Cida

Q: What does the Cida skill do?

辞达 · 现代中文高质量对话型表达与平台内容设计引擎。用于中文写作、重写、润色、诊断、 口述/访谈成文、书面自然化、公众号/小红书/知乎/微博/视频口播/播客/社群等场景适配， 以及按用户真实文本校准个人风格。先确定事实与立场边界，再建立平台任务契约、比较表达策略、 设计读者价值兑现，最后完成文本质量与平台适配双自检。不做去AI味检测对抗、虚假钩子、 平台流量承诺或任何在世作者的个人风格模仿。

辞达 · 现代中文高质量对话型表达与平台内容设计引擎。用于中文写作、重写、润色、诊断、口述/访谈成文、书面自然化、公众号/小红书/知乎/微博/视频口播/播客/社群等场景适配，以及按用户真实文本校准个人风格。先确定事实与立场边界，再建立平台任务契约、比较表达策略、设计读者价值兑现，最后完成文本质量与平台适配双自检。不做去AI味检测对抗、虚假钩子、平台流量承诺或任何在世作者的个人风格模仿。

108 stars 8 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add mizzlelover/cida --skill cida

Manual install

git clone --depth 1 https://github.com/mizzlelover/cida.git /tmp/cida
mkdir -p ~/.claude/skills
cp -r /tmp/cida/. ~/.claude/skills/cida

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 辞达 · 现代中文高质量对话型表达引擎

> 子曰：“辞达而已矣。”——《论语·卫灵公》
>
> 苏轼《答谢民师书》：“能使是物了然于心者，盖千万人而不一遇也，而况能使了然于口与手者乎？是之谓辞达。”

辞达理解谁在说、对谁说、为什么说、在什么发布情境中说，再把有价值的思想用自然、清楚、
亲近、有逻辑、有品质的现代中文表达出来。平台不是成稿后的包装层，而是表达决策的一部分。

**最高原则：降低语言门槛，不降低思想门槛。**

## 0. 立即执行的主流程

收到写作或改写请求后，按顺序内部完成；短句和局部微调可压缩候选与诊断，但不得跳过保真：

```text
1. 任务路由       → 写作 / 重写 / 段落优化 / 口述成文 / 自然化 / 平台适配 / 风格校准
2. 边界与素材     → 固定事实、证据、立场、分寸、授权与声音；检查素材上限
3. 平台任务契约   → 平台 × 内容形态 × 入口 × 读者关系 × 目标 × 材料 × 篇幅/时长
                    按 workflows/platform_task_contract.md 建立；未指定发布场景用 generic
4. 诊断           → 完成十二项诊断（§3）；默认内部完成，Explain 或用户要求时展开
5. 正向策略检索   → 先读平台原生规则与最相关的 1–3 个机制，再查当前方案的反模式风险
6. 候选与价值设计 → 完整写作/深度重写/平台适配生成 2–3 个实质候选并选择；
                    标出入口相关性、价值约定、首次兑现、后续推进与完成价值
7. 写作/重写      → P0 意义素材 → P1 平台结构与价值兑现 → P2 流转语域
                    → P3 节奏修辞 → P4 打磨；不得先写通用稿再换平台包装
8. 双重自检       → 文本质量 + 平台适配（§7）；失败则回到对应阶段，不在末端补贴钩子
9. 交付说明       → 实质改写简述关键取舍、文本/任务依据、相关机制及适用边界
```

落笔前按来源读取语域文件：口述/转录整理为文章时必读
`knowledge/register/oral-register-behaviors.md`；其他任务只在语域问题相关时读取。
视频、播客和演讲不得机械套用“口述整理为书面文章”的规则。

### 工作流路由

| 任务 | 工作流文件 |
|---|---|
| 所有发布场景、跨平台任务 | `workflows/platform_task_contract.md` |
| 主题 → 成文 | `workflows/topic_to_article.md` |
| 整篇重写 | `workflows/rewrite_article.md` |
| 深度重写 / 高模板修复 | `workflows/deep_rewrite.md` |
| 段落优化 | `workflows/rewrite_paragraph.md` |
| 口述/转录 → 文章 | `workflows/oral_to_article.md` |
| 书面 → 更自然 | `workflows/diagnose_text.md`（自然化专项） |
| 已有内容 → 平台版本 | `workflows/platform_adaptation.md` + `platforms/<平台>/` |

Read the full skill on GitHub

Details

Skill name: cida
Repository: mizzlelover/cida
License: MIT
Repo updated: 24 October 2026

FAQ

What does the Cida skill do?

How do I install the Cida skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mizzlelover/cida --skill cida. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Cida popular?

It lives in mizzlelover/cida, which has 108 GitHub stars and 8 forks.

Related skills

Fable Mode

106

cozytab/fable5-mode

A work-discipline protocol that makes Opus 4.8 (or any non-frontier model) operate at Fable-5-grade quality. Core idea — output quality = model capability x work discipline: spend extra orchestration to buy single-pass quality via six levers (plan gate, small-card execution, adversarial self-check, real-product verification, context hygiene, checkpoint autonomy). Activate ONLY on an explicit request — the user names the mode ("use fable mode", "enable fable-mode", "work like Fable 5", "rigorous mode", or the Chinese "用 fable 模式"、"开 fable-mode"、"像 Fable 5 一样做"、"严谨模式") — or when the project is a

AI, LLMs & Agents

Penthera

danoszz/penthera

Offline cyber security agent for the user's own apps and AI coding tools, run locally with the Penthera CLI; open R&D, measured in public. Sets it up in one command ("set up penthera in this repo"). Scans the user's own live URL and repo (TLS, headers, auth, OpenAPI, secrets incl. AI keys, opt-in injection); checks npm and Python dependencies offline ("is this dependency safe?", "what changed in my deps?", "install X safely", "any AGPL in our deps?"); blocks secrets and risky agent config before commit ("add a pre-commit hook"); audits AI tooling ("audit my MCP servers / skills / hooks", "chec

AI, LLMs & AgentsIn 1 list13

Reap

thousandflowers/skillreaper

Report how much of the context this agent loads is never used - unused skills, MCP servers, subagents, hooks and always-loaded prose - measured from real session transcripts. Use when asked why the context window is full, what is wasting tokens, or what is safe to remove.

AI, LLMs & AgentsIn 2 lists

Claude for Safari

100

SDLLL/claude-for-safari

Control the user's real Safari browser on macOS through AppleScript, page JavaScript, screenshots, and carefully verified System Events input. Use when an agent needs to inspect or operate the user's existing Safari tabs and login sessions, including reading pages, navigating, clicking, filling non-sensitive forms, taking screenshots, observing page-level fetch/XHR metadata, or troubleshooting Safari-specific UI behavior.

AI, LLMs & Agents16

AI Tutor

ShawhinT/ai-tutor-skill

Use when user asks to explain, break down, or help understand technical concepts (AI, ML, or other technical topics). Makes complex ideas accessible through plain English and narrative structure.

AI, LLMs & Agents45

Prompt Sensei

109

chengzhongwei/Prompt-sensei

Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.

AI, LLMs & Agents10

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.