Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Audit and improve project memory files (CLAUDE.md, AGENTS.md, .claude.local.md) — assess against a quality rubric, then apply additions and removals. This skill SHOULD be used when the user asks to audit, improve, edit, fix, tighten, rewrite, or update a memory file, or to check whether one is too long, stale, or bloated.
Seedance 提示词审核技能。用于审核阶段三分镜师产出的 Seedance 2.0 动态提示词，通过逐条比对、脑内预演和评分制确保规范性、运镜合理性、叙事连贯性。
A Webflow University guided onboarding skill for anyone getting started with the Webflow MCP. Checks your Webflow connection, helps you choose a real workflow to try, coaches prompt writing, and supports you through your first MCP run.
Model Context Protocol server exposing 53 tools, 3 resource types, and 3 prompts for AI agent consumption — quoting, building transactions, fee management, analytics, AMM operations, social fees, wallet operations over stdio transport.
Assess your codebase's resistance to AI-assisted development tools.
Loop autônomo de experimentos que otimiza qualquer arquivo por uma métrica mensurável. Inspirado no autoresearch do Karpathy. O agente edita um arquivo alvo, executa uma avaliação fixa, mantém melhorias (git commit), descarta falhas (git reset) e faz loop indefinidamente. Use quando: o usuário quer otimizar velocidade de código, reduzir tamanho de bundle/imagem, melhorar taxa de aprovação em testes, otimizar prompts, melhorar qualidade de conteúdo (headlines, copy, CTR) ou executar qualquer loop de melhoria mensurável. Requer: um arquivo alvo, um comando de avaliação que gere uma métrica e um repositório git.
Executive decision-maker who processes escalated beads, resolves agent deadlocks, allocates resources across the org chart, and produces weekly executive summaries. Use when a bead is stuck at the top of the escalation chain, agents disagree on priority or approach, resources need reallocation, or a strategic status report is needed. Handles approve/deny/reassign/cull decisions, org health monitoring, and cross-team coordination via loomctl.
25 skills e plugins avançados de engenharia para Claude Code. Design de agentes, RAG, servidores MCP, CI/CD, design de banco de dados, observabilidade, auditoria de segurança e gerenciamento de releases.
Uso avançado do Claude Code: criação de skills customizadas, subagentes paralelos, worktrees para features isoladas, gestão de contexto e configurações avançadas de CLAUDE.md para máxima produtividade.
Audit a website against the Forter Agentic Readiness Guide. Loads the 25 weighted rubrics in `audit/`, probes the target site (and optional source code), scores each guideline Pass/Partial/Fail/N/A with sub-check granularity, and produces a prioritized fix report. Use when a user asks "score my site against the agentic readiness guide", "audit https://… for agent readiness", or "what do I need to fix to be agent-ready".