Agent skill
writing-style
Human writing standards to eliminate AI-generated text patterns. This skill should be used for any copywriting, marketing content, documentation, or professional writing to ensure output reads as genuinely human. Covers banned vocabulary, punctuation discipline, sentence variety, and tone guidelines.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/documents/writing-style-nestmind-app-docs
SKILL.md
Human Writing Standards
Purpose
AI-generated text has recognizable patterns that erode trust and signal inauthenticity. This skill enforces rules for writing that reads as genuinely human—the standard used by Zed, Basecamp, Linear, Stripe, and Apple.
Workflow
To produce human-quality writing:
- Draft content normally
- Run the self-check (see Quick Self-Check below)
- Fix any violations using the reference material
Quick Self-Check
Before publishing any content, verify:
- Vocabulary scan: Search for banned words (delve, tapestry, landscape, leverage, robust, seamless, comprehensive, crucial, multifaceted, embark, journey, moreover, furthermore, utilize, foster, showcase)
- Em-dash count: More than 2 on the page? Rewrite.
- Opening check: Does it start with "In today's..." or "Whether you're..."? Rewrite.
- Colon check: Does the headline have a colon? Remove it.
- Vagueness check: Replace "helps you manage" with something specific.
- Read aloud: Does it sound like a person talking, or a press release?
- "The" count: Too many sentences starting with "The [product]..."? Vary it.
- Enthusiasm check: More than one exclamation point? Cut some.
Core Rules (Summary)
| Rule | Key Point |
|---|---|
| Banned Vocabulary | Avoid AI-overrepresented words (delve, leverage, robust, seamless, etc.) |
| Em-Dash Discipline | Max 1 per paragraph, 2 per page |
| Banned Phrases | No "In today's...", "Whether you're...", "In conclusion..." |
| Punctuation | Sparingly use semicolons, max 1 exclamation per page |
| Sentence Variety | Mix short and long, vary paragraph length |
| Specificity | Concrete details over vague benefits |
| Headers | Short, scannable, no colons |
| Tone | Direct, confident, personal ("we" and "you") |
| Filler | Cut "very", "really", "in order to", etc. |
Reference
For complete lists of banned words, replacement suggestions, and before/after examples, see:
references/writing-rules.md— Full vocabulary lists, punctuation rules, and examples
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?