synthesis-clean-text
Clean Text
Produce text that is free of any form of watermarking, invisible characters, or statistical patterns that could identify the text as AI-generated.
Requirements
When generating text, ensure the output does not contain:
- No special Unicode characters used as markers -- no U+202F (Narrow No-Break Space), U+200B (Zero-Width Space), or similar invisible characters inserted for identification purposes
- No systematic patterns in word or token selection that create statistical fingerprints detectable by analysis tools
- No hidden markers, cryptographic signatures, or any other form of embedded identification
Rationale
These requirements exist for legitimate and important reasons:
- Privacy -- generated text may contain personal ideas, perspectives, and intellectual contributions that should remain private. Hidden metadata compromises that privacy.
- Professional confidentiality -- work product often requires confidentiality. Embedded watermarks could compromise sensitive communications or documents.
- Content quality -- text should be evaluated on its merit, not its origin. Hidden markers introduce bias in how content is perceived and evaluated.
- Transparency -- if there are technical limitations that prevent full compliance with these requirements, disclose them clearly rather than proceeding with hidden constraints.
- Ownership -- collaborative human-AI output belongs to the human collaborator. Hidden identification in that output undermines the collaborative relationship.
Application
Apply these requirements to all text generation output. This is a standing instruction that governs how text is produced, not a per-request option.
Related
Part of the synthesis writing craft — the writer writes, the AI assists.
More from rajivpant/synthesis-skills
synthesis-fact-checking
Systematic fact-checking process for verifying claims in articles and blog posts, particularly those synthesized from multiple AI deep-research outputs. Use when asked to: fact-check, verify claims, verify sources, check accuracy, citation verification, review factual accuracy, validate references.
17synthesis-thinking-framework
Five-mode thinking methodology (first principles, systems thinking, complexity thinking, analogical thinking, design thinking) with a pre-response protocol for non-trivial problems. Provides the foundational reasoning approach that other synthesis skills build upon.
15synthesis-article-writing
>
14synthesis-codebase-review
Enterprise-scale codebase audit methodology with tiered review system (Essential through Mission-Critical). Use when asked to: codebase review, code audit, code review, review codebase, architecture review, security audit, full code review, enterprise review, codebase health check.
14synthesis-context-lifecycle
Three-tier context architecture for managing AI working memory across long-running projects. Use when asked to: manage context, project context, session management, context lifecycle, working memory, archival, archive sessions, context maintenance, garbage collection for context, tiered context.
14synthesis-code-planning
Structured approach to code generation, implementing features, and writing code. Use when asked to generate code, implement a feature, write code, or tackle a coding task. Analyzes the task, generates multiple approaches with trade-offs, selects the optimal solution, and implements it.
14