sergebulaev/linkedin-skills / .codex-marketplace/linkedin-skills/skills/linkedin-humanizer
linkedin-humanizer
VerifiedRemove AI tells from LinkedIn posts/comments: 2026 vocabulary density, reveal bridges, staccato fragments, stacked triads, performed sincerity. Tiered rewriter plus `--mode audit` LinkedIn post auditor and `--mode profile` voice builder. Not for drafting from scratch (use linkedin-post-writer) or beating AI detectors. Keywords: humanize, de-AI, post audit, post auditor, audit before posting.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 16.4 KB |
| references/audit-ai-tells.md | markdown | 11.6 KB |
| references/audit-checklist.md | markdown | 4.1 KB |
| references/audit-examples.md | markdown | 452 B |
| references/detector-list.md | markdown | 6.1 KB |
| references/emoji-patterns.md | markdown | 3.8 KB |
| references/examples.md | markdown | 1.4 KB |
| references/rules-explainer.md | markdown | 14.8 KB |
| references/scrub-rules.md | markdown | 27.0 KB |
| references/tier-rationale.md | markdown | 17.3 KB |
| references/v3-changes.md | markdown | 3.2 KB |
| references/voice-fingerprint.md | markdown | 5.3 KB |
| scripts/detectors.env.example | other | 428 B |
| scripts/test_detectors.pyexecutable | script | 13.0 KB |
| sub-skills/detector-tester.md | markdown | 6.0 KB |
| sub-skills/emoji-detector.md | markdown | 3.9 KB |
| sub-skills/illustration.md | markdown | 7.4 KB |
| sub-skills/post-audit.md | markdown | 4.9 KB |
| sub-skills/rules-explainer.md | markdown | 5.2 KB |
| sub-skills/voice-profile.md | markdown | 3.0 KB |
references/v3-changes.md
View on GitHub# What changed in V3
Evidence tier in brackets: [strong] = replicated across 2+ independent 2025-2026 studies or our own length-controlled corpus; [vendor] = single platform or vendor dataset; [weak] = one study or expert-panel report.
- **Vocabulary moved from a delete-list to density scoring.** The 2023-24 words (delve, tapestry, realm, journey) are decaying as humans avoid them [strong: Geng & Trotta 2025]. The durable 2026 markers are common words (significant, crucial, notably, comprehensive, insights, robust, leverage, foster, landscape, nuanced, streamline, elevate) plus grammar: nominalisations and "-ing" clause openers at 5.3x human rate [strong: Kobak Sci Adv 2025; Wu et al 2026; PNAS 2025]. AI vocabulary is also the one marker consistently reach-negative on LinkedIn in our own corpus (0.74-0.84 author-relative) [strong]. One marker in a paragraph is not a verdict. Three or more is.
- **Em dash is no longer a tell.** GPT-5.4 emits 1.43 per 1,000 words, below the 3.23 human baseline; 29% of human captions and 23% of top-creator LinkedIn posts in our corpus use one (author-relative ratio 1.09) [strong]. Zero em dashes is now its own tell (the writer is trying to look human). New rule: cap at about 1 per 100 words, replace excess with comma, colon, parentheses or a rewrite. Never a period.
- **Forced burstiness is the #1 2026 tell, not the fix.** LLM sentence-length variance is half of human [strong], but detectors do not score it, mechanical long/short alternation is a learnable humanizer fingerprint [weak: DAMAGE 2025], and on LinkedIn sentence-length variance is not an engagement lever in either direction (our corpus, n=397, within-creator: null to slightly negative) [strong]. "Short. Punchy. Done.", "No X. No Y. Just Z.", one-word paragraphs and "The result?" reveals are the current top tells. Pass 2 is now RHYTHM, not BREAK: fix machine-flat rhythm, never manufacture variance.
- **Rule of three is still a tell, at density.** Tricolon runs at 2x expert-human rate across 2026 frontier models [strong: arXiv 2604.19768]. Stacked, perfectly parallel triads and 3+ per post get scrubbed. One natural triple stays (26% of top human tweets have one).
- **Fingerprint injection was half wrong.** Named entities and concreteness are supported [strong: lower entity density in LLM text across 3 studies]; an odd-precision number with a referent in line 1 lifts likes 34% [vendor]. Bare numbers are not a discriminator, and inserted hedges and confessions backfire: performed hesitancy is 2x more common in LLM text than expert human text, and sincerity announcements ("let me be honest") are a named 2026 tell [strong: tropes.fyi false vulnerability; Schilke & Reimann 2025]. Pass 3 now asks for a flat, dated, uncomfortable fact instead.
- **Over-correction guard.** Humanizer output has its own fingerprint; "writing slightly worse on purpose" now reads as a tell [weak: DAMAGE 2025; slopotron]. Pass 4 checks whether Passes 1-3 introduced the very patterns they were meant to remove. Edits are proportional to real problems. When in doubt, leave it.
See `../sub-skills/rules-explainer.md` for per-rule justification, defenses, and citations, and `tier-rationale.md` §V3 for the evidence.
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: 471k | 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: 471k | 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: 471k | 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 |