applied-artificial-intelligence/claude-code-toolkit/plain-language
Claude Code and agent skill by applied-artificial-intelligence/claude-code-toolkit
- community
Checking that the SKILL.md file is still in the repository.
Simplification and readability techniques. Use when writing for broad audiences or simplifying complex content. Covers active voice, short sentences, jargon elimination, and accessibility principles from the Plain Language Movement.
Install
npx vskill@latest install applied-artificial-intelligence/claude-code-toolkit/plain-languageSKILL.md
Plain Language
Purpose: Write clearly and directly using active voice, simple sentences, and minimal jargon.
Origin: Plain Writing Act of 2010 (US), Plain Language Movement
Use When: Drafting and reviewing content to maximize clarity (Phases 4-5)
Core Principle
Plain language means readers understand immediately what you're saying - no rereading required.
Why It Matters
- Comprehension: 80% of readers prefer plain language (Bailey 2017)
- Efficiency: Plain language reduces reading time by 25-40% (Redish 1985)
- Accessibility: Technical audiences still prefer clarity over jargon
The Four Rules
1. Use Active Voice (>80% target)
Passive: Subject receives action ("The error was caught by the test") Active: Subject performs action ("The test caught the error")
Why Active is Better:
- Shorter (fewer words)
- Clearer (who does what)
- More direct (action-oriented)
Examples:
Detection Pattern: "was/were/is/are + past participle + by"
When Passive is Okay:
- Unknown actor: "The system was compromised"
- Actor irrelevant: "Errors are logged automatically"
- Emphasizing recipient: "The president was elected by landslide"
2. Shorten Sentences (<25 words average)
Principle: Long sentences increase cognitive load and reduce comprehension.
Targets:
- Average: <25 words per sentence
- Maximum: Avoid >35 word sentences
- Variety: Mix short (10-15) and medium (20-25) sentences
Techniques:
How to Shorten:
- Split at "and", "but", "because"
- Remove redundancy
- Break into bullets if listing >3 items
- Move subordinate clauses to new sentence
3. Eliminate Jargon (or Explain on First Use)
Jargon: Specialized terminology that excludes readers.
When to Use Jargon:
- ✅ Technical audience expects it (API docs for developers)
- ✅ No simpler alternative exists (monadic bind operation)
- ✅ Explained on first use with example
When to Avoid:
- ❌ Simpler word exists: "utilize" → "use"
- ❌ Buzzword adds no meaning: "leverage synergistic paradigms"
- ❌ Abbreviation unexplained: "RBAC" (first use: Role-Based Access Control)
Examples:
4. Write Clearly (Avoid Common Issues)
Nominalization (verb → noun weakens writing):
Weak Verbs (vague actions):
Redundancy (unnecessary words):
Weasel Words (often removable):
Application by Mode
Tutorial (Maximum Clarity)
- Active voice: >90%
- Short sentences: <20 words average
- No jargon: Explain everything
- Encouraging tone: "You'll see", "Now you can"
How-To (Direct and Efficient)
- Active voice: >85%
- Imperative mood: "Run the command", "Configure the setting"
- Minimal prose: Action-focused
- Technical terms okay if audience expects them
Reference (Precise but Clear)
- Active voice: >70% (passive okay for specifications)
- Longer sentences acceptable: Technical precision matters
- Jargon expected: But define abbreviations
- Neutral tone: No "should" or opinions
Explanation (Thoughtful Clarity)
- Active voice: >80%
- Medium sentences: <25 words average
- Analogies valued: Make abstract concepts concrete
- Jargon explained: Teach terms through use
Measurement
Active Voice Percentage
Calculation:
- Count sentences with passive voice markers ("was/were + past participle + by")
- Count total sentences
- Active % = (1 - passive_count / total) * 100
Targets:
- 90-100%: Excellent (Tutorial)
- 80-89%: Good (How-To, Explanation)
- 70-79%: Acceptable (Reference)
- <70%: Needs improvement
Sentence Length
Calculation:
- Count words per sentence
- Calculate average
- Flag sentences >35 words
Targets:
- <20 words: Excellent clarity
- 20-25 words: Good balance
- 25-30 words: Acceptable but monitor
- >30 words: Consider splitting
Readability (Flesch-Kincaid)
Plain language typically scores:
- Reading Ease: 60-70 (Standard)
- Grade Level: 8-10 (8th-10th grade)
Quality Checklist
Plain language compliance:
- [ ] Active voice >80% (or mode-appropriate target)
- [ ] Average sentence length <25 words
- [ ] No sentences >50 words
- [ ] Jargon explained on first use
- [ ] No nominalization ("make a decision" → "decide")
- [ ] No weak verbs ("utilize" → "use")
- [ ] No redundancy ("advance planning" → "planning")
- [ ] Weasel words removed or justified
- [ ] Abbreviations spelled out on first use
- [ ] Technical terms defined through use
References
- Plain Writing Act of 2010. US federal requirement for clear communication.
- Redish, J.C. (1985). "The Plain English Movement". Technical communication study.
- Bailey, S. (2017). "Plain Language: A Strategic Approach". Comprehension research.
- Flesch, R. (1948). "A New Readability Yardstick". Original readability formula.
- Strunk, W., & White, E.B. (2000). The Elements of Style. Clarity principles.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingexamples/writing/skills/plain-language/SKILL.md
Popularity
- Repository stars
- 45
- Repository forks
- 13
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 22 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/applied-artificial-intelligence/claude-code-toolkit/plain-language)