Learning System Skill

v1.0.0

AI 领域系统学习体系。管理知识图谱、深度学习笔记、实战复盘和关联网络。触发场景：学习计划、知识图谱更新、深度研究某个 AI 主题、实战复盘总结、调研后沉淀知识、每周学习回顾。当用户说'学了什么'、'总结一下'、'沉淀知识'、'复盘'、'更新图谱'、'深入研究'、'写笔记'、'学习回顾'、'review what...

⭐ 0· 107·0 current·0 all-time

by@onlyloveher

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for onlyloveher/learning-sys-v1.

Previewing Install & Setup.

Prompt PreviewInstall & Setup

Install the skill "Learning System Skill" (onlyloveher/learning-sys-v1) from ClawHub.
Skill page: https://clawhub.ai/onlyloveher/learning-sys-v1
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install learning-sys-v1

ClawHub CLI

Package manager switcher

npx clawhub@latest install learning-sys-v1

Security Scan

VirusTotal

Pending

View report →

OpenClaw

Benign

high confidence

✓

Purpose & Capability

The skill name/description (learning system, knowledge map, deep-dive notes, weekly review) matches the actual files and scripts. The included Python scripts operate on local workspace paths (~/.openclaw/workspace/...), which is proportional to the stated purpose. No unrelated env vars, binaries, or config paths are requested.

ℹ

Instruction Scope

SKILL.md explicitly instructs the agent to read memory logs, PR records, deep-dive notes, and the knowledge map and to create/update notes/weekly reviews. That behavior is coherent for a learning-management skill but means the skill will access personal project/activity logs. SKILL.md also mentions sending summaries via Feishu and '按需加载' other AI/ML skills; those actions may require external connectors/credentials or cause the agent to call other skills (expands scope).

✓

Install Mechanism

No install spec; this is instruction-only with two small helper scripts bundled. No network downloads, package installs, or archive extraction are present—lowest install risk.

✓

Credentials

The skill requests no environment variables, no secrets, and no external credentials in its metadata. Occasional references to sending reports via Feishu are present in the docs but no Feishu token or connector is demanded by the skill itself. Overall the requested environment access is proportional to the purpose.

✓

Persistence & Privilege

always: false and default autonomous invocation allowed (platform default). The skill does not request permanent platform-wide privileges or modify other skills. It suggests writing/updating files under the user's notes directory and optionally scheduling cron jobs (user action), which are expected for a notes/reporting tool.

Assessment

This skill appears coherent for managing learning notes and computing mastery scores. Before installing, note: (1) it reads files under ~/.openclaw/workspace/ (notes, memory logs, deep-dives, weekly-reviews) and will rely on those files to generate reports—ensure you are comfortable with it reading those local files; (2) SKILL.md instructs the agent to create and update note files (ai-knowledge-map.md, deep-dives, weekly reviews) — if you allow autonomous runs or use the --quick flag the agent may write files without extra confirmations; (3) the docs mention sending summaries via Feishu and '按需加载' other skills — if you enable those actions you will need to provide/configure credentials or connectors and that expands the skill's effective access; (4) scripts only read and analyze files and print reports (no network calls or hidden endpoints were found), but review the scripts yourself if you have sensitive data in your workspace; (5) consider backing up notes/knowledge map before first run and avoid enabling fully autonomous operation until you confirm the behavior fits your workflow.

Like a lobster shell, security has layers — review code before you run it.

latestvk975vhpmd8s7c5ncbf2mzqrvsn83px6p

107downloads

0stars

1versions

Updated 1mo ago

v1.0.0

MIT-0

Learning System

将零散的资讯、调研、代码实战转化为体系化的 AI 领域专业知识。

核心理念

输入不等于学习。 看了 100 篇推文不代表懂了推理优化。改了 3 个 MCP bug 不代表吃透了 MCP 协议。学习 = 输入 + 加工 + 关联 + 输出。

模式选择

根据 $ARGUMENTS 或用户意图选择模式：

参数	模式	说明
`--mode deep-dive`	深度研究	选题 → 研究 → 写笔记 → 更新图谱
`--mode recap`	实战复盘	分析 PR/改动 → 提炼知识点 → 关联图谱
`--mode review`	每周回顾	汇总本周 → 更新图谱 → 生成周报
`--mode health`	健康检查	运行 `scripts/health_check.py` 输出报告
无参数	自动判断	根据上下文推断最合适的模式

附加参数：

--topic <name>: 指定主题（deep-dive 模式）
--quick: 跳过确认节点，全自动执行

文件结构

notes/areas/
├── ai-knowledge-map.md           # 知识图谱（掌握程度标记）
├── deep-dives/                    # 深度学习笔记
│   ├── mcp-tool-call-design.md
│   └── ...
└── weekly-reviews/                # 每周学习回顾
    ├── 2026-W07.md
    └── ...

Mode: 深度研究 (deep-dive)

Copy this checklist and check off items as you complete them:

Deep Dive Progress:

Mode: 实战复盘 (recap)

Recap Progress:

Mode: 每周回顾 (review)

Weekly Review Progress:

Mode: 健康检查 (health)

python3 scripts/health_check.py

输出知识图谱统计、深度笔记状态、本周活动量、改进建议。

Mode: Mastery Score (mastery)

python3 scripts/mastery_score.py          # 表格报告
python3 scripts/mastery_score.py --json   # 附加 JSON 输出

自动计算每个知识图谱主题的掌握分数，基于：

Recency（时间衰减）: 指数衰减，半衰期 30 天。今天接触 = 1.0，30 天前 = 0.5，60 天前 = 0.25
Repetition（重复次数）: 跨不同日期的接触次数累加
Depth（深度权重）: deep-dive 笔记 ×3.0，PR/复盘 ×2.0，普通提及 ×1.0

输出包含：分数排名、建议升降级、衰减警告（60 天未接触）。

关联网络

在深度笔记和复盘中主动建立关联。格式：→ 关联: [主题](相对路径)

关联类型	示例
技术关联	vLLM → PagedAttention → KV Cache 管理
实战关联	gemini-cli OAuth PR → OAuth 2.1 协议
对比关联	Flash Attention vs PagedAttention

与其他 skill 的关系

para-second-brain: 学习笔记存在 PARA 的 areas/ 下，自动被 memory_search 索引
85 个 AI/ML skills: 作为参考资料，深度学习时按需加载对应 skill
openclaw-feeds / news-summary: 资讯输入源，但不等于学习——需要加工和关联

Comments

Loading comments...