borghei/Claude-Skills / tools/linkedin/linkedin-humanizer
linkedin-humanizer
VerifiedAudits and rewrites LinkedIn drafts to remove machine-sounding patterns: tiered tell catalogue, emoji-pattern scoring, rule explanations, and a voice fingerprint built from the author's own posts. Use when a draft reads generated, before publishing, or when an edit flattened someone's voice.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.9 KB |
| assets/audit_report_template.md | markdown | 2.3 KB |
| assets/sample_draft.txt | markdown | 1.0 KB |
| assets/sample_draft_edited.txt | markdown | 1.1 KB |
| assets/sample_past_posts.txt | markdown | 2.7 KB |
| assets/sample_voice.json | config | 899 B |
| assets/voice_profile_template.md | markdown | 3.0 KB |
| references/emoji-patterns.md | markdown | 7.4 KB |
| references/rewrite-playbook.md | markdown | 12.0 KB |
| references/rule-catalogue.md | markdown | 19.4 KB |
| references/voice-fingerprint-guide.md | markdown | 9.7 KB |
| scripts/emoji_audit.py | script | 8.6 KB |
| scripts/tell_audit.py | script | 10.8 KB |
| scripts/tell_rules.py | script | 17.5 KB |
| scripts/voice_fingerprint.py | script | 11.1 KB |
assets/voice_profile_template.md
View on GitHub# Voice Profile: {author name}
Fill this in once per author and keep it with their fingerprint file. Sections
1 and 2 come from `scripts/voice_fingerprint.py`; sections 3 to 6 can only come
from the author or someone who edits them regularly.
- **Profile owner:** {who maintains this file}
- **Last rebuilt:** {YYYY-MM-DD}
- **Source posts:** {path to the past-posts file} ({n} posts, dated {from} to {to})
- **Were any source posts drafted with assistance?** {no / yes: which, and why they were kept}
## 1. Measured habits
Paste from `voice_fingerprint.py --input {file}`.
| Measure | Median | Notes |
|---------|--------|-------|
| Post length (words) | {n} | |
| Opening line (characters) | {n} | |
| Words per sentence | {n} | |
| Sentence spread | {n} | |
| Words per paragraph | {n} | |
| First-person words per 100 | {n} | |
| Contractions per 100 | {n} | |
| Dashes per 100 words | {n} | |
| Fragments per post | {n} | |
| Triples per post | {n} | |
| Emoji per post | {n} | Use as `--usual` in the emoji audit |
| Closes on a question | {share} | |
Confidence label from the tool: {thin / usable / solid}
## 2. Protected rules
Rules the audit waives for this author, and why.
| Rule | Reason reported by the tool | Agreed with the author? |
|------|-----------------------------|-------------------------|
| {RD-xx} | {reason} | {yes / no / not asked} |
Rules the author has asked to keep **against** the tool's advice (record the
date and their reason):
- {rule id}: {reason}, {date}
## 3. Words and phrases
- **Says:** {words the author reaches for: e.g. "customers" not "users"}
- **Never says:** {words that are off-limits for this author, beyond the catalogue}
- **Spelling and style:** {British / American; numerals or words under ten; Oxford comma}
- **Names things as:** {how they refer to their company, team, product, role}
## 4. How they open and close
- **Typical opening:** {a figure / a date / a scene / a flat claim}
- **Would never open with:** {…}
- **Typical close:** {a question / the last fact / a postscript}
- **Asks for comments?** {never / sometimes, in these words: …}
## 5. Subjects and limits
- **Writes about:** {three or four subjects}
- **Will not write about:** {clients by name, salaries, politics, …}
- **People they may name without asking:** {…}
- **People or companies that must be described by role only:** {…}
- **Figures that must be checked with {whom} before publishing:** {…}
## 6. Things an editor should know
- **Humour:** {dry / none / self-deprecating; an example}
- **How they handle being wrong in public:** {…}
- **A post of theirs that sounds most like them:** {first line or link kept privately}
- **A past edit they rejected, and why:** {…}
## Gate settings for this author
```bash
python3 scripts/tell_audit.py --input {draft.txt} --voice {voice.json} --max-load {6}
python3 scripts/emoji_audit.py --input {draft.txt} --usual {n} --fail-under {60}
python3 scripts/voice_fingerprint.py --input {past_posts.txt} --compare {draft.txt} --max-drift {2}
```
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 |