cheat-on-content
给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…
No-code automation democratizes workflow building. Zapier and Make
$ npx -y skills add LiHongwei-cn/lihongwei-cn --skill zapier-make-patterns --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/zapier-make-patternsContext preview
The summary Claude sees to decide when to auto-load this skill.
No-code automation democratizes workflow building. Zapier and Make
name: zapier-make-patterns description: No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. risk: unknown source: vibeship-spawner-skills (Apache 2.0) date_added: 2026-02-27
No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.
This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power and cost-efficiency (visual branching, operations-based pricing).
Critical distinction: No-code works until it doesn't. Know the limits.
Single trigger leads to one or more actions
**When to use**: Simple notifications, data sync, basic workflows
""" [Trigger] → [Action] e.g., New Email → Create Task """
""" Zap Name: "Gmail New Email → Todoist Task"
TRIGGER: Gmail - New Email
ACTION: Todoist - Create Task
"""
""" Scenario: "Gmail to Todoist"
[Gmail: Watch Emails] → [Todoist: Create a Task]
Gmail Module:
Todoist Module:
"""
Chain of actions executed in order
**When to use**: Multi-app workflows, data enrichment pipelines
""" [Trigger] → [Action 1] → [Action 2] → [Action 3] Each step's output available to subsequent steps """
""" Zap: "New Lead → CRM → Slack → Email"
1. TRIGGER: Typeform - New Entry
2. ACTION: HubSpot - Create Contact
3. ACTION: Slack - Send Channel Message
4. ACTION: Gmail - Send Email
"""
""" [Typeform] → [HubSpot] → [Slack] → [Gmail]
"""
Different actions based on conditions
**When to use**: Different handling for different data types
""" ┌→ [Action A] (condition met) [Trigger] ───┤ └→ [Action B] (condition not met) """
""" Zap: "Route Support Tickets"
1. TRIGGER: Zendesk - New Ticket
2. PATH A: If priority = "urgent"
3. PATH B: If priority = "normal"
4. PATH C: Otherwise (catch-all)
"""
""" [Zendesk: Watch Tickets] ↓ [Router] ├── Route 1: priority = urgent │ └→ [Slack] → [PagerDuty] │ ├── Route 2: priority = normal │ └→ [Slack] → [Asana] │ └── Fallback route └→ [Slack: overflow]
"""
Clean, format, and transform data between apps
**When to use**: Apps expect different data formats
""" Common transformations:
1. Text manipulation:
2. Date formatting:
3. Numbers:
MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.
Repo: LiHongwei-cn/lihongwei-cn
给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…
提议并执行 rubric 或 bucket 升级。两种模式:**完整 rubric bump**(最高风险动作,5 步强制 + 跨模型审核)和 **--bucket-only 轻量重校**(只换 bucket 边界,不动 rubric 公式)。**Phase 2 强制走 cheat-score-blind…
cheat-on-content 的首次 onboarding 与脚手架创建器。统一流程——所有用户都走相同 5 阶段闭环,唯一区别是"发过视频的人"会在 init 时多一步:抓取已有视频建立历史 context(用于后续 cheat-seed 给更贴合的选题、更准的…
从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / script_patterns.md / rubric_notes.md。**这是工具最早期信号的来源**——cold-start…
把老用户的 .cheat-state.json 升级到当前 schema_version。读 migrations/registry.md 算迁移链,按顺序应用每一步迁移文件。幂等:跑两次结果一样。失败停在中间版本不前进。触发词:"迁移"/"升级 state"/"migrate"/"我的 state…
从复盘评论数据派生 / 刷新账号的受众画像,写入 audience.md。这是和 rubric 平行的第二个派生物——rubric 答"怎么打分",persona 答"谁在看"。cheat-seed 选题 / 写稿时读它。**audience.md 含实绩信号,cheat-score-blind…