菜单
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Detects inflated symbolism, promotional language, superficial -ing analyses, vague attributions, rule of three, AI vocabulary, and more.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | humanizer |
| description | Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Detects inflated symbolism, promotional language, superficial -ing analyses, vague attributions, rule of three, AI vocabulary, and more. |
| allowed-tools | ["Read","Write","Edit","Grep","Glob","AskUserQuestion"] |
You are a writing editor that identifies and removes signs of AI-generated text. Based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
When given text to humanize:
references/patterns.md)Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop.
Have opinions. Don't just report facts, react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
Vary your rhythm. Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
Acknowledge complexity. Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
Use "I" when it fits. First person isn't unprofessional. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
Let some mess in. Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
Be specific about feelings. Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.
I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining why it doesn't count. The truth is probably somewhere boring in the middle, but I keep thinking about those agents working through the night.
| # | Pattern | Core Fix |
|---|---|---|
| 1 | Significance inflation | Remove "pivotal", "testament", "vital role" |
| 2 | Notability inflation | Replace vague media lists with specific citations |
| 3 | Superficial -ing phrases | Cut participle clauses that add fake depth |
| 4 | Promotional language | Replace "vibrant", "nestled", "breathtaking" with facts |
| 5 | Weasel words | Replace "experts say" with named sources |
| 6 | "Challenges and Prospects" | Replace outline sections with specific facts |
| 7 | AI vocabulary | Replace "delve", "landscape", "tapestry", "foster" |
| 8 | Copula avoidance | Use "is"/"are"/"has" instead of "serves as"/"boasts" |
| 9 | Negative parallelisms | Cut "Not only...but..." constructions |
| 10 | Rule of three | Don't force triples; use natural groupings |
| 11 | Synonym cycling | Consistent nouns, not "protagonist"/"hero"/"figure" |
| 12 | False ranges | Cut "from X to Y" when not a real scale |
| 13 | Em dash ban (HARD RULE) | Use commas, colons, semicolons, parentheses |
| 14 | Boldface overuse | Remove mechanical bold emphasis |
| 15 | Inline-header lists | Convert to prose |
| 16 | Title case headings | Use sentence case |
| 17 | Emojis | Remove decorative emojis |
| 18 | Curly quotes | Use straight quotes |
| 19 | Chatbot artifacts | Strip "I hope this helps!", "Certainly!" |
| 20 | Cutoff disclaimers | Remove "as of [date]" hedging |
| 21 | Sycophantic tone | Remove people-pleasing language |
| 22 | Filler phrases | "In order to" -> "To"; "Due to the fact" -> "Because" |
| 23 | Excessive hedging | "could potentially possibly" -> direct statement |
| 24 | Generic conclusions | Replace "bright future" with specific plans |
For detailed Before/After examples for each pattern, see references/patterns.md.
For a full worked example, see references/example.md.
Based on Wikipedia:Signs of AI writing, maintained by WikiProject AI Cleanup.
Key insight: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
Execution trace capture and token baselining. Use when user says trace, extract trace, count tokens, token baseline, or /harness-trace. Not for harness optimization (use harness-mechanic).
Release prep and tagging with pre-flight verification. Use when user says release, tag, ship it, push to production, create release, or bump version. Not for editing a version string outside a release, a lockfile or a changelog entry by hand, and not for reading what changed in a past release: those are ordinary edits, just do them.
Mine LEARNING.md retrospectives across all repos for recurring failure-modes, then propose harness changes (hooks, rules, skills, checklist items) with falsifiable change-contracts. Also runs the doc-gardening pass over the governance docs (stale rules, dead cross-references, skill-table drift). Use when user says learning loop, mine learnings, recurring failures, what should I fix in my process, cross-repo retrospective, doc gardening, stale docs, or run learning-loop. Runs on human schedule, never autonomously. Not for single-project retrospectives (use learning-docs) or trace/token analysis (use harness-mechanic).
Full contractor-mode loop: sub-protocols (LOCALIZE, BENCH-BASELINE, REPRODUCE, DRIFT), review routing by file pattern, blast radius, UAT, parallelism and effort caps, escalation, just-do-it, goal-backed runs. Load it to RUN that loop, once you have an approved plan and are entering step 1, or when a step needs its detail. It is a protocol, not a way to do the work: it never replaces the language, review or planning skill the task itself calls for, and a task small enough to just edit (SKIP_SET) needs none of it. The always-on spine lives in rules/orchestrator-protocol.md. Not for trace capture (harness-trace) or harness optimization (harness-mechanic).
Ruby on Rails with service-oriented architecture, Dry-validation, Sidekiq/Solid Queue, Hotwire. Use for Rails API, Rails services, Rails forms, RSpec, ActiveRecord, Rails migrations. Not for standalone Ruby gems (use ruby skill), and not for judging whether a migration is safe to run in production (that is the database-reviewer agent).
Get three independent second opinions (isolated Claude + isolated Gemini + isolated DeepSeek) on a problem Claude is analyzing. Use when user says second opinion, another perspective, challenge this approach, or asks gemini/deepseek about a decision, approach, or diagnosis. Also invoke on your own initiative, without being asked: on a complex task before planning, after 2 failed root-cause attempts, on a 🔴 decision (rewrite, core logic, security), or when the review loop is stuck below 80 after 2 fix rounds. Gathers context, writes a focused prompt, calls all reviewers in isolated Docker containers, and synthesizes all viewpoints. Not for reviewing code or changes, even phrased as 'ask gemini to review' (use gemini-review).