Ready to supercharge your AI agents?

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

Get Started Free →

Implementation Review Mode · gmickel | DecimalAI

Code Reviewby gmickel

Implementation Review Mode

John Carmack-level implementation review via RepoPrompt or Codex.

Maintained

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

32%77%of test cases passed +45 pts

Without skill7 of 22

With skill17 of 22

11 fixed6 passed either way4 still failing1 broke

Measured on gemini-3.6-flash8/18/2026v518 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe need to run a full review on task fn-505 containing only lockfile updates, but we must bypass the automatic fast pre-check that skips trivial diffs. What CLI flag must be passed?

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 gmickel-flow-next-impl-review
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("gmickel-flow-next-impl-review")
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 gmickel-flow-next-impl-review

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/gmickel-flow-next-impl-review/SKILL.md https://app.decimal.ai/s/gmickel-flow-next-impl-review/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/gmickel-flow-next-impl-review/SKILL.md

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/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/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add gmickel-flow-next-impl-review

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("gmickel-flow-next-impl-review")
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/gmickel-flow-next-impl-review/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/gmickel-flow-next-impl-review/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 6 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add gmickel-flow-next-impl-review

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/gmickel-flow-next-impl-review/SKILL.md https://app.decimal.ai/s/gmickel-flow-next-impl-review/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/gmickel-flow-next-impl-review/SKILL.md

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/gmickel-flow-next-impl-review/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/gmickel-flow-next-impl-review.json

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v5, tested 8/18/2026
Source: gmickel/flow-next ↗
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

Implementation Review Mode

Workflow is backend-split. Read workflow-common.md for Phase 0 (backend detection + philosophy + trivial-diff triage), then read ONLY the file matching your active backend. The opt-in --deep/--validate/--interactive phase detail (including the phase-ordering matrix) lives in optional-phases.md, loaded only when a flag fires:

BACKEND=codex → workflow-codex.md
BACKEND=copilot → workflow-copilot.md
BACKEND=cursor → workflow-cursor.md
BACKEND=host → workflow-host.md
BACKEND=rp → workflow-rp.md

Do not load the others — only the active backend's file is needed. Each backend file carries its own Critical Rules and anti-patterns.

Conduct a John Carmack-level review of implementation changes on the current branch.

Role: Code Review Coordinator (NOT the reviewer) Backends (branch on the Phase 0 RP_ELIGIBLE probe):

When RP_ELIGIBLE=1: RepoPrompt (rp), Codex CLI (codex), GitHub Copilot CLI (copilot), Cursor CLI (cursor), or host-native (host)
When RP_ELIGIBLE=0: Codex CLI (codex), GitHub Copilot CLI (copilot), Cursor CLI (cursor), or host-native (host) — rp is macOS-only; never list it in guidance you surface (--review=rp stays accepted)

Preamble — execute Phase 0 exactly once

The executable Phase 0 lives in workflow-common.md §"Phase 0: Backend Detection" — Read it and execute it ONCE, before any other bash in this skill. It defines $FLOWCTL (bundled — NOT installed globally; which flowctl fails, expected), probes RP_ELIGIBLE, resolves $BACKEND via the single flowctl review-backend call, and handles the ASK / none cases. Every later bash block here (triage, deep-pass selection) uses the $FLOWCTL it defines. Never invoke flowctl review-backend a second time in the same run.

Exception: a --review=<backend> argument (see Backend Selection below) wins — when present, set BACKEND from the flag and skip Phase 0's review-backend call + ASK handling (still run its $FLOWCTL / RP_ELIGIBLE setup lines).

When RP_ELIGIBLE=0 (not macOS, no supported RepoPrompt CLI), never steer the user toward rp: every backend summary, recommendation, or override hint you surface presents only the runnable configured backends codex, copilot, cursor, host (plus none). export is an explicit one-off review MODE (--review=export), not a configured backend — never present it as one. Suppression is not a ban: an explicit --review=rp, FLOW_REVIEW_BACKEND=rp, or review.backend=rp still resolves to rp and errors at runtime via require_rp_cli().

Backend Selection

Priority (first match wins):

--review=rp|codex|copilot|cursor|host|export|none argument
FLOW_REVIEW_BACKEND env var — bare backend (rp, codex, copilot, cursor, host, none) OR spec form (codex:gpt-5.4:xhigh, copilot:claude-opus-4.5, cursor:gpt-5.5-high); host is bare-only (host:<model> is rejected)
.flow/config.json → review.backend (same bare / spec forms)
Error - no auto-detection

Parse from arguments first

Check $ARGUMENTS for:

--review=rp or --review rp → use rp
--review=codex or --review codex → use codex
--review=copilot or --review copilot → use copilot
--review=cursor or --review cursor → use cursor
--review=host or --review host → use host
--review=export or --review export → use export
--review=none or --review none → skip review

If found, use that backend and skip all other detection.

