AGENT SKILL

writing-clearly-and-concisely

Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

适用职业内容创作者
使用场景写作与文案
License 许可
MIT
最近更新
2026-11-14
Stars
★ 3.3w
Forks
3.9k

01 前言 Front Matter

name
writing-clearly-and-concisely
description
Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.

02 资源文件 12

03 SKILL.md 正文

Writing Clearly and Concisely

Overview

Write with clarity and force. This skill covers what to do (Strunk) and what not to do (AI patterns).

When to Use This Skill

Use this skill whenever you write prose for humans:

  • Documentation, README files, technical explanations
  • Commit messages, pull request descriptions
  • Error messages, UI copy, help text, comments
  • Reports, summaries, or any explanation
  • Editing to improve clarity

If you're writing sentences for a human to read, use this skill.

Limited Context Strategy

When context is tight:

  1. Write your draft using judgment
  2. Dispatch a subagent with your draft and the relevant section file
  3. Have the subagent copyedit and return the revision

Loading a single section (~1,000-4,500 tokens) instead of everything saves significant context.

Elements of Style

William Strunk Jr.'s The Elements of Style (1918) teaches you to write clearly and cut ruthlessly.

Rules

Elementary Rules of Usage (Grammar/Punctuation):

  1. Form possessive singular by adding 's
  2. Use comma after each term in series except last
  3. Enclose parenthetic expressions between commas
  4. Comma before conjunction introducing co-ordinate clause
  5. Don't join independent clauses by comma
  6. Don't break sentences in two
  7. Participial phrase at beginning refers to grammatical subject

Elementary Principles of Composition:

  1. One paragraph per topic
  2. Begin paragraph with topic sentence
  3. Use active voice
  4. Put statements in positive form
  5. Use definite, specific, concrete language
  6. Omit needless words
  7. Avoid succession of loose sentences
  8. Express co-ordinate ideas in similar form
  9. Keep related words together
  10. Keep to one tense in summaries
  11. Place emphatic words at end of sentence

Reference Files

The rules above are summarized from Strunk's original text. For complete explanations with examples:

Section File ~Tokens
Grammar, punctuation, comma rules 02-elementary-rules-of-usage.md 2,500
Paragraph structure, active voice, concision 03-elementary-principles-of-composition.md 4,500
Headings, quotations, formatting 04-a-few-matters-of-form.md 1,000
Word choice, common errors 05-words-and-expressions-commonly-misused.md 4,000

Most tasks need only 03-elementary-principles-of-composition.md — it covers active voice, positive form, concrete language, and omitting needless words.

AI Writing Patterns to Avoid

LLMs regress to statistical means, producing generic, puffy prose. Avoid:

  • Puffery: pivotal, crucial, vital, testament, enduring legacy
  • Empty "-ing" phrases: ensuring reliability, showcasing features, highlighting capabilities
  • Promotional adjectives: groundbreaking, seamless, robust, cutting-edge
  • Overused AI vocabulary: delve, leverage, multifaceted, foster, realm, tapestry
  • Formatting overuse: excessive bullets, emoji decorations, bold on every other word

Be specific, not grandiose. Say what it actually does.

For comprehensive research on why these patterns occur, see signs-of-ai-writing.md. Wikipedia editors developed this guide to detect AI-generated submissions — their patterns are well-documented and field-tested.

Bottom Line

Writing for humans? Load the relevant section from elements-of-style/ and apply the rules. For most tasks, 03-elementary-principles-of-composition.md covers what matters most.

04 同仓库更多 Skills

davila7
davila7/claude-code-templates

wealthville-pool-scoring

Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.

Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

technical-debt-auditor

Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.

Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

readonly-sql-guard

Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.

数据分析师后端与接口Skill与智能体开发
★ 3.3w
davila7
davila7/claude-code-templates

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 3.3w
davila7
davila7/claude-code-templates

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

测试与质量前端开发
★ 3.3w
davila7
davila7/claude-code-templates

discernment-nudge

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

内容创作者写作与文案Skill与智能体开发
★ 3.3w