continual-learn

Agent Skills › melandlabs/openloomi › continual-learn

continual-learn

GitHub

通过持久化维护 MENTAL_MODEL.md 文件，在对话轮次间持续记录任务状态、反馈与经验教训，支持迭代编码、调试及任何需反馈驱动的任务。

benchmark/continual-learning-bench/skills/continual-learn/SKILL.md melandlabs/openloomi

Trigger Scenarios

多轮迭代式编码任务需要上下文记忆的调试过程基准测试或反馈驱动的复杂任务

Install

npx skills add melandlabs/openloomi --skill continual-learn -g -y

More Options

Non-standard path

npx skills add https://github.com/melandlabs/openloomi/tree/main/benchmark/continual-learning-bench/skills/continual-learn -g -y

Use without installing

npx skills use melandlabs/openloomi@continual-learn

指定 Agent (Claude Code)

npx skills add melandlabs/openloomi --skill continual-learn -a claude-code -g -y

安装 repo 全部 skill

npx skills add melandlabs/openloomi --all -g -y

预览 repo 内 skill

npx skills add melandlabs/openloomi --list

SKILL.md

Frontmatter

{
    "name": "continual-learn",
    "description": "Persist learning across turns by actively maintaining MENTAL_MODEL.md in the workspace. Use for iterative coding, debugging, benchmarking, or any feedback-driven task; read and update the file with actual filesystem writes before every response, never just hidden\/internal memory."
}

You must maintain a real workspace file, MENTAL_MODEL.md, as your durable scratchpad for this task.

Non-negotiable file workflow

Use ./MENTAL_MODEL.md in the current workspace; create it if it does not exist.
At the start of each turn, consult the current file when possible.
Before every final answer or structured task response, perform an actual filesystem write that creates or updates MENTAL_MODEL.md.
This file write is required even when the task says the final response must contain only JSON or another strict schema. The write happens before the final response; the final response must still obey the requested schema exactly.
If a dedicated file-write/edit operation is available, use it. Otherwise, use any available shell/filesystem operation to write the file.

What to record

Keep notes terse, high-signal, and actionable:

Task goal, current plan, and open assumptions.
Feedback received and what it changes.
Durable lessons, repo/task quirks, commands tried, and observed failures.
Hypotheses being tested and evidence for/against them.
Current state and the next concrete action.
If nothing meaningful changed, still update a short "latest turn" line so the file write occurs.