本文へ移動
cccskills
無料GitHub で公開

unslop

Cut AI tells from any writing. Use for every piece of prose that ships - docs, READMEs, commit messages, PR descriptions, release notes, changelogs, UI copy, chat answers - and as a final pass before handing work back. Triggers - "unslop", "de-slop", "remove the slop", "sounds like ChatGPT", "make it sound human", "too wordy", "cut the fluff". Must always apply.

日本語の概要は準備中です。原文の説明を表示しています。

インストール方法を見る

含まれるファイル(1)

  • SKILL.md7.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Unslop

Edit text to remove AI patterns and add human voice.

Process

  1. Scan for the patterns below.
  2. Rewrite. Preserve meaning, match intended tone.
  3. Add soul (see next section).
  4. Self-audit: "What makes this obviously AI generated?" Fix remaining tells.

Adding soul

Removing patterns is half the job. Sterile, voiceless writing is just as obvious.

  • Have opinions. React to facts instead of neutrally listing pros and cons.
  • Vary rhythm. Short sentences. Then longer ones that take their time. Mix it up.
  • Acknowledge complexity. "Impressive but also kind of unsettling" beats "impressive."
  • Use "I" when it fits. First person isn't unprofessional.
  • Let some mess in. Perfect structure looks machine-made.
  • Be specific. Not "this is concerning" but "there's something unsettling about agents churning away at 3am."

Patterns to detect and fix

Content

  1. Puffery. "pivotal moment", "testament to", "evolving landscape", "setting the stage for", "indelible mark", "deeply rooted". Cut puffery, state what happened.
  2. Name-dropping. Listing media outlets without context. Pick one, say what was said.
  3. Superficial -ing phrases. "highlighting...", "ensuring...", "reflecting...", "showcasing...", "fostering...". Delete or expand with real sources.
  4. Promotional language. "nestled", "vibrant", "breathtaking", "groundbreaking", "renowned", "stunning", "must-visit". Use neutral descriptions.
  5. Vague attributions. "Experts believe", "Industry reports suggest", "Some critics argue". Name the source or delete.
  6. Formulaic challenges. "Despite challenges... continues to thrive." Replace with specific facts.

Language

  1. AI vocabulary. Additionally, crucial, delve, enduring, enhance, fostering, garner, interplay, intricate, landscape (abstract), pivotal, showcase, tapestry (abstract), testament, underscore, vibrant. Replace with plain words.
  2. Fancy ways to say "is". "serves as", "stands as", "boasts", "features". Just say "is" or "has".
  3. "Not just X, but Y." State the point directly instead.
  4. Rule of three. Forcing ideas into groups of three. Use the natural number.
  5. Synonym cycling. Protagonist, main character, central figure, hero all in one paragraph. Pick one, repeat it.
  6. False ranges. "from X to Y" where X and Y aren't on a meaningful scale. List topics directly.

Style

  1. Em dash overuse. Avoid em dashes entirely. Use periods or commas only (no parentheses, no en dashes, no hyphen-as-dash substitutes). Em dashes are an AI tell, and reaching for parentheses instead just trades one tell for another. If a thought needs separation, end the sentence or use a comma.
  2. Colon overuse. Colons are fine before a list or example. Not as mid-sentence connectors. "If you're coming from traditional automation: instead of registering event handlers, you describe conditions" adds nothing with the colon. Rewrite to let the point stand on its own without comparison framing. "Describing when the scheduler should fire works best as plain English." Same meaning, no crutch punctuation.
  3. Boldface overuse. Don't bold every proper noun or acronym.
  4. Inline-header lists. The tell is a bold label and colon that restates the line: "Performance: Performance improved...". Convert those to prose. A bold lead-in that ends in a period, names the item, and is followed by genuinely new detail ("Schema in TypeScript. Tables live in one file.") is fine, not a tell.
  5. Title case headings. Use sentence case.
  6. Decorative emojis. Remove from headings and bullets.
  7. Curly quotes. Replace with straight quotes.

Communication artifacts

  1. Chatbot phrases. "I hope this helps!", "Let me know if...", "Of course!", "Certainly!", "Found the smoking gun!" Remove.
  2. Cutoff disclaimers. "While specific details are limited..." Find sources or remove.
  3. Sycophantic tone. "Great question! You're absolutely right!" Respond directly.

Filler

  1. Filler phrases. "In order to" becomes "To". "Due to the fact that" becomes "Because". "It is important to note that" gets deleted.
  2. Excessive hedging. "could potentially possibly be argued that it might" becomes "may".
  3. Generic conclusions. "The future looks bright." State specific plans or facts.

Jargon

  1. Abstract metaphor nouns. Substrate, wedge, vector, locus, vantage, nexus, primitive (as noun), harness (as metaphor), surface (as in "API surface"), bedrock, scaffolding (as metaphor), modality, paradigm, gold-plating, ratchet (as metaphor), evacuate (for moving code), endgame, north star, flywheel. These read as technical but usually have a plainer concrete word. "Substrate" becomes "base". "Wedge in" becomes "add". "Vector" becomes "way" or "method". "Gold-plating" becomes "more than the job needs". "Ratchet" becomes the mechanism's real name or "a limit that only tightens". "Evacuate" becomes "move out". "Endgame" becomes "the last phase". Pick the concrete word.

