跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Skill Optimizer

技能 活跃

Guide to analyze a current work session and propose improvements to skills. Use (1) automatically after working with a skill to capture learnings, (2) when the user suggests improvements, corrections, or additions during a skill-related session, or (3) when the user manually invokes `self-improve`.

目的

To systematically enhance the quality and accuracy of other skills by learning from user interactions and providing a structured feedback loop.

功能

  • Analyze conversation for skill improvement signals
  • Evaluate feedback against quality criteria (Complete, Precise, Atomic, Stable)
  • Propose skill instruction changes with source attribution
  • Support manual and automatic improvement modes
  • Track modifications via changelog

使用场景

  • Automatically capture learning after working with a skill
  • Manually improve a skill based on user suggestions during a session
  • Enable automatic skill analysis to capture feedback without explicit invocation
  • Review past skill modifications and revert to previous versions

非目标

  • Performing the actual modifications to skills without user approval
  • Guessing user intent when feedback is unclear
  • Inferring requirements that are not explicitly stated
  • Adding vague or subjective instructions to skills

实践

  • Skill Development
  • Prompt Engineering
  • Feedback Integration

先决条件

  • Access to Claude Code environment
  • Ability to modify local skill files (SKILL.md, CHANGELOG.md)

License

  • warning:License usabilityThe license is AGPL-3.0, a strong copyleft license. While OSS, its network interaction clause and strong copyleft nature might impose requirements on distributed or network-served derivatives, potentially impacting usability depending on the context of use.

Maintenance

  • warning:Commit recencyThe last commit was on March 3, 2026, which is over 2 months ago, suggesting potential unmaintained status given the current date of May 13, 2026.

Trust

  • info:Issues AttentionIn the last 90 days, 3 issues were opened and 7 were closed, indicating a moderate level of maintenance engagement.

Install

  • warning:Installation instructionThe README provides instructions for enabling automatic mode by adding a hook to settings, but it lacks a clear, copy-pasteable invocation example for the primary `self-improve` command.

Practical Utility

  • warning:Usage examplesWhile the README provides two examples of user feedback and the expected output, it lacks a concrete, copy-pasteable invocation example for the primary `self-improve` command.

安装

请先添加 Marketplace

/plugin marketplace add lawvable/awesome-legal-skills
/plugin install skill-optimizer-lawvable@lawvable

质量评分

76 /100
1 day ago 分析

信任信号

最近提交2 months ago
星标349
许可证AGPL-3.0-or-later
状态
查看源代码

类似扩展

Fixflow

100

使用严格的交付工作流执行编码任务:构建完整计划、分步实现、持续运行测试,并默认在每一步 (`per_step`) 后提交。当用户要求行为驱动交付或需求不明确时,支持显式提交策略覆盖 (`final_only`, `milestone`) 和可选的 BDD(给定/当/则)。

技能
majiayu000

Ralplan

99

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

技能
Yeachan-Heo

Cli Creator

100

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.

技能
openai

Context Mode Ops

100

使用并行子代理军队管理 context-mode GitHub 问题、PR、发布和营销。为每个任务编排 10-20 个动态代理。在分类问题、审查 PR、发布版本、撰写 LinkedIn 帖子、宣布发布、修复错误、合并贡献、验证 ENV 变量、测试适配器或同步分支时使用。

技能
mksglu

Kotlin Mcp Server Generator

100

Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library.

技能
github

Spec to Repo

100

Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I have requirements and need a codebase', or provides a natural-language project specification and expects a complete, runnable repository. Stack-agnostic: Next.js, FastAPI, Rails, Go, Rust, Flutter, and more.

技能
alirezarezvani