发现 Skills

网页设计与部署。生成精美的单页 HTML 网页（报告、落地页、数据可视化等），支持一键部署到 Cloudflare Pages。使用 Tailwind CSS + Chart.js + Font Awesome 技术栈。当用户要求制作网页、生成报告页面、创建落地页、数据可视化展示、部署网页到线上时使用。

Write a 5-email onboarding sequence for new subscribers. Each email has a clear purpose — welcome, quick win, origin story, best resources, and next steps.

Guide founders through startup idea generation and evaluation using Paul Graham's methodology from Y Combinator. Use when users want to brainstorm startup ideas, evaluate existing ideas, find problems worth solving, or overcome mental blocks like schlep blindness. Helps identify ideas that are organic, have deep demand, and can grow into successful startups.

Agentic PRD batch: when user says 'process PRDs' or 'run batch from PRD folder'; implement per spec; update status; write outcome; reference PRD schema + external-agent guide. Use when editing .agent/queue/**, prds/**, *.prd.md.

Decision tree / reverse prompt workflow - AI prompts user one question at a time with 4 options (A-D), preferred choice + rationale; build context for maximum impact. Use when user says 'decision tree', 'run the decision tree', 'reverse prompt', or 'reverse prompt workflow'; or when editing .agent/queue/**, PRD.md, *.prd.md.

Create or import Agent Skills–compliant skills for this framework; import skills from Anthropic or elsewhere; export framework skills for use in other hosts. Use when creating a new skill, importing an existing skill (e.g. anthropics/skills), adapting a doc into a skill, or making skills interchangeable across ecosystems.

Install developer tool components from the Elements registry. Use when a user needs JSON viewers, API response displays, code diff viewers, CLI output renderers, environment editors, error boundaries, webhook testers, or schema viewers. Triggers on 'devtools', 'json viewer', 'API response', 'webhook tester', 'env editor', 'code diff', 'schema viewer', 'error boundary', 'CLI output'.

Skill for configuring AI Chat in Orchard Core using the CrestApps AI Chat module. Covers chat profiles, admin chat UI, frontend chat widgets, provider connections, and the AI Agent module for task automation.

Draft professional emails for various contexts including business, technical, and customer communication. Use when the user needs help writing emails or composing professional messages.

PASSIVE: Use cmux sidebar metadata to display rich status information — status pills, progress bars, and structured log entries — visible at a glance in the workspace sidebar. Use automatically during multi-step tasks, builds, deploys, and any operation where progress visibility helps. Requires cmux.

Distributed task-allocation protocol in which agents negotiate task assignments via contract bidding

Formal verification approach to LLM evaluation ensuring correctness and consistency in automated judging

Agent skill for calling MCP servers through MCPorter. Use when you need to call MCP tools.

Nutrition planning and meal prep for Tory Owens. Bridges the gap between knowing macros are off and actually hitting them. Generates daily/weekly meal plans targeting P 210g / C 130g / F 71g / 2,000 kcal. Creates grocery lists. Adapts to real life constraints (busy weekdays, family dinners, meal prep). Triggers on: "Meal plan", "What should I eat", "Macro plan", "Grocery list", "Meal prep", "Hit my macros", "What's for dinner", "Plan my meals", "High protein meals", "Meal ideas", "Food plan", "Nutrition plan", "Help me eat right". The plan that sits in a spreadsheet loses. The plan that's simple enough to follow wins.

Social feed with batch queries, cursor pagination, trending algorithms, and engagement tracking. Efficient database queries for infinite scroll feeds.

Brief description of what this skill does and when to use it. Be specific about capabilities and use cases to help agents decide when to load this skill.

Guides cyber threat intelligence (CTI)—collection and vetting of intel from OSINT, commercial feeds, and ISACs; threat actor and campaign analysis; IOC/TTP production with MITRE ATT&CK mapping; STIX/TAXII and sharing concepts; strategic, tactical, and operational intel briefs; fusion with hunts and incident response; confidence scoring and source handling. Use for CTI, threat intelligence, threat actor profiling, IOC production, TTP analysis, intel briefs, STIX, ISAC reporting, campaign analysis, APT reporting—not proactive hunt execution (threat-hunter), SOC alert triage (soc-analyst), adversary simulation ops (red-team-specialist), incident command (incident-responder), or legal conclusions.

