Explorar skills
31.375 skills encontradas
x-audit-perf
独立性能巡检 skill。不在 x-dev → x-verify → x-qa-gate 主流程内,由用户手动触发或在大里程碑后调用。 调子 agent 做全项目视角的性能审查:N² 嵌套、不必要循环、大对象拷贝、同步阻塞、数据库 N+1、缓存失效、不必要的 await。 触发:用户说"性能巡检"、"audit perf"、"看看有没有性能问题"、"perf review",或大版本发布前。
confidence-scorer
Assign confidence scores (0-100) to every claim in a response. Helps users understand which parts are verified facts and which are educated guesses. Use when the user needs to know how much to trust each part of the answer.
legal-matter-tracker
Scan local workspace folders by client or case name and assemble a chronological timeline of events with key facts. No external integrations required. Triggers: 'matter tracker', 'case timeline', 'track [client]', 'timeline for [case]', 'client history', 'matter report', 'summarize [client] matter', 'трекер дела', 'хронология дела', 'история клиента', 'что было по [клиент]', 'отчёт по делу', 'хрон
experience-and-design-system
Anti-AI-slop design system for distinctive, premium interfaces. Bold typography, dark-first #060610, fluid clamp() type, cascade layers + native nesting + container queries, OKLCH color, @starting-style, View Transitions API, DTCG tokens.
zendesk-triage
Pull open tickets from [Zendesk](https://composio.dev/toolkits/zendesk) and triage by priority, category, and SLA status
simmer-judge
Judge subskill for simmer. Scores a candidate artifact against user-defined criteria on a 1-10 scale and produces ASI (highest-leverage direction) for the next generator round. Supports judge-only, runnable evaluator, and hybrid evaluation modes. Do not invoke directly — dispatched as a subagent by the simmer orchestrator.
operating-system
Supreme policy layer governing all Claude Code behavior. Autonomy, one-line prompt interpretation, speed standards, emphasis signal processing, cross-skill coordination, done definitions, conflict resolution. Loaded every prompt.
goal-supervisor
The mission-level supervisor. One level above goals. Reads the user's mission charter and the most-recently-completed goal's artifacts, then decides whether to PROCEED (draft + activate the next goal), declare the mission DONE, or ESCALATE to the user. Use this skill when the user invokes /goal-supervisor after a goal completes, or when running a multi-goal arc where each next goal's shape is info
outreach-campaign
Set up customer outreach sequences via [Lemlist](https://composio.dev/toolkits/lemlist), [Reply.io](https://composio.dev/toolkits/reply-io), or [Woodpecker](https://composio.dev/toolkits/woodpecker-co)
mac-software-storage-cleanup-cn
审计 macOS 已安装软件占用并执行分级清理。当用户提出“检查安装了哪些软件”“列出软件占用大小”“清理优先级 1 缓存和模拟器数据”或“给出可回收空间建议”等磁盘治理需求时使用。
generate-closure-report
Generates a project closure report aggregating data from charter, plan-fact report, risk register, and lessons learned. Last artifact of the Closing phase. Summarizes project outcomes, deviations, realized risks, and lessons.
tailwind
Tailwind CSS 스타일링 규칙. className 패턴, cn() 유틸 사용, tailwind.config, dark mode.