Skill Optimizer Lawvable
插件 警告 活跃Analyze work sessions and propose improvements to skills based on corrections and edge cases
To help users refine and improve their AI skills by automatically learning from their interactions and feedback.
功能
- Analyze conversation sessions for skill improvement signals
- Propose specific, actionable improvements to skills
- Apply quality criteria (completeness, precision, atomicity, stability)
- Support manual and automatic modes for improvement capture
- Track skill modifications via a natural language changelog
使用场景
- Capturing user corrections to existing skills
- Improving skills based on identified edge cases
- Refining skills with user-accepted outputs
- Automatically enhancing skills during a work session
非目标
- Guessing user intent or inferring requirements
- Modifying skills without explicit user approval
- Adding vague or subjective instructions to skills
Documentation
- info:Configuration & parameter referenceThe README mentions enabling automatic mode by adding a hook to `.claude/settings.local.json`, but does not detail other configuration options or parameters.
License
- critical:License usabilityThe plugin is licensed under the GNU Affero General Public License v3, which has strong copyleft provisions and may not be suitable for all use cases, especially in commercial environments without making the entire system open-source.
安装
请先添加 Marketplace
/plugin marketplace add lawvable/awesome-legal-skills/plugin install skill-optimizer-lawvable@lawvable质量评分
警告类似扩展
Obey
100让 Claude 真正遵循您的规则。通过自然语言保存规则，通过钩子强制执行规则，跨会话记忆规则。
Karpathy Coder
100Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, keep it simple, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check slash command, and a pre-commit hook. All tools stdlib-only.
Autoresearch Agent
100Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).
Discovery Interview Prep
100Plan customer discovery interviews with the right goal, segment, constraints, and method.
Oh My Claudecode
99Multi-agent orchestration system for Claude Code
Agenthub
99Multi-agent collaboration plugin for Claude Code. Spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any problem that benefits from diverse solutions. Evaluate by metric or LLM judge, merge the winner. 7 slash commands, agent templates, git DAG orchestration, message board coordination.