Ready to supercharge your AI agents?

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

Memory — Active Write & Consolidate · fradser | DecimalAI

Agent Toolingby fradser

Memory — Active Write & Consolidate

This skill should be used when the user asks to "consolidate memory", "tidy memory", "rebuild MEMORY.md", or wants to normalize, deduplicate, prune, or rebuild project memory. Consolidates the project's memory as one unlayered store — the private harness memory (~/.claude/projects/<escaped-cwd>/memory) and the repo-local memory (docs/memory/).

Maintained

SkillScore

SkillScore41/100

Test results 41

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

27%41%of test cases passed +14 pts

Without skill6 of 22

With skill9 of 22

6 fixed3 passed either way10 still failing3 broke

Measured on gemini-3.6-flash8/29/2026v212 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskA memory file `feedback_user_creds_handler.md` was accidentally written to both harness and `.memory/` in the past, but is now identified as containing private user workflow preferences. What action must consolidation take on `.memory/feedback_user_creds_handler.md`?

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 fradser-consolidate
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("fradser-consolidate")
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 fradser-consolidate

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/fradser-consolidate/SKILL.md https://app.decimal.ai/s/fradser-consolidate/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/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/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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("fradser-consolidate")
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/fradser-consolidate/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/fradser-consolidate/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 fradser-consolidate

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/fradser-consolidate/SKILL.md https://app.decimal.ai/s/fradser-consolidate/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/fradser-consolidate/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/fradser-consolidate/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/fradser-consolidate.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: v2, tested 8/29/2026
Source: fradser/dotclaude ↗
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

Memory — Active Write & Consolidate

The project's memory lives in two locations that must stay identical for safe (public) files (idempotent):

~/.claude/projects/<escaped-cwd>/memory/ — harness, loaded by Claude Code, written first
.memory/ — canonical, git-tracked, written second — safe files only

Resolve the harness path: ~/.claude/projects/<cwd-with-/→->/memory/ (probe both space-handling forms: /→-+ →- and /→-+space-kept).

Private files (user preferences, credentials, PII) live in harness only. They must never appear as files or index lines under .memory/.

Active Write

When you encounter a decision, preference, lesson, or anything worth remembering, write it immediately — do not wait for /memory:consolidate.

Before writing

Search existing memories first (Grep/Read harness *.md by theme keywords). If one already covers the topic, edit that file instead of creating a near-duplicate.
Refuse pure operation logs: if you cannot state a durable Why and a reusable How to apply, do not write a memory. Put timelines in git/commits/docs, not memory.
Prefer one decision per file. Two independent decisions → two files; the same decision learned twice → one file.

Privacy check

.memory/ is a public GitHub repo. Private = secrets/PII/credentials or user preferences / personal workflow habits. Safe technical content → both locations. Private → harness only; harness index line ends with (harness only).

How to write

Write file to harness .../memory/<filename>.md
If safe → write identical file to .memory/<filename>.md. If private → do not write to .memory/; if .memory/<filename>.md already exists, delete it.
Update indexes:
- Harness MEMORY.md: include every file (private lines marked (harness only))
- .memory/MEMORY.md: safe lines only — never copy (harness only) lines into the public index

File naming: <type>_<kebab-slug>.md (type: feedback, project, reference)

Format:

---
name: <kebab-slug>
description: <one-line hook distinguishing this from similar files>
type: feedback | project | reference
---

<the fact>

**Why:** <why this decision exists>

**How to apply:** <actionable rules>

**Related:** [[other-memory]] [[another-memory]]

Memory is decision log, not operation log

Every memory file answers two questions only:

Why — why this decision or rule exists
How to apply — what to do next time

Remove all operation history (version numbers, dates-as-timeline, "first X then Y"). That lives in git log. Keep only the durable rationale and actionable rules.

MEMORY.md index format

Each line: one concise sentence, no version numbers, no date ranges, no timeline descriptions. One line per surviving file. Prefer ≤50 lines for scanability; if more files exist, keep every entry and group by theme — never drop entries to hit 50.

Good: feedback_git_commit_hook_needed.md — git PreToolUse hook intercepts git add/commit, redirects to /git:commit; allows chain + GIT_SKILL_FALLBACK=1 escape Bad: feedback_git_commit_hook_needed.md — git PreToolUse hook intercepts git add/commit; v0.5.3 command position anchoring + two exceptions + 26 regression tests

Red lines

Never drop [[name]] cross-links when rewriting — preserve all from the original unless the target is intentionally deleted and the reference is removed in the same pass
Never delete a file referenced by [[name]] in another memory file unless the reference is also removed
rm only under the harness memory directory or .memory/ — never elsewhere
Never publish private content to .memory/ (file body or index line)

Consolidate (/memory:consolidate)

User-invoked only. No auto-consolidation. Default failure mode of a weak run is cosmetic tidy while leaving thematic redundancy and factually dead notes. This procedure is fail-closed against that.

Work order: harness first, then sync to .memory/.