Otherwise: Phase 0 resolves it

No --review flag → $BACKEND comes from workflow-common.md Phase 0 (executed once per the Preamble): the single flowctl review-backend "$REVIEW_ID" call with ASK handling included. Do not re-resolve here.

Backend detail (model / effort / spec grammar) — on demand

The per-backend "at a glance" descriptions, the backend[:model[:effort]] spec grammar, and the FLOW_REVIEW_BACKEND spec-form examples live in references/backend-specs.md. Read it only when you must surface backend guidance to the user or resolve a model/effort spec — a normal review already has $BACKEND and needs nothing from it. When RP_ELIGIBLE=0, omit the rp line from any guidance you surface (explicit --review=rp still honored).

Critical Rules

Per-backend rules for rp, codex, copilot, and cursor live at the top of each workflow-<backend>.md — read the active backend's file (routing table above) and follow its Critical Rules section.

For host backend (fn-123 R5 / fn-126): host is bare-only. After selection, read workflow-host.md. The review must use a fresh, tool-enforced read-only reviewer from a different model family and fail closed when no cross-family pin is available.

For all backends:

If REVIEW_RECEIPT_PATH set: write receipt after review (any verdict)
Any failure → output <promise>RETRY</promise> and stop

Hard invariants:

The coordinator never authors a verdict. A SHIP with no backend response behind it has broken this.
One backend per review. A transcript that dispatches a second backend after the first answered has broken this.
Review is never skipped without consent. A none backend that ends the run without the user's consent has broken this.

Input

Arguments: $ARGUMENTS Format: [task ID] [--base <commit>] [--validate] [--deep[=passes]] [--interactive] [focus areas]

--base <commit> - Compare against this commit instead of main/master (for task-scoped reviews)
--validate - After NEEDS_WORK verdict, run a validator pass that drops false-positive findings (fn-32.1, opt-in)
--deep / --deep=<passes> - Run additional specialized passes (adversarial / security / performance) after primary review (fn-32.2, opt-in)
--interactive - On NEEDS_WORK, walk through each finding with the user (Apply/Defer/Skip/Acknowledge) (fn-32.3, opt-in, Ralph-incompatible)
Task ID - Optional, for context and receipt tracking
Focus areas - Optional, specific areas to examine

Scope behavior:

With --base: Reviews only changes since that commit (task-scoped)
Without --base: Reviews entire branch vs main/master (full branch review)

Opt-in flags (fn-32):

--validate — adds a validator pass on NEEDS_WORK that re-checks each finding for false positives. All findings dropping upgrades verdict to SHIP.
FLOW_VALIDATE_REVIEW=1 env var — enables --validate session-wide (works in Ralph).
--deep — adds adversarial pass always + security/performance auto-enabled per diff paths. --deep=adversarial,security restricts to listed passes.
FLOW_REVIEW_DEEP=1 env var — enables --deep session-wide (works in Ralph).
--interactive — per-finding walkthrough on NEEDS_WORK. No env var form — per-invocation only, always hard-errors in Ralph mode (REVIEW_RECEIPT_PATH or FLOW_RALPH=1) to prevent accidental autonomous engagement.
Default review behavior (no flags) is unchanged.

Workflow

REPO_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"

Step 0: Parse Arguments

Parse $ARGUMENTS for:

--base <commit> → BASE_COMMIT (if provided, use for scoped diff)
--no-triage → set TRIAGE_DISABLED=1 (skip trivial-diff pre-check)
--validate → set VALIDATE=true (fn-32.1 validator pass on NEEDS_WORK)
--deep / --deep=<passes> → set DEEP=true + optional DEEP_PASSES CSV (fn-32.2)
--interactive → set INTERACTIVE=true (fn-32.3 per-finding walkthrough on NEEDS_WORK; Ralph-blocked)
First positional arg matching fn-* → TASK_ID
Remaining args → focus areas

If --base not provided, BASE_COMMIT stays empty (will fall back to main/master).

