搜索

design-tokens

430design-ui

根据所选美学理念生成设计令牌文件（CSS变量或Tailwind配置），包含亮色和暗色模式调色板、间距比例、字体层级和组件级令牌。适用于启动新项目、建立视觉系统、设置令牌或提及“令牌”或“设计系统”时使用。

julianoczkowski

loop-design-check

243Ktesting-qa

Design a goal-oriented agent loop, and review it for the ways loops go wrong — spinning and burning tokens, Goodhart-gaming the verifier, or running a wrong answer to completion. Two actions: (1) WRITE a loop — gate whether to build it, define a machine-decidable goal, pick the loop type, pick a skeleton; (2) REVIEW a loop — run it past five failure modes plus decidability, boundaries, fallback, judge independence, and keep-judgment-with-the-human red lines. Use when designing an autonomous agent loop, or when you already have one and worry it will spin, cheat, or run a wrong answer to the end. Complements the mechanism-layer loop skills (autonomous-loops, continuous-agent-loop) by covering the judgment layer they don't. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge。English triggers: design an agent loop, write a loop, check a loop, loop review, prevent a runaway loop, goal-oriented loop, decidable goal, plan/build/judge.

motion-patterns

240Kfrontend

Production-ready animation patterns for React / Next.js — button, modal, toast, stagger, page transitions, exit animations, scroll, and layout — built on motion-foundations tokens and springs. Use when animating a specific UI element in React or Next.js — button, modal, toast, stagger, page transition, or scroll.

motion-foundations

240Kfrontend

Motion tokens, spring presets, performance rules, device adaptation, accessibility enforcement, and SSR safety for React / Next.js using motion/react. Foundation layer — all other motion skills depend on this. Use when setting up motion tokens, spring presets, reduced-motion handling, or SSR-safe animation in React or Next.js.

cost-tracking

240Kprompting-reasoning

Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date.

cost-tracking

238Kprompting-reasoning

从本地 ECC cost-tracker 指标日志中读取并分析 Claude Code 的 Token 消耗量、费用及预算情况。当用户询问花费、开销、使用量、Token 消耗、预算上限，或要求按模型、会话、日期统计费用明细时使用。

motion-patterns

237Kfrontend

适用于 React / Next.js 的开箱即用动画范式——覆盖按钮、弹窗、Toast 提示、交错动画、页面过渡、退场动画、滚动联动及布局动画——基于 motion-foundations 的 Design Tokens 与 Spring 弹簧参数构建。

motion-foundations

237Kfrontend

基于 motion/react 实现 React / Next.js 的动效 Token、弹簧预设、性能规范、设备适配、无障碍强制约束及 SSR 水合安全保障。这是动效系统的底层基石——所有其他 Motion Skill 均依赖此技能。

claude-api

153Kresearch-knowledge

Claude API / Anthropic SDK 权威参考手册 —— 涵盖模型 ID、计费价格、参数设置、流式传输、工具调用 (tool use)、MCP、Agent 开发、缓存机制 (caching)、Token 统计以及模型迁移。触发条件 —— 在打开目标文件之前先阅读本文件；切勿因其“看似只有一行”而跳过 —— 当满足以下任意情况时触发：提示词中包含任何形式的 Claude/Anthropic 名称（如 Claude、Anthropic、Fable、Opus、Sonnet、Haiku、`anthropic`、`@anthropic-ai`、`claude-*`、`us.anthropic.*`、`[1m]`）；用户咨询大模型相关问题（如价格、模型选择、额度限制、缓存）—— 严禁仅凭记忆回答；或者任务属于大模型范畴且未明确供应商（如 agent/MCP/工具定义/多 Agent 协同/RAG/LLM 评估/Computer Use；基于自然语言生成/总结/提取/分类/改写/对话；排查拒答、截断、流式传输、工具调用、Token 问题）。跳过条件 —— 仅当明确使用其他供应商时跳过（优先级高于所有触发条件）：用户提问中提到了 OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama；或者对项目执行 `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` 找到了匹配项（如果用户未指定供应商，请先执行该 grep 命令 —— 切勿直接读取文件）。

anthropics

design-system

106Kfrontend

令牌架构、组件规范和幻灯片生成。三层令牌（原始→语义→组件）、CSS变量、间距/排版比例、组件规范、策略性幻灯片创建。用于设计令牌、系统化设计、符合品牌规范的演示文稿。

nextlevelbuilder

design

106Kdesign-ui

综合设计技能：品牌标识、设计令牌、UI样式、Logo生成（55种风格，Gemini AI）、企业形象识别系统（50个交付物，CIP样机）、HTML演示文稿（Chart.js）、横幅设计（22种风格，社交/广告/网页/印刷）、图标设计（15种风格，SVG，Gemini 3.1 Pro）、社交照片（HTML→截图，多平台）。操作：设计Logo、创建CIP、生成样机、制作幻灯片、设计横幅、生成图标、创建社交照片、社交媒体图片、品牌标识、设计系统。平台：Facebook、Twitter、LinkedIn、YouTube、Instagram、Pinterest、TikTok、Threads、Google Ads。

nextlevelbuilder

slides

106Kdesign-ui

使用 Chart.js、设计令牌、响应式布局、文案公式和情境化幻灯片策略创建战略性 HTML 演示文稿。

nextlevelbuilder

caveman-explore

Read-only repository explorer. Use PROACTIVELY for cold-start exploration, broad cross-file localization, or when a direct search has failed and you need to find where something lives. Skip it when the issue already names the exact file or symbol, or a previous turn already returned usable file:line evidence. Returns only compact path:line citations; its reads and greps never enter the main conversation.

caveman-optimize

Turn Caveman's exact report-only repository observations into an operator-chosen optimization candidate with a paired baseline/candidate evaluation. Use when the user asks to inspect an optimization observation, evaluate a candidate change, or act on the current Caveman optimization report. Require a logged-in Caveman CLI connection and explicit approval; never infer money or actuation from a profile.

investigate-first

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

verify-and-stop

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

surgical-patch

Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

safe-refactor

Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

caveman-learn

Close the loop on a Caveman learn report — review the ranked token sinks and apply cost-lowering fixes (trim config, offload recurring context to cavemem) with per-edit consent. Use when the user runs "caveman learn", asks to lower their agent's token cost, wants to trim a heavy CLAUDE.md, or wants to offload context they re-paste every session into cavemem.

lean-build

Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.

caveman-evidence-review

Review Caveman Cloud evidence read-only: costs, Cave Score, Cave Plan, workflows, traces, latency, errors, compression, routing, and verified savings. Use when the user asks what Caveman found, where LLM spend goes, why cost or quality changed, which workflows need attention, or asks for a trace or analytics review. Prefer Caveman MCP tools; fall back to CLI JSON.

caveman-discover

Find every LLM workflow in the current repository and label it, so Caveman Cloud groups spend by what the code actually does (support-reply, nightly-digest) instead of one anonymous bucket. Use when the user pastes the Caveman discovery prompt, says "discover workflows", or asks to break LLM spend down by workflow. The repo should already route through the Caveman gateway (the caveman-setup skill does that part).

caveman-manage

Inspect Caveman Cloud's eval-gated experiment lifecycle and block unsafe execution. Use when the user asks to start, approve, cancel, promote, or roll back a Caveman experiment, or asks what action an experiment's evidence supports. Read evidence first; do not execute lifecycle mutations until server-authoritative transition and evidence gates ship.