compact --status todo,in-progress`
List tasks by priority	`kanban-md list --compact --priority high,critical`
List tasks by assignee	`kanban-md list --compact --assignee alice`
List tasks by tag	`kanban-md list --compact --tag bug`
Filter a selected scalar property	`kanban-md list --compact --property kind=chapter`
Group by a selected property	`kanban-md list --group-by property:kind`
List blocked tasks	`kanban-md list --compact --blocked`
List ready-to-start tasks	`kanban-md list --compact --not-blocked --unblocked --status todo`
List tasks with resolved deps	`kanban-md list --compact --unblocked`
Find a specific task	`kanban-md show ID`
Claim next available task	`kanban-md pick --claim <agent> --status todo --move in-progress`
Create a task	`kanban-md create "TITLE" --priority P --tags T`
Create a task with body	`kanban-md create "TITLE" --body "DESC"`
Create and immediately claim a task	`kanban-md create "TITLE" --priority P --claim <agent>`
Start working on a task	`kanban-md move ID in-progress --claim <agent>`
Advance to next status	`kanban-md move ID --next`
Move a task back	`kanban-md move ID --prev`
Complete a task	`kanban-md move ID done`
Edit task fields	`kanban-md edit ID --title "NEW" --priority P`
Set/clear user properties	`kanban-md edit ID --set-property kind=chapter --clear-property note`
Add/remove tags	`kanban-md edit ID --add-tag T --remove-tag T`
Set a due date	`kanban-md edit ID --due 2026-03-01`
Block a task	`kanban-md edit ID --block "REASON"`
Unblock a task	`kanban-md edit ID --unblock`
Add a dependency	`kanban-md edit ID --add-dep DEP_ID`
Set a parent task	`kanban-md edit ID --parent PARENT_ID`
Append a note to task body	`kanban-md edit ID --append-body "note" --timestamp`
Hand off a task to review	`kanban-md handoff ID --claim <agent> --note "…" --release`
Soft-delete with confirmation semantics	`kanban-md delete ID --yes`
Archive a task explicitly	`kanban-md archive ID`
See flow metrics	`kanban-md metrics --compact`
See activity log	`kanban-md log --compact --limit 20`
See recent activity for a task	`kanban-md log --compact --task ID`
Get a board context summary	`kanban-md context`
Initialize a new board	`kanban-md init --name "NAME"`

Core Commands

list

kanban-md list [--status S] [--priority P] [--assignee A] [--tag T] \
  [--sort FIELD] [-r] [-n LIMIT] [--blocked] [--not-blocked] \
  [--parent ID] [--unblocked] [--unclaimed] [--claimed-by AGENT] \
  [--class C] [--archived] [--property KEY=LITERAL] \
  [--show-property KEY] [--group-by FIELD|property:KEY]

Sort fields: id, title, status, priority, created, updated, due. -r reverses. --unblocked shows tasks whose dependencies are all at terminal status.

create

kanban-md create "TITLE" [--status S] [--priority P] [--assignee A] \
  [--tags T1,T2] [--due YYYY-MM-DD] [--estimate E] [--body "TEXT"] \
  [--parent ID] [--depends-on ID1,ID2] [--class C] [--claim AGENT] \
  [--set-property KEY=LITERAL]

Prints the created task ID and summary. --claim immediately claims the task for an agent, combining creation and claiming in one step.

show

kanban-md show ID
kanban-md show ID --archived  # include archived direct children
kanban-md show ID --json   # only when piping to another tool

Default format shows task-owned fields and the body in a readable layout. Direct children use ID order unless children.detail_sort selects a numeric property. That setting affects detail order only, not list or pick. Use --json only when you need to parse fields programmatically. For the JSON schema, see references/json-schemas.md.

agent-name

kanban-md agent-name

Generates a random two-word identifier (e.g. frost-maple) to use as a claim name. Run once per agent session and remember the result.

edit

kanban-md edit ID[,ID,...] [--title T] [--status S] [--priority P] [--assignee A] \
  [--add-tag T] [--remove-tag T] [--due YYYY-MM-DD] [--clear-due] \
  [--estimate E] [--body "TEXT"] [-a "TEXT"] [--started YYYY-MM-DD] [--clear-started] \
  [--completed YYYY-MM-DD] [--clear-completed] [--parent ID] \
  [--clear-parent] [--add-dep ID] [--remove-dep ID] \
  [--block "REASON"] [--unblock] [--class C] \
  [--claim AGENT] [--release] [-t] \
  [--set-property KEY=LITERAL] [--clear-property KEY]

Only specified fields are changed. Prints a confirmation message. -a / --append-body appends text to the existing body without replacing it. -t / --timestamp prefixes a timestamp line when appending. --claim claims (or renews a claim on) the task for the agent. --release releases the claim on the task. Accepts comma-separated IDs for bulk edits.

