Plugins

Create and validate production-grade agent skills with 100-point marketplace grading. Supports creation workflows, eval-driven development, and auto-fix for spec compliance.

Meza's skill creator

Create and update portable agent skills.

Agent Skillの設計・作成・パッケージング（skill-authoring-guide）と、評価・ベンチマーク・イテレーション改善（skill-evaluator）を支援するプラグイン。SKILL.mdの構成、段階的開示パターン、ワークフロー設計、eval・収束判定・description最適化のベストプラクティスを網羅。

Packages new commands/agents/domains/role-skills into this repo's convention and syncs the catalog. Provides: skill-creator. Requires: dependency-resolver.

새로운 스킬 생성, 기존 스킬 수정/개선, 스킬 성능 측정 및 최적화를 위한 스킬 생성기.

Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.

from m-brady/claude-plugins

from macnversion/skills

Create, test, and iteratively improve Claude Code skills with the official lean coaching loop, an eval harness for benchmarking with variance analysis, and automated description-trigger optimization

Interactive MCP App dashboard: quality checks, token budgets, freshness, and repo hygiene

Self-contained toolkit to author Claude Agent Skills — create, score, refactor, tune, dogfood.

Claude Codeプラグイン用スキル作成のベストプラクティス

Grade agent skills from local conversation history (efficiency + code quality), draft skill edits, and render a shareable HTML report. Runs entirely locally.

Evaluate Claude Code skills against best practices. Tracks skill usage globally via hooks.

Authoring skills, pattern references, and governance guides for the skill factory

Find, compare, vet, and prepare agent-usable skills, tools, MCP servers, workflows, packages, documentation sources, and capability stacks.

Skillを自動的に成長させるためのプラグイン。セッション中のユーザー発言・承認コマンド・スキル発火をセッション別ディレクトリに記録し、セッション終了時にやり取りの要約も書き出す。蓄積されたログから新しいスキルを作成する3つの分析スキル（複数セッション横断のパターン検出、単一セッションからのスキルdraft生成、承認コマンド分析）を提供する。

from susuyan/skills

Local, model-agnostic automatic skill injection: embeds the prompt locally, ranks it against skill descriptions, and injects the matched skill via UserPromptSubmit/PostToolUse/SessionStart hooks (ski). Requires the `ski` binary — cargo install --path .

Tools for auditing and improving Claude Code skill definitions

Design, evaluate, and improve Agent Skills with intent compilation, isolated evaluation, and deterministic validation

Skill 创建预检与可靠性验收工具，支持旧版指令失稳识别、硬要求来源发现、Ed25519-signed 外部基线与 held-out、逐约束追踪、验证模态与产物阶段匹配、候选/producer 绑定运行证据、最终回执验签、多轮漂移门禁、七层 Harness、业务流和安全风险审查

Maintenance tools for skills repos: validation, quality, freshness, upstream detection, best practices review, wiki-sanity lint

Skill management utilities — load, install, and register skills into the local plugin system

Three-tier activation manager for agent assets (skills, subagents, commands, workflows): keep a large library dormant at zero context cost and activate only what each project needs, via a symlink/junction/tracked-copy ladder with drift detection and repair.

Manage your Claude Code skills and plugins from inside any project — switch which plugins are active, publish and sync local skills to a central marketplace, and diagnose and auto-repair a broken setup. Adapts to any repo layout and delegates skill authoring to the native skill-creator.

管理 Claude Code、Codex 和 OpenClaw Skills/Commands 的安装、同步、卸载和列表查看

Personal Agent Skills collection for Claude Code and Codex.

Slim and restructure a SKILL.md without losing behavior, trigger coverage, anchors, or facts.