PHASE 5 of the Planitor pipeline. Dual-LLM: Model A (analytical) and Model B (creative) generate independent strategies from distinct approaches (analytical-structured vs. creative-disruptive). Planitor synthesizes the best of both into a final STRATEGY.json.

Control smart home devices via MQTT on the home lab. Toggle lights, read sensors, trigger automations, and manage Tasmota/Shelly devices through the Mosquitto broker on server. Use when: "turn on lights," "mqtt," "smart home," "toggle device," "read sensor," "home automation," "tasmota," "shelly," "mosquitto."

Per-task context survey — reads specs/ and CONVENTIONS.md, maps the current lifecycle phase, and suggests the next skill to invoke. Use at the start of any new task, when returning to a project after a break, or when unsure what to do next.

Add structured JSON logging, observability commands, and idempotent setup scripts to a project. Use when a project needs production-readiness instrumentation, when user wants structured logging, or as a production-readiness gate at any phase of development.

Edit and improve documents by restructuring sections, improving clarity, and tightening prose. Use when a user wants to edit, revise, restructure, or improve any document — including specs/files, articles, READMEs, or technical writing.

**UNIVERSAL TRIGGER**: Use when user wants to ANALYZE Kubernetes cluster resource efficiency. Common patterns: - "analyze/check/get cluster efficiency", "show cluster resources" - "list/display/retrieve node utilization", "fetch cluster metrics" - "проанализируй эффективность кластера", "проверь ресурсы кластера" - "find over-provisioned workloads", "найди переоцененные ресурсы" - "why nodes are not consolidating", "почему ноды не консолидируются" - "optimize cluster costs", "оптимизируй затраты на кластер" Specific analysis types supported: **Nodes Utilization**: - "show node utilization", "check nodes efficiency" - "low utilization nodes", "ноды с низкой утилизацией" - "node consolidation candidates", "кандидаты на консолидацию" ⚙️ **Workloads Efficiency**: - "find over-provisioned pods", "переоцененные workloads" - "CPU/memory efficiency", "эффективность CPU/памяти" - "requests vs actual usage", "requests vs фактическое потребление" **Karpenter Analysis**: - "karpenter consolidation status", "статус консолидации" - "consolidation blockers", "блокеры консолидации" - "nodepool configuration", "конфигурация NodePool" **Cost Optimization**: - "cluster cost optimization", "оптимизация затрат" - "resource savings recommendations", "рекомендации по экономии" - "YAML resource patches", "YAML патчи ресурсов" **Historical Analysis** (with Prometheus): - "analyze with prometheus", "historical resource usage" - "7-day resource trends", "тренды за 7 дней" TRIGGERS: cluster efficiency, cluster resources, node utilization, workload efficiency, karpenter consolidation, over-provisioned, resource optimization, cost optimization, kubernetes resources, k8s efficiency, эффективность кластера, утилизация нод, переоцененные ресурсы, оптимизация затрат, консолидация, анализ кластера, cluster analysis, resource analysis, node analysis, pod resources This skill provides comprehensive Kubernetes cluster resource efficiency analysis using a bash script that works with any cluster context.

**UNIVERSAL TRIGGER**: SAVE/PUBLISH/EXPORT implementation plan TO GitHub issue for separate session execution. Common patterns: - "save/publish/export plan to issue" - "create issue from plan", "plan to github" - "сохрани план в issue", "создай issue из плана" **Save Plan**: - "save plan to issue", "publish plan to github" - "сохрани план в issue", "экспортируй план" **Create Issue from Plan**: - "create issue from plan", "plan as issue" - "создай issue из плана", "план в задачу" **Execute Later**: - "save for separate session", "execute plan later" - "сохрани для отдельной сессии", "выполнить потом" **Should NOT activate**: - General "create issue" without plan context - Reading existing issues - Working with issue checkboxes TRIGGERS: plan to issue, save plan, export plan, publish plan, plan as issue, issue from plan, plan to github, сохрани план, план в issue, экспорт плана, план в задачу, save for later, execute later, separate session, сохрани для сессии, выполнить потом, план в github