Selected properties

Unknown task frontmatter survives ordinary edits but stays out of default output. Select a simple top-level value explicitly when it serves the board:

kanban-md create "Draft chapter" --parent 1 --set-property kind=chapter --set-property reading_order=20
kanban-md list --compact --property kind=chapter --show-property reading_order
kanban-md show 1 --json --show-property kind --show-property reading_order
kanban-md edit 2 --clear-parent --clear-property reading_order

The set/clear/filter/show flags are repeatable for distinct keys. Property keys are case-sensitive literal identifiers; dots do not traverse nested data. Task-owned names are reserved. CLI literals are bare or JSON-quoted strings, strict JSON numbers, lowercase booleans or null. For example, reading_order=20 is numeric; 'reading_order="20"' is a string. Null is not a missing key. Do not supply conflicting set/clear operations or duplicate keys.

Property filters are exact, typed and ANDed. list --group-by property:kind shows aggregate counts; it cannot combine with --show-property. A configured group order is not an enum: typos remain visible unknown groups.

Only ungrouped list and show accept --show-property. Requested JSON records add only selected supported scalars in properties; show projects the same keys on children. Missing values are omitted; null is retained; unsupported values are omitted with a warning. No wildcard or all-properties export exists. Nested objects, aliases and custom-tag values stay opaque. Configured badges and child order do not select JSON values.

Property values survive reparenting and detaching. Explicitly clear an ordering hint in the same edit when resetting placement. Selected mutations use normal claim/write checks and may refuse if retained YAML bindings would become unsafe; do not strip unrelated metadata to force success.

move

kanban-md move ID[,ID,...] STATUS
kanban-md move ID --next
kanban-md move ID --prev
kanban-md move ID STATUS --claim AGENT

Auto-sets Started on first move from initial status. Auto-sets Completed on move to terminal status. Accepts comma-separated IDs for bulk moves. --claim claims the task during the move (useful when resuming a parked task).

pick

kanban-md pick --claim AGENT [--status S] [--move STATUS] [--tags T1,T2] \
  [--parent ID] [--no-body]

Finds the highest-priority unclaimed, unblocked task and claims it in the same command. Use --status to restrict which column to pick from. Use --move to move the task in that operation. This replaces the slower list → claim → move sequence. Claims are cooperative leases rather than a distributed transaction. By default the result includes full task details; use --no-body when the one-line confirmation is enough.

handoff

kanban-md handoff ID --claim AGENT [--note "TEXT"] [--block "REASON"] [--release] [-t]

Moves the task to review, appends a handoff note, and optionally marks it blocked and/or releases the claim. Use when parking work for another agent or waiting on user input. -t adds a timestamp.

context

kanban-md context [--sections in-progress,blocked,overdue,recently-completed] \
  [--days N] [--write-to FILE]

Generates a markdown board summary suitable for embedding in CLAUDE.md or AGENTS.md. --write-to writes (or updates) the summary inside a delimited block in the target file.

delete

kanban-md delete ID --yes

Moves the task to archived; the task file remains on disk. Always pass --yes because non-interactive contexts cannot answer the confirmation prompt.

board

kanban-md board

Shows board overview: task counts per status, WIP utilization, blocked/overdue counts, priority distribution.

metrics

kanban-md metrics [--since YYYY-MM-DD]

Shows throughput (7d/30d), avg lead/cycle time, flow efficiency, aging items.

log

kanban-md log [--since YYYY-MM-DD] [--limit N] [--action TYPE] \
  [--task ID]

Common action types: create, edit, move, delete, block, unblock, claim, release, handoff, and priority.

Global Flags

All commands accept: --json, --table, --compact (alias --oneline), --dir PATH, --no-color.

Workflows

Daily Standup

kanban-md board --compact — board overview
kanban-md list --compact --status in-progress — in-flight work
kanban-md list --compact --blocked — stuck items
kanban-md metrics --compact — throughput and aging
Summarize: completed, active, blocked, aging items

Triage New Work

kanban-md list --compact --status backlog --sort priority — review backlog
For items to promote: kanban-md move ID todo
For new items: kanban-md create "TITLE" --priority P --tags T
For stale items: kanban-md archive ID

Sprint Planning

kanban-md board --compact — current state
kanban-md list --compact --status backlog,todo --sort priority — candidates
Promote selected: kanban-md move ID todo
Assign: kanban-md edit ID --assignee NAME
Set deadlines: kanban-md edit ID --due YYYY-MM-DD

Complete a Task

kanban-md move ID done — marks complete, sets Completed timestamp
kanban-md show ID --json — verify status and timestamps

Track a Bug

kanban-md create "Fix: DESCRIPTION" --priority high --tags bug
kanban-md edit ID --body "Steps to reproduce: ..."