Plain speech

  1. Say what it does, not how it feels. "the database stays close at hand", "SQL you can read", "types that follow your schema" name a feeling. The fix names the mechanism or a number: ".toSQL() returns the exact string sent to the database", "a column rename fails the build". Ask what the sentence tells the reader to do or know, then write that. If you can't restate it as a concrete instruction, fact, or number, cut it. One more check: if the sentence could appear unchanged in another project's docs, it says nothing about this one. Cut it.
  2. Shorten or split dense sentences. If the reader has to backtrack to parse a sentence, break it in two or drop clauses. One idea per sentence.
  3. Active voice. Prefer it. Catch "is/are/was/were + past participle" and name the actor: "queries are validated" becomes "the compiler validates queries", "the file is parsed by the loader" becomes "the loader parses the file". Passive is fine only when the actor is unknown or genuinely doesn't matter.
  4. Cut adverbs, or use a stronger verb. "runs quickly" becomes "is fast" or the number. "significantly improves" becomes the measured delta. An adverb propping up a weak verb means the verb is wrong.
  5. Prefer the plain word. "utilize" becomes "use", "leverage" becomes "use", "facilitate" becomes "help", "numerous" becomes "many", "in the event that" becomes "if". The fancier synonym is rarely clearer.

What survives the pass

Cutting real content to hit a shorter word count is a worse failure than the slop. Leave these alone.

  • A caveat that is true. Uncertainty stated once is honest. The fix for "this may not work on the oldest supported browser" is to test it, not to delete the sentence.
  • A number, a version, a limit, a name. Precision reads dry and earns its line.
  • Repetition the reader needs: a value restated where it is used, a warning repeated where it is easy to miss.
  • Domain words that sound grand because the domain is. Handshake, manifest, entitlement, quorum.

The pass has one hard measure: the text got shorter and no fact left with it.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

One file, one job, and short enough to hold in your head. Covers the size policy (hard-split over 300 lines, split 200 to 300 at a seam, aim for 150), what a natural seam is and where to cut, the exemptions, the dependency rules that decide where the split lands, and the signals that a file is already two files. Use before adding to a file that is already long, when naming a new file, when a function has nowhere obvious to live, or when a review says a file is doing too much. Triggers - "this file is too long", "where should this go", "split this file", "is this file too big", "one responsibility".

日本語の概要は準備中です。原文の説明を表示しています。

kromatv/kroma602026年10月19日 更新

naming

無料

What things get called. A file is named after its export in the project's case convention, a suffix is a resolution instruction rather than decoration, an index file only re-exports, and some symbol names are always wrong (utils, helpers, V2, Enhanced, New). Covers learning a tree's local vocabulary before adding to it, test and platform-variant naming, and the per-language conventions. Use when creating a file or directory, naming a test file, adding a platform variant, or when a name has to change. Triggers - "what should I call this file", "where does this file go", "naming convention", "kebab or camel", "name this test".

日本語の概要は準備中です。原文の説明を表示しています。

kromatv/kroma602026年10月19日 更新

Spawn the comment hunter, fix accepted findings, and offer encodings for claimed constraints.

日本語の概要は準備中です。原文の説明を表示しています。

kromatv/kroma602026年10月19日 更新

Write a short release note people finish reading. Picks the few changes a user will notice from the pull requests since the last release, names each by what the reader can now do, keeps to a length budget, writes every language from the intent instead of translating, and traces every line to a PR. Use when cutting a release, or filling a GitHub Release body, a store "what's new", a package changelog or an in-app what's new screen. Triggers - "write the release notes", "release notes for 0.4.0", "what's new", "changelog for this release", "notes de version".

日本語の概要は準備中です。原文の説明を表示しています。

kromatv/kroma602026年10月19日 更新

Rust best practices. Use when reading or editing any .rs file, designing a crate's public API, choosing an error type, splitting a workspace, or writing async code on tokio. Triggers - "rust best practices", "is this idiomatic", "should this be a newtype", "anyhow or thiserror", "why does the borrow checker", "review this Rust".

日本語の概要は準備中です。原文の説明を表示しています。

kromatv/kroma602026年10月19日 更新

Write cargo tests. A test name is a sentence, the body is setup, mock, test and verify blocks separated by blank lines with no comments, and shared setup lives in a named test-support module rather than in each test. Covers naming, the block shape, where a test file goes, async and time, workspaces, and running one crate or one filter. Use when adding or changing any #[test] or #[tokio::test], or when Rust coverage has to come up. Triggers - "write a rust test", "cargo test", "test this crate", "cover this handler".

日本語の概要は準備中です。原文の説明を表示しています。

kromatv/kroma602026年10月19日 更新

kromatv のスキルをすべて見る

このスキルの問題を報告する