CRITICAL: Mutation freeze until planning artifacts exist

Do not Write, Edit, or rm any memory file until all three artifacts exist in this conversation:

Inventory — complete name list of harness *.md and .memory/*.md (including both MEMORY.md)
Cluster map — every non-index file appears in exactly one theme cluster
Staleness table — every non-index file has a rubric verdict (step 4)

After ground-truth probes (step 5), also hold a ground-truth table with tool-observed paths (path → found|missing|updated) before applying claim fixes. Fabricating these tables without Read/Grep/find/ls is a failed run.

CRITICAL: Machine validator (cannot self-attest past this)

Write inventory / cluster / staleness / report to temp files, then run:

# Pre-mutation (lift freeze only if exit 0)
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/validate-consolidate.py" \
  --inventory /tmp/mem-inventory.txt \
  --cluster /tmp/mem-cluster.txt \
  --staleness /tmp/mem-staleness.txt \
  --check=cluster,staleness

# Post-sync before claiming done (exit 0 required)
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/validate-consolidate.py" \
  --inventory /tmp/mem-inventory.txt \
  --cluster /tmp/mem-cluster.txt \
  --staleness /tmp/mem-staleness.txt \
  --report /tmp/mem-report.md \
  --harness "<harness-memory-dir>" \
  --public "<repo>/.memory"

Exit 1 → fix artifacts / privacy and re-run. Exit 0 is required to lift the mutation freeze (pre) and to report consolidate complete (post). Do not claim G2/G3/G4/privacy by prose alone.

CRITICAL exit gates (must all pass before reporting done)

Do not claim consolidate complete unless every gate below is true:

Gate	Requirement
G1 Read	Every `*.md` in harness and `.memory/` was read (including both `MEMORY.md`)
G2 Cluster	Theme-cluster map covers every non-index file before any merge/delete
G3 Staleness	Every file scored with the staleness rubric (not calendar age alone)
G4 Ground truth	Every `project_` claim checked against the current* tree with cited paths (or N/A with reason)
G5 Merge bias	Every multi-file cluster either merged, or has an explicit one-line "keep separate because …"
G6 Adversarial	Independent second pass ran when required (step 8); findings applied or rejected with reason
G7 Report	Report includes inventory counts, cluster map, prune/merge table, ground-truth table, residual risks
G8 Validator	`validate-consolidate.py` exit 0 on pre-mutation (`cluster,staleness`) and post-sync (full checks)

If any gate fails mid-run, continue until it passes — do not stop at "normalized frontmatter + rebuilt index".

1. Read every file

Read every *.md in both harness memory and .memory/, including MEMORY.md. Detect drift (name sets and content hashes / word-level diffs). List harness-only private files. Emit the inventory.

2. Normalize shape plan (do not stop here; mutations still frozen)

Plan only until artifacts in the freeze section exist:

Relative dates → absolute YYYY-MM-DD
Frontmatter: name, description, type only (strip node_type, originSessionId, modified, nested metadata)
description specific enough to distinguish similar files
Ensure Why / How to apply sections exist; if missing, derive them or mark for prune as non-decision

Normalization alone is not consolidation.

3. CRITICAL: Theme-cluster before merge

Group every non-index file into theme clusters (e.g. deploy, billing, review pipeline, naming). Use overlapping keywords, shared [[links]], and near-duplicate descriptions.

Output a cluster map (keep it for the report):

cluster: <theme>
  - file-a.md
  - file-b.md
  merge-default: yes|no — <one line>

Default bias: 2+ files in one theme → merge into one decision log, unless each holds a distinct durable decision that would become muddled if combined.

4. CRITICAL: Staleness rubric (practical expiry ≠ calendar expiry)

Score every non-index file. Calendar age is only one signal — a note can be days old and still SUPERSEDED or OPS-ONLY.

Read references/staleness-examples.md for the full table, actions, and worked examples. Protect feedback_* preferences: incident dates do not make them OPS-ONLY.

5. CRITICAL: Ground-truth verify

For each project_* (and any reference_* that asserts repo-local facts):

Locate the claimed path, flag, API, architecture fact, or workflow in the current working tree
Record: VERIFIED | UPDATED | PRUNED | N/A (no repo) | UNVERIFIABLE (state why) plus tool-observed path → found|missing
Never leave a known-false claim in place after consolidate

Use Grep, Read, and allowed Bash (find/ls/stat/diff/…) against the project — not arbitrary shell. Do not trust memory text over the tree.

feedback_* about user/process preferences: verify consistency with other feedback files and current plugin/skill code when they name a mechanism; do not invent user-preference changes. Prefer KEEP on preference files unless contradicted by the user's later explicit preference.

6. Deduplicate and merge within clusters

Mutation freeze lifts only after inventory + cluster map + staleness table exist and pre-mutation validate-consolidate.py --check=cluster,staleness exits 0. For claim edits, also hold the ground-truth table first.

Merge duplicates; keep the most detailed durable rules
Collapse near-duplicates that differ only in incident detail
Preserve all unique [[name]] targets; rewrite links to survivors after renames/merges
After merge, survivor must still be decision-log shaped (Why + How), not a concatenated scrapbook

7. Rewrite for concision

Why — root cause or decision rationale (1–3 short paragraphs max)
How to apply — actionable bullets
Related — [[name]] cross-links
Strip version theater, step timelines, and "we tried X then Y"

8. CRITICAL: Independent adversarial pass

Run a second pass with clean context when any of: starting count ≥ 8 (excluding MEMORY.md); any cluster has 2+ files; ≥3 merges/deletes; user mentioned redundancy/stale memory; or you are unsure about keep-separate.

How: launch Agent (subagent_type general-purpose or Explore; fresh context). Pass inventory, cluster map, and paths only — not your keep-separate justifications. Ask it to propose merges, flag CONTRADICTED/SUPERSEDED/OPS-ONLY, list near-duplicate descriptions, and default to merge or prune when uncertain. Apply accepted findings; reject with one-line reasons in the report.

Zero findings despite multi-file clusters → re-check the largest cluster yourself. Skip only when count ≤ 5, all clusters size 1, no mutations, and ground-truth found nothing stale — state the skip. Never skip because the first pass "felt thorough".

9. Rebuild indexes (split public/private)

Rewrite two indexes:

Harness MEMORY.md — one line per surviving harness file; private lines end with (harness only)
.memory/MEMORY.md — one line per safe survivor only; strip every (harness only) line

No version/date theater. Group by theme if helpful. Keep every required entry (no hard 50-line drop).

10. Sync to `.memory/` (privacy fail-closed)

For each file in harness memory:

If safe → write identical content to .memory/
If private → do not write to .memory/; delete .memory/<same name> if it exists (stale public copy)
Delete *.md in .memory/ that are not among current safe harness files
Never delete harness private files by "syncing absence" from a partial .memory/ read

After sync: public safe sets match; no private bodies or private index lines remain under .memory/.

rm targets only paths under harness memory or .memory/.

11. Report (required sections)

## Consolidate report
- Inventory: harness N, .memory/ M, drift: …
- Clusters: (map covering every non-index file)
- Staleness: verdict counts
- Ground truth: rows with path → found|missing + VERIFIED/UPDATED/PRUNED counts
- Merged: (old files → survivor) × reasons
- Pruned: (file × rubric verdict × reason)
- Kept-separate: (cluster × justification)
- Privacy: private files kept harness-only; public scrub actions
- Adversarial pass: ran|skipped — findings applied/rejected
- Index rebuilt: harness yes|no; .memory yes|no (safe-only)
- Validator: pre exit=…; post exit=… (paste PASSED/FAILED summary)
- Residual risks: anything still fuzzy
- Gates: G1–G8 checklist

Write the report body to a temp file and run the post-sync validator (full checks). Exit non-zero → do not claim done. If nothing changed after a full gated run, still show inventory, cluster map, ground-truth, and validator output.

Anti-patterns (do not do these)

"Normalized frontmatter and rebuilt MEMORY.md" as the whole job while thematic near-duplicates remain
Pruning only by "older than 3/6 months" while leaving last week's superseded architecture notes
Creating a new memory file without searching for an existing theme file to edit
Concatenating three incident writeups and calling it a merge (that is still an ops log)
Skipping adversarial review because the first pass "felt thorough"
Reporting done without G1–G8, without pre-mutation inventory/cluster/staleness, or without validator exit 0
Copying the same MEMORY.md (including (harness only) lines) into both locations
Leaving a private file that was once copied into .memory/ after a later privacy classification
Self-attesting cluster/path/privacy in prose while skipping validate-consolidate.py

About this skill

Automatic

Knowledge Management 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

fradser / dotclaude

memory/skills/consolidate/SKILL.md

View on GitHub ↗

License MITImported 8/17/2026Version v2Bundled 1 file

Illustrative Want to see what fradser/consolidate 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

Memory — Active Write & Consolidate

Active Write

Before writing

Privacy check

How to write

Memory is decision log, not operation log

MEMORY.md index format

Red lines

Consolidate (/memory:consolidate)

CRITICAL: Mutation freeze until planning artifacts exist

CRITICAL: Machine validator (cannot self-attest past this)

CRITICAL exit gates (must all pass before reporting done)

1. Read every file

2. Normalize shape plan (do not stop here; mutations still frozen)

3. CRITICAL: Theme-cluster before merge

4. CRITICAL: Staleness rubric (practical expiry ≠ calendar expiry)

5. CRITICAL: Ground-truth verify

6. Deduplicate and merge within clusters

7. Rewrite for concision

8. CRITICAL: Independent adversarial pass

9. Rebuild indexes (split public/private)

10. Sync to .memory/ (privacy fail-closed)

11. Report (required sections)

Anti-patterns (do not do these)

SkillSafety

Source

Related skills

More in the registry

10. Sync to `.memory/` (privacy fail-closed)