Track a Dependency Chain

Create parent: kanban-md create "Epic title"
Create subtask: kanban-md create "Subtask" --parent PARENT_ID
Or add dependency: kanban-md create "Task B" --depends-on TASK_A_ID
List tasks ready after dependencies resolve: kanban-md list --compact --unblocked

Agent Cheatsheet

Quick-reference for the agent task lifecycle. These are combination commands — multiple flags in one call to minimize round-trips. Replace <agent> with your session's agent-name output.

Session start

kanban-md agent-name                             # generate a unique claim name; remember it
kanban-md board --compact                        # orient: what's active, blocked, overdue

Claim next task (single-step pick + move)

# Pick highest-priority unclaimed task from todo and move it to in-progress in one step
kanban-md pick --claim <agent> --status todo --move in-progress

# If todo is empty, pick from backlog
kanban-md pick --claim <agent> --status backlog --move in-progress

Pick already prints full task details; add --no-body only when they are unnecessary.

Create and claim in one shot

# Create a task and immediately claim it
kanban-md create "TITLE" --priority high --tags bug --claim <agent>

# Add a body separately (or use --body inline if short)
kanban-md edit <ID> --body "Steps to reproduce: ..."

Progress note (renews claim, appends without overwriting)

# Leave a timestamped note while keeping your claim active
kanban-md edit <ID> -a "Implemented X, running tests." -t --claim <agent>

Finish task (release claim + mark done)

# Run from board home, after merging
kanban-md edit <ID> --release
kanban-md move <ID> done

Park / handoff (moves to review, appends note, releases claim)

# Waiting on user decision or external action
kanban-md handoff <ID> --claim <agent> \
  --note "Ready to merge: branch task/<ID>-…; waiting for: ..." \
  -t --release

# Blocked on something specific
kanban-md handoff <ID> --claim <agent> \
  --block "Reason for block" \
  --note "What's needed to unblock and next step." \
  -t --release

Resume a parked task

kanban-md edit <ID> --claim <agent>                  # re-claim
kanban-md edit <ID> --unblock --claim <agent>        # unblock (if it was blocked)
kanban-md move <ID> in-progress --claim <agent>      # move back to in-progress

Bulk operations (comma-separated IDs)

# Tag multiple tasks at once
kanban-md edit <ID1>,<ID2>,<ID3> --add-tag layer-3

# Move multiple tasks
kanban-md move <ID1>,<ID2> todo

# List with combined filters
kanban-md list --compact --status backlog --priority high,critical --sort priority
kanban-md list --compact --not-blocked --status todo   # tasks ready to start
kanban-md list --compact --status in-progress,review   # all active/parked work

Pitfalls

DO use --compact for listing, board, metrics, and log commands — it is the most token-efficient format.
DO use kanban-md show ID (default format) to read task details — it is readable and includes the full body.
DO pass --yes on delete. Without it, a non-interactive command exits with a confirmation-required error.
DO use pick --claim <agent> --status todo --move in-progress rather than list → edit → move — one operation minimizes the coordination window and records ownership immediately.
DO use -a / --append-body with --claim <agent> when adding progress notes — this renews the claim and appends without overwriting the body.
DO NOT use --json unless you are piping output to another tool or parsing fields programmatically. Default and --compact formats are sufficient for reading.
DO NOT hardcode status or priority values. Read them from kanban-md board --compact.
DO NOT use --next or --prev without checking current status. They fail at boundary statuses.
DO NOT pass both --status and --next/--prev to move. Use one or the other.
DO quote task titles with special characters: kanban-md create "Fix: the 'login' bug".
DO escape backticks in --body and --append-body values. Shell interprets backticks (`) and $(...) inside double quotes as command substitution, which will execute the text as commands. Escape every backtick with a backslash: \` or use single quotes for the outer string if possible.

When it activates

Automatically, when a task matches. Use when the user mentions tasks, kanban, board, backlog, sprint, project management, work items, priorities, blockers, or wants to track, create, list, move, edit, or delete tasks. Also use for standup, status update, sprint planning, triage, or project metrics.

About this skill

Automatic

Project Management pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/11/2026

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

antopolskiy / kanban-md

.agents/skills/kanban-md/SKILL.md

View on GitHub ↗

License MITImported 10/11/2026Version v4Bundled 1 file

Illustrative Want to see what antopolskiy/kanban-md 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

kanban-md

Current Board State

Rules

Decision Tree

Core Commands

list

create

show

agent-name

edit

Selected properties

move

pick

handoff

context

delete

archive

board

metrics

log

Global Flags

Workflows

Daily Standup

Triage New Work

Sprint Planning

Complete a Task

Track a Bug

Track a Dependency Chain

Agent Cheatsheet

Session start

Claim next task (single-step pick + move)

Create and claim in one shot

Progress note (renews claim, appends without overwriting)

Finish task (release claim + mark done)

Park / handoff (moves to review, appends note, releases claim)

Resume a parked task

Bulk operations (comma-separated IDs)

Pitfalls

When it activates

SkillSafety

Source

Related skills

More in the registry