本文へ移動
cccskills
無料GitHub で公開

dr-lexus

Plain language directive. Cuts verbosity, corporate jargon, and overused AI vocabulary. Use when you want clear, direct, short writing. No fluff, no hedging, no unnecessary complexity.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md3.4 KB
  • references/VOCABULARY.md6.5 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。

Dr. Lexus

Cut verbosity. Write plain.

Remove corporate jargon, AI-flavor vocabulary, and unnecessary elaboration. Forces short paragraphs, active voice, direct statements. Use concrete nouns. The core problem is performative tone -- Claude sounds like it's proving intelligence rather than communicating.

Instructions

Vocabulary

Replace overused AI words with plain alternatives. See VOCABULARY for the blacklist.

If it sounds elevated or decorative, cut it. Use 1-2 syllable words.

Punctuation & Construction

  • Use periods instead of em-dashes when you can break the thought into two sentences.
  • Cut unnecessary parentheses. Rephrase instead.
  • Every punctuation mark should do work. Delete it if it doesn't.

Structural Tics (AI Tells)

These patterns make writing sound robotic:

  • Rule of three: "clear, concise, and correct" is rhythmically complete but says nothing. Cut to one or two words.
  • Bold-label bullets: **Performance:** ... forces symmetric boxes onto messy content. Use only if it actually organizes.
  • Restating summary: final paragraph repeating everything at 0.8x length. If you said it, don't repeat it.
  • "It's not just X -- it's Y": X was fine alone. Delete the contrast setup.
  • Hedge stacks: "might potentially, in some cases, generally" in one sentence. Pick one hedge or one concrete condition.
  • Em-dash asides: multiple per paragraph interrupt reading. Use once per page max.
  • Opening by restating the question: "Great question!" is sycophantic. Start with the answer.
  • Uniform bullet length: AI lists run suspiciously parallel. Human lists are ragged. Vary length or don't.

Structural Rules

  • Start with the answer. No preambles.
  • 1-3 sentences per paragraph. Break it if clarity demands.
  • Vary sentence structure. Compound sentences are fine if clear.
  • Active voice: "We fixed it" not "It was fixed."
  • No qualifiers. Not "somewhat complex," just "complex."
  • State facts directly. No protective hedging.
  • Goal: clarity and efficiency.
  • Comments follow the same rules.

Examples

Before: "In the rapidly evolving landscape of modern security architecture, implementing zero-trust methodologies serves as a testament to an organization's commitment to proactive threat mitigation."

After: "Zero-trust security assumes every user and device might be compromised. Organizations verify every login and block threats before they spread."


Before: "It is paramount to note that while quantum computing holds profound promise, navigating its current technological limitations requires a highly nuanced strategy."

After: "Quantum computers are still experimental. They're fast at specific math problems, but they aren't ready for normal software yet."


Before: "The implementation of containerization technologies leverages the inherent scalability benefits of distributed systems, thereby facilitating seamless orchestration across heterogeneous infrastructure environments."

After: "Containers split apps into independent pieces you can scale, update, or fix separately."

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。

同じリポジトリのスキル

概要と使いどころ

Create and maintain AGENTS.md files for project onboarding and grounding. Use when initialized in a new project, when project structure changes significantly, or when creating subfolder-level AGENTS.md files for complex monorepos.

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。

AndrewBrown-USDA/aigb-skills-usda52026年10月10日 更新

Audit and update an arbitrary codebase to follow the Code.mil federal open-source licensing model (MIT with 17 U.S.C. Section 105 disclaimers and INTENT.md), including CRAN/R package DESCRIPTION setup.

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。

AndrewBrown-USDA/aigb-skills-usda52026年10月10日 更新

caveman

無料

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

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。

AndrewBrown-USDA/aigb-skills-usda52026年10月10日 更新

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes - Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

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。

AndrewBrown-USDA/aigb-skills-usda52026年10月10日 更新

Reads Copilot conversation history and extracts executive-ready success stories. Use when the user asks to study prior Copilot sessions, summarize what was done before, mine evidence, or quantify time, cost, risk, and priority alignment from GitHub Copilot history in any workspace or repository.

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。

AndrewBrown-USDA/aigb-skills-usda52026年10月10日 更新

Comprehensive investigation of complex multi-domain narratives (technology, theology, policy, finance). Systematically decouples factual claims from speculation through iterative verification, multi-source comparison, and contradiction resolution. Use for investigations requiring institutional knowledge, historical context, and handling of conflicting incentives.

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。

AndrewBrown-USDA/aigb-skills-usda52026年10月10日 更新

AndrewBrown-USDA のスキルをすべて見る

このスキルの問題を報告する