Home / hashgraph-online / awesome-codex-plugins · GitHub

continuous-learning SKILL.md skillA

continuous-learning from hashgraph-online/awesome-codex-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add hashgraph-online/awesome-codex-plugins/continuous-learning@v2.1.0

Pins v2.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: hashgraph-online/awesome-codex-plugins
Path: plugins/Colin4k1024/tsp/skills/continuous-learning-v2/SKILL.md
Versions recorded: 1
Latest version: v2.1.0, committed May 12, 2026
Size: 4,359 bytes
Repository stars: 1,501
License: Apache-2.0

基于 instinct 的持续学习系统，通过 hooks 观察会话，创建带置信度评分的 atomic instincts，并将高置信度 instinct 演进为 skills/commands/agents。v2.1 增加项目级 instincts 防止跨项目污染。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Continuous Learning v2.1 - Instinct-Based Architecture

一个高级学习系统，通过 atomic "instincts" 将 Claude Code 会话转化为可重用知识。

**v2.1** 增加 **项目级 instincts** — React 模式保留在 React 项目中，Python 约定保留在 Python 项目中，通用模式（如"始终验证输入"）全局共享。

## 何时激活

- 设置从 Claude Code 会话自动学习
- 配置基于 hooks 的行为提取
- 调优学习行为的置信度阈值
- 审查、导出或导入 instinct 库
- 将 instincts 演进为完整 skills、commands 或 agents
- 管理项目级 vs 全局 instincts
- 将 instincts 从项目级提升到全局级

## Instinct 模型

一个 instinct 是一个小的学习行为：

```yaml
---
id: prefer-component-colocation
trigger: "当多个组件使用相同状态时"
confidence: 0.7
domain: "frontend-architecture"
source: "session-observation"
scope: project
project_id: "a1b2c3d4e5f6"
project_name: "points-frontend"
---

# 组件状态共置

## 行为
当多个组件使用相同状态时，考虑将状态提升到共同祖先。

## 证据
- 在 5 个实例中观察到状态提升模式
- 用户在 2026-03-29 将组件本地状态改为共享状态
```

**属性**:
- **Atomic** -- 一个 trigger，一个 action
- **Confidence-weighted** -- 0.3 = 试探性，0.9 = 几乎确定
- **Domain-tagged** -- code-style, testing, git, debugging, workflow 等
- **Evidence-backed** -- 跟踪创建它的观察
- **Scope-aware** -- `project`（默认）或 `global`

## 存储结构

```
~/.claude/homunculus/
+-- projects.json           # 项目注册表: hash -> name/path
+-- observations.jsonl      # 全局观察（fallback）
+-- instincts/
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add hashgraph-online/awesome-codex-plugins/continuous-learning@sha256:9a4af32c7f51d9f4

The line at the top of this page pins the label v2.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_e3gjiqanvfywv7pn.svg)](https://markdownregistry.com/a/art_e3gjiqanvfywv7pn)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on May 12, 2026.

version	committed	commit	size	audit
v2.1.0 latest	2026-05-12	6523792	4,359 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (4359 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

hashgraph-online/awesome-codex-plugins · 1,501 stars · license Apache-2.0 · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_e3gjiqanvfywv7pn
GET https://markdownregistry.com/api/v1/resolve?ref=hashgraph-online/awesome-codex-plugins/continuous-learning
GET https://markdownregistry.com/api/v1/blob/9a4af32c7f51d9f467094de12c1d90f24b6fc0c1e631a4dd57b5341f70e7a87e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from hashgraph-online/awesome-codex-plugins

AGENTS.md AGENTS.md file

hashgraph-online/awesome-codex-plugins · AGENTS.md

git:20261103.f1993d0 · audit A · 1,501 stars

ontoly-software-graph SKILL.md skill

hashgraph-online/awesome-codex-plugins · plugins/0xsarwagya/ontoly-codex-plugin/skills/ontoly-software-graph/SKILL.md · Use Ontoly Software Graph evidence, CLI reports, MCP, and official Ontoly Agent Skills before searching source files…

git:20260714.2040a1b · audit A · 1,501 stars

agent-debug-fixer SKILL.md skill

hashgraph-online/awesome-codex-plugins · plugins/1139030773-cmd/agent-workflow-system/skills/agent-debug-fixer/SKILL.md · 中文调试修复技能。用于报错、测试失败、页面异常、功能不符合预期、需要定位根因并做最小修复时。触发语包括"进入调试模式""帮我修问题""报错了""测试失败""页面坏了""找根因"。