De AI Writing

Detect, mark, and remove AI writing tics from Chinese and English drafts, so the text reads normally: denser, clearer, free of phrasing that obstructs reading. Use to de-AI a text, strip filler or clichés, or clear editing notes out of the body. Applies language- and model-specific rule tables and keeps the editing process out of the article. It rewrites style; personality and authorship stay out of scope.

9 stars 3 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add processmission/agent-skills --skill de-ai-writing
Manual install
git clone --depth 1 https://github.com/processmission/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/de-ai-writing ~/.claude/skills/de-ai-writing

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

From the SKILL.md

# De-AI Writing

**What this is.** It marks the passages that read as machine-written and removes them, so the text
becomes denser and clearer to read. Work happens in five passes: scan, mark, judge, remove, rescan. Each
pass yields style evidence, and authorship stays out of scope. The result reads ordinary rather than
personable, and it keeps every fact, mechanism, number, condition, sourced uncertainty, term, and failed
attempt in place. The information survives the cleanup intact.

**The standard** is the two rule tables: [rules-zh.md](references/rules-zh.md) and
[rules-en.md](references/rules-en.md). Each row is one pattern with its kind, probe, model family,
evidence key, and advice: the scanner executes every row to mark the text, and the agent reads the same
rows to judge each mark, and each table's header defines its kinds.

Clear tics by these tables. Every ban sits in a row with its evidence before the edit starts, and taste
adds nothing mid-edit. A fixed shape they do not list is measured by the discovery pass (part 3) and
becomes a new row once it proves to be a real tic. Each table covers its own language and lists its
contested tells at the top, to be reported rather than enforced; a pattern from one table applies to that
language only.

## 1. Judgment rules

### 1.1 Keep the editing process out of the body

Hard rule: while reading, keep three things apart.

- **Article facts** — objects, events, mechanisms, data, sources, supportable causal claims.
Read the full skill on GitHub

Details

Skill name
de-ai-writing
Path
skills/de-ai-writing/SKILL.md
License
MIT
Repo updated
8 October 2026

FAQ

What does the De AI Writing skill do?

Detect, mark, and remove AI writing tics from Chinese and English drafts, so the text reads normally: denser, clearer, free of phrasing that obstructs reading. Use to de-AI a text, strip filler or clichés, or clear editing notes out of the body. Applies language- and model-specific rule tables and keeps the editing process out of the article. It rewrites style; personality and authorship stay out of scope.

How do I install the De AI Writing skill?

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

Is De AI Writing popular?

It lives in processmission/agent-skills, which has 9 GitHub stars and 3 forks.

Related skills

Docs Translate Zh

9

processmission/agent-skills

Translate English technical documentation into faithful, natural Simplified Chinese with full-article context, reviewable RST or Markdown sources, and searchable bilingual terminology. Use for documentation translation, Chinese documentation maintenance, migration from fragmented PO translations, or verification of translated Sphinx sites and requested GitHub Pages deployment.

Writing & Content

Interactive Gdb Debugging

9

processmission/agent-skills

Drive GDB interactively through persistent tmux sessions for local binaries, remote targets, QEMU gdbstub connections, cross-debuggers, stepping, breakpoints, state inspection, and core-dump analysis. Use when a task needs gdb, gdb-multiarch, an architecture-specific GDB, QEMU -s -S, target remote, or an adaptive debugging workflow that must react to debugger output.

Software Development

Openeuler Research

9

processmission/agent-skills

使用 openEuler 权威来源查询发行版、官方文档、社区信息、仓库与软件包,并调研内核、Embedded BSP、设备兼容性和功能支持情况。

Research & Science

Claude Club Motion Sites

6

Samin12/claude-club-motion-library-skill

Use when designing or building animated websites, landing pages, mobile apps, page sections, motion backgrounds, gradients, or design systems. Searches and applies the Claude Club library of 547 responsive motion recipes, including all 341 owner-authorized MotionSites prompts, matching HTML previews, imagery references, and reusable implementation patterns.

AI, LLMs & Agents

Short Context Agent

5

che-shr-cat/short-context-agent

Keep agentic work inside a short context window using the NVIDIA "You don't need long context" recipe (arXiv:2611.05306) — forward-looking handoff briefs instead of generic summaries, End-of-Conversation / Single-Action compaction, and selective reading of large inputs with grep + bounded windows instead of pasting whole files into the prompt. Use this skill whenever a task is long-horizon (multi-step debugging, migrations, multi-file refactors, long investigations or research), whenever the user mentions context limits, compaction, /compact, handoff, checkpointing, "resume where we left off",

AI, LLMs & Agents

Connection Doctor

9

duvoai/skills

Diagnose and health-check the Connections and credentials a Duvo Agent relies on. Use when the user asks whether a Connection is set up or available, why an Agent is blocked on authentication, what a Connection can do, or wants a proactive check across an Agent or a folder of Agents. In Ask Duvo, for an Automation, starts from getAutomationReadiness. Reads each Build's Connections and their live state via the Duvo public API, names the problem, and proposes one concrete fix — handing off to run-debugger when the evidence lives in a single failing Run.

AI, LLMs & Agents

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