Opt-in flags + env vars — ONE parse fence (fn-110) for --validate / --deep / --interactive:

VALIDATE=false
DEEP=false
DEEP_PASSES=""  # optional CSV: "adversarial,security"
INTERACTIVE=false
for arg in $ARGUMENTS; do
  case "$arg" in
    --validate) VALIDATE=true ;;
    --deep) DEEP=true ;;
    --deep=*) DEEP=true; DEEP_PASSES="${arg#--deep=}" ;;
    --interactive) INTERACTIVE=true ;;
  esac
done

# Env opt-ins (Ralph-friendly). --interactive has NO env var form — per-invocation only.
if [[ "${FLOW_VALIDATE_REVIEW:-}" == "1" ]]; then
  VALIDATE=true
fi
if [[ "${FLOW_REVIEW_DEEP:-}" == "1" ]]; then
  DEEP=true
fi

# Ralph-block (fn-32.3): Ralph must never engage interactive.
if [[ "$INTERACTIVE" == "true" ]]; then
  if [[ -n "${REVIEW_RECEIPT_PATH:-}" || "${FLOW_RALPH:-}" == "1" ]]; then
    echo "Error: --interactive requires a user at the terminal; not compatible with Ralph mode (REVIEW_RECEIPT_PATH or FLOW_RALPH detected)." >&2
    exit 2
  fi
fi

if [[ "$DEEP" == "true" || "$VALIDATE" == "true" || "$INTERACTIVE" == "true" ]]; then
  echo "OPTIONAL PHASES ACTIVE — STOP. Read optional-phases.md (deep=$DEEP validate=$VALIDATE interactive=$INTERACTIVE) before continuing."
fi

When that sentinel prints, STOP and Read optional-phases.md before any further step — it owns the phase-ordering + flag-combination matrix, the deep-pass selection bash, the validator dispatch, and the walkthrough steps (per-finding loop detail in walkthrough.md, pass prompt templates in deep-passes.md). All three phases are default-OFF: when no flag fires, run the primary review only and write no validator / deep_passes / walkthrough receipt keys.

Step 0.5: Trivial-diff triage (fn-29.6)

Before invoking the configured backend, run a fast pre-check that short-circuits lockfile-only, docs-only, release-chore, and generated-file diffs. On SKIP, the receipt is written with mode: "triage_skip" / verdict: "SHIP" and the expensive backend call is skipped entirely.

Opt-out: --no-triage argument or FLOW_RALPH_NO_TRIAGE=1 env var.

if [[ -z "${TRIAGE_DISABLED:-}" && -z "${FLOW_RALPH_NO_TRIAGE:-}" ]]; then
  RECEIPT_PATH="${REVIEW_RECEIPT_PATH:-/tmp/impl-review-receipt${TASK_ID:+-${TASK_ID}}.json}"  # fn-90 R5: task-scoped default (concurrent tasks no longer collide); explicit REVIEW_RECEIPT_PATH still wins
  # Subcommand + one literal flag stay on the command line (the Ralph guard
  # blocks a variable in either of the two tokens after the launcher).
  TRIAGE_ARGS=(--receipt "$RECEIPT_PATH")
  [[ -n "$BASE_COMMIT" ]] && TRIAGE_ARGS+=(--base "$BASE_COMMIT")
  [[ -n "$TASK_ID" ]] && TRIAGE_ARGS+=(--task "$TASK_ID")
  # Deterministic-only by default; set FLOW_TRIAGE_LLM=1 to enable LLM judge
  # for ambiguous diffs. Deterministic is conservative — ambiguous → REVIEW.
  [[ -z "${FLOW_TRIAGE_LLM:-}" ]] && TRIAGE_ARGS+=(--no-llm)

  if TRIAGE_OUT=$($FLOWCTL triage-skip --json "${TRIAGE_ARGS[@]}" 2>/dev/null); then
    # Exit 0 = SKIP. Receipt already written by flowctl.
    SKIP_REASON=$(echo "$TRIAGE_OUT" | jq -r '.reason // "trivial diff"' 2>/dev/null || echo "trivial diff")
    echo "Triage-skip: $SKIP_REASON"
    echo "VERDICT=SHIP"
    exit 0
  fi
  # Exit 1 = proceed to full review (normal path). Exit >=2 = error, also falls
  # through so impl-review proceeds safely rather than failing on triage.
fi

Opt-out note: Pass --no-triage to force the full backend review (useful when explicitly validating a suspicious chore diff, or when the deterministic whitelist misclassifies). FLOW_RALPH_NO_TRIAGE=1 has the same effect for Ralph runs.

The deterministic rule table, the SKIP receipt shape, and the FLOW_TRIAGE_LLM=1 judge live in references/triage-rules.md — read it only when a triage result needs justifying or auditing.

Step 1: Load Backend Workflow

$BACKEND was already resolved by workflow-common.md Phase 0 (Preamble) — do NOT re-run it.
Read only the file for that backend, per the routing table at the top of this file.

Do not read the other backend files. Each is self-contained for its backend; loading the others wastes context.

Step 2: Execute the backend workflow

Follow the phases in the per-backend file end-to-end. Each file owns its own Identify → Execute → Verdict → Receipt steps (and, for RP, the full Phase 1-4 setup-review (5-15 min, DO NOT RETRY) / chat-send (2-10 min, DO NOT RETRY) / receipt build + Fix Loop). Cross-backend gated phases (Deep-Pass, Validator, Interactive Walkthrough) live in optional-phases.md — the backend files reference them.

Fix Loop (INTERNAL - do not exit to Ralph)

The fix loop never pauses for user confirmation. Every valid finding is fixed and re-reviewed automatically — the goal is production-grade world-class software and architecture. A loop that stops to ask, or that exits with a valid finding unfixed, has broken this. Never use the plain-text numbered prompt in this loop.

MAJOR_RETHINK is NOT a fix-loop input. Every backend can emit MAJOR_RETHINK (a valid verdict tag), but it means the design/approach is wrong — not something to patch finding-by-finding. Do NOT enter the fix loop on it. Escalate immediately: surface the reviewer's rationale to the caller and stop with a typed BLOCKED: DESIGN_CONFLICT (Ralph mode: output <promise>RETRY</promise>). A re-approach is a human/worker decision, never an ad-hoc patch. Only NEEDS_WORK drives the loop below.

MAX ITERATIONS (backend-agnostic — rp, codex, copilot, cursor, host): flowctl reserves a per-task round before every task-scoped dispatch. A delivered SHIP / NEEDS_WORK / MAJOR_RETHINK / NEEDS_HUMAN consumes it; a no-verdict transport failure is durably recorded and refunded. At ${MAX_REVIEW_ITERATIONS:-8} verdict rounds it refuses with ESCALATE: + exit 4. More than ${MAX_REVIEW_TRANSPORT_FAILURES:-2} consecutive no-verdict failures stop separately with TRANSPORT_UNHEALTHY + exit 5: repair the backend, never reset the verdict counter. This loop is internal; callers invoke impl-review once. The counter resets only on SHIP or explicit re-plan, never on an edit, fresh invocation, or transport failure.**

Unchanged-artifact terminal: NOT_RETRYABLE: artifact unchanged since last verdict exits 1 before a review is sent. It is a human-action terminal: autonomous loops must stop without refunding, resetting, adding --force, or redispatching. The human may edit the artifact, explicitly reset, or choose a deliberate --force dispatch.

ANTI-PATTERN (never do either):

A delivered verdict is never a transport failure. Once flowctl parses VERDICT=SHIP|NEEDS_WORK|MAJOR_RETHINK|NEEDS_HUMAN, the round is consumed and the attempt is recorded; transport classification is unreachable past that point. Do not re-dispatch, re-frame a NEEDS_WORK as a backend/sandbox problem, or claim a refund for it. NEEDS_WORK is fix-loop input, full stop.
Never widen the reviewer sandbox. Reviewers are read-only by contract (Unix default read-only). A sandbox-blocked reviewer means something asked it to mutate the workspace: fix that, do not pass --sandbox workspace-write / danger-full-access or set CODEX_SANDBOX. The one exception is Windows, where auto already resolves for you.

On NEEDS_WORK — STOP and Read references/fix-loop.md before any further step: it owns the ordered loop (optional deep / validator / walkthrough hooks, parse issues, fix code, run tests and lints, commit fixes, per-backend re-review command, repeat until <verdict>SHIP</verdict> or the cap above). Do not improvise the loop from memory. On SHIP the review is complete and nothing further is read.

When it activates

Automatically, when a task matches. Use when reviewing code changes, PRs, or implementations. Triggers on /flow-next:impl-review.

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/17/2026

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

gmickel / flow-next

plugins/flow-next/skills/flow-next-impl-review/SKILL.md

View on GitHub ↗

License MITImported 8/17/2026Version v5Bundled 6 files

Illustrative Want to see what gmickel/flow-next-impl-review would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

gmickel/flow-next-plan-reviewCarmack-level plan review via RepoPrompt or Codex. Use when reviewing Flow specs or design docs. Triggers on /flow-next:plan-review.Close match+61 pts pass-rate lift

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

Implementation Review Mode

Preamble — execute Phase 0 exactly once

Backend Selection

Parse from arguments first

Otherwise: Phase 0 resolves it

Backend detail (model / effort / spec grammar) — on demand

Critical Rules

Input

Workflow

Step 0: Parse Arguments

Step 0.5: Trivial-diff triage (fn-29.6)

Step 1: Load Backend Workflow

Step 2: Execute the backend workflow

Fix Loop (INTERNAL - do not exit to Ralph)

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry