guillaumemeyer/watermarks-remover / skills/clean-user-facing-text
clean-user-facing-text
FlaggedClean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting prose while preserving facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI text, Markdown, or HTML prose, or when a project rule or instruction file explicitly requires this workflow. Don't use for code-only tasks or undisclosed authorship evasion; leave code, commands, identifiers, paths, APIs, formulas, citations, required disclosures, and verbatim quotations unchanged.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.6 KB |
| references/detectors.md | markdown | 8.1 KB |
| references/responsible-use.md | markdown | 536 B |
| references/watermark-notes.md | markdown | 1.2 KB |
| references/writing-in-your-voice.md | markdown | 2.5 KB |
| scripts/clean_text.pyexecutable | script | 3.0 KB |
| scripts/common.py | script | 20.9 KB |
| scripts/inspect_text.pyexecutable | script | 4.4 KB |
| scripts/score_stylometry.py | script | 19.5 KB |
| scripts/text_unicode.pyexecutable | script | 24.5 KB |
references/watermark-notes.md
View on GitHub# Text watermark notes
## Deterministic marks
Invisible Unicode, bidirectional controls, tag characters, exotic spaces, and selected confusables can carry machine-readable signals or cause broken copy, search, and diffs.
`clean_text.py` removes or normalizes known carriers and reports exact counts. By default it preserves contextual characters used by emoji, joining scripts, Mongolian selectors, Khmer inherent vowels, Hangul fillers, and Arabic/Syriac orthography. The lightweight workflow also disables space normalization by default so multilingual typography remains intact. Aggressive flags can damage intentional text and should remain opt-in.
## Statistical marks
Token-sampling watermarks such as green-list or tournament-sampling schemes live in word choice and token sequences rather than metadata. A substantial rewrite can weaken such signals by changing syntax and vocabulary.
This is best-effort:
- no bundled detector has the vendor's secret key
- a rewrite generated by the same provider may introduce a new signal
- short or predictable text provides little statistical evidence either way
- detector behavior can change independently of this skill
Never describe a successful rewrite as certified, undetectable, or proof of human authorship.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |