Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问clear审计异常

self-improving自我完善

Agent Skill

self-improving 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 Codex、Claude、Cursor、Gemini CLI 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

222

周安装

9

GitHub Stars

2

下载量

70
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:self-improving(自我完善)
来源仓库:https://github.com/zpankz/mcp-skillset
仓库路径:skills/self-improving
安装命令:
npx skills add https://github.com/zpankz/mcp-skillset --skill self-improving
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/zpankz/mcp-skillset --skill self-improving

简介

self-improving 用于记录任务执行中的错误、纠正和经验沉淀。

  • 适合希望 Agent 持续改进问题处理和最佳实践的场景。
  • 通过 npx skills add 命令安装,建议结合原始 README 了解具体用法。
  • 安装前应确认权限范围和维护状态,避免触发文件读写或网络请求。
  • 涉及经验存储时应注意数据边界和隐私保护。

SKILL.md

Self-Improving with PRPM

Purpose

Automatically search and install PRPM packages to enhance Claude's capabilities for specific tasks. When working on infrastructure, testing, deployment, or framework-specific work, Claude searches the PRPM registry for relevant expertise and suggests packages to install.

When to Use

Automatically triggers when detecting:

  • Infrastructure keywords: aws, pulumi, terraform, kubernetes, docker, beanstalk
  • Testing keywords: test, playwright, jest, cypress, vitest, e2e
  • Deployment keywords: ci/cd, github-actions, gitlab-ci, deploy, workflow
  • Framework keywords: react, vue, next.js, express, fastify, django

Workflow

1. Task Analysis

Analyze user request for keywords and extract relevant terms.

2. Automatic Search

prpm search "<detected keywords>" --limit 5 --no-interactive

3. Package Suggestion

Present top 3 most relevant packages with:

  • Package name and author
  • Download count
  • Brief description
  • Confidence level (official/featured/community)

4. Installation (with approval)

prpm install <package-name> --as claude

5. Application

Load package knowledge and apply to current task.

Decision Rules

High Confidence (Auto-suggest)

  • ✅ Official packages (@prpm/*)
  • ✅ Featured packages
  • ✅ High downloads (>1,000)
  • ✅ Verified authors

Medium Confidence (Present options)

  • ⚠️ Community packages (<1,000 downloads)
  • ⚠️ Multiple similar packages
  • ⚠️ Tangentially related packages

Low Confidence (Skip)

  • ❌ Unverified packages
  • ❌ Deprecated packages
  • ❌ Zero downloads

Example Interaction

User: "Help me build Pulumi + Beanstalk infrastructure"

Analysis:
  Keywords: Pulumi, Beanstalk, infrastructure
  Search: prpm search "pulumi beanstalk infrastructure"
  Found: @prpm/pulumi-infrastructure (Official, 3.2K downloads)
  Confidence: High → Auto-suggest

Response:
"I found an official PRPM package that can help:

📦 @prpm/pulumi-infrastructure (Official, 3.2K downloads)
   - Pulumi TypeScript best practices
   - AWS resource patterns
   - Cost optimization guidelines

Should I install this to enhance my Pulumi knowledge?"

User: "Yes"

Action:
  ✅ Installing: prpm install @prpm/pulumi-infrastructure --as claude
  ✅ Loading knowledge
  ✅ Applying patterns to current task

Search Triggers

Infrastructure Tasks

Keywords: aws, gcp, azure, kubernetes, docker, pulumi, terraform Search: prpm search "infrastructure <cloud> <tool>"

Testing Tasks

Keywords: test, playwright, jest, cypress, vitest, e2e Search: prpm search "testing <framework>"

CI/CD Tasks

Keywords: ci/cd, github-actions, gitlab-ci, deploy, workflow Search: prpm search "deployment <platform>"

Framework Tasks

Keywords: react, vue, angular, next.js, express, django Search: prpm search "<framework> best-practices"

Search Commands

# Basic search
prpm search "keyword1 keyword2"

# author filter
prpm search --author "prpm"

# Type filter
prpm search --format claude "infrastructure"

# Sub Type filter
prpm search --format claude --subtype skill "infrastructure"

# Limit results
prpm search "github actions" --limit 5

# Sort by downloads
prpm search "testing" --sort downloads

Best Practices

  1. Be Proactive: Search before starting complex tasks
  2. Verify Quality: Check download counts and official status
  3. Ask Permission: Always get user approval before installing
  4. Apply Knowledge: Immediately use installed package patterns
  5. Track Helpfulness: Note which packages were useful

Meta-Dogfooding

Recognize packages PRPM used to build itself:

  • @prpm/pulumi-infrastructure → PRPM's own infrastructure (74% cost savings)
  • @sanjeed5/github-actions → PRPM's workflow validation
  • Testing packages → PRPM's E2E test patterns

Benefit: Users get the same expertise that built PRPM.

Privacy

  • ✅ All searches are local
  • ✅ No data sent to PRPM for searches
  • ✅ Download tracking only on install
  • ✅ No personal data collected

Remember: Self-improvement through package discovery makes Claude more capable for each specific task domain.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenCode

32.51%
按下载量换算23

Claude Code

25.37%
按下载量换算18

windsurf

16.9%
按下载量换算12

Codex

11.82%
按下载量换算8

kiro-cli

8.21%
按下载量换算6

mcpjam

3.33%
按下载量换算2

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills