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…
This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
Claude Code
$ npx -y skills add LiHongwei-cn/lihongwei-cn --skill agents-md --agent claude-code
Codex
$ npx skills add LiHongwei-cn/lihongwei-cn --skill agents-md -a codex -y
Cursor
$ npx skills add LiHongwei-cn/lihongwei-cn --skill agents-md -a cursor -y
Gemini CLI
$ npx skills add LiHongwei-cn/lihongwei-cn --skill agents-md -a gemini-cli -y
GitHub Copilot
$ npx skills add LiHongwei-cn/lihongwei-cn --skill agents-md -a github-copilot -y
OpenCode
$ npx skills add LiHongwei-cn/lihongwei-cn --skill agents-md -a opencode -y
Windsurf
$ npx skills add LiHongwei-cn/lihongwei-cn --skill agents-md -a windsurf -y
name: agents-md description: This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation. risk: unknown source: community
AGENTS.md is the canonical agent-facing documentation. Keep it minimal—agents are capable and don't need hand-holding. Target under 60 lines; never exceed 100. Instruction-following quality degrades as document length increases.
1. Create `AGENTS.md` at project root 2. Create symlink: `ln -s AGENTS.md CLAUDE.md`
Analyze the project to understand what belongs in the file:
1. **Package manager** — Check for lock files (`pnpm-lock.yaml`, `yarn.lock`, `package-lock.json`, `uv.lock`, `poetry.lock`) 2. **Linter/formatter configs** — Look for `.eslintrc`, `biome.json`, `ruff.toml`, `.prettierrc`, etc. (don't duplicate these in AGENTS.md) 3. **CI/build commands** — Check `Makefile`, `package.json` scripts, CI configs for canonical commands 4. **Monorepo indicators** — Check for `pnpm-workspace.yaml`, `nx.json`, Cargo workspace, or subdirectory `package.json` files 5. **Existing conventions** — Check for existing CONTRIBUTING.md, docs/, or README patterns
Which tool and key commands only:
## Package Manager Use **pnpm**: `pnpm install`, `pnpm dev`, `pnpm test`
Per-file commands are faster and cheaper than full project builds. Always include when available:
## File-Scoped Commands | Task | Command | |------|---------| | Typecheck | `pnpm tsc --noEmit path/to/file.ts` | | Lint | `pnpm eslint path/to/file.ts` | | Test | `pnpm jest path/to/file.test.ts` |
Always include this section. Agents should use their own identity:
## Commit Attribution AI commits MUST include:
Co-Authored-By: (the agent model's name and attribution byline)
Example: `Co-Authored-By: Claude Sonnet 4 <noreply@example.com>`
Project-specific patterns agents must follow. Keep brief.
Add only if truly needed:
Omit these:
# Agent Instructions ## Package Manager Use **pnpm**: `pnpm install`, `pnpm dev` ## Commit Attribution AI commits MUST include:
Co-Authored-By: (the agent model's name and attribution byline)
## File-Scoped Commands | Task | Command | |------|---------| | Typecheck | `pnpm tsc --noEmit path/to/file.ts` | | Lint | `pnpm eslint path/to/file.ts` | | Test | `pnpm jest path/to/file.test.ts` | ## API Routes [Template code block] ## CLI | Command | Description | |---------|-------------| | `pnpm cli sync` | Sync data |
MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.
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…
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…
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…
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 /…
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…
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…
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…