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/audit_report_template.md
View on GitHub# Draft Audit: {post working title}
- **Author:** {name}
- **Auditor:** {name}
- **Date:** {YYYY-MM-DD}
- **Draft file:** {path}
- **Mode:** {audit only / audit and proposed rewrite}
- **Voice file used:** {path, or "none: no past posts available"}
## Assumptions
List anything that was assumed rather than confirmed. If the author said "just
clean it up", every assumption goes here.
- {assumption}
## Verdict
| Check | Result | Detail |
|-------|--------|--------|
| Tell audit gate | {PASS / FAIL} | blockers {n}, habit load {n} of {limit} |
| Emoji pattern | {PASS / FAIL} | score {n} of 100 |
| Voice comparison | {PASS / FAIL / not run} | {n} measures outside range |
**One-sentence summary:** {what is wrong with the draft, in plain words, or
"nothing that needs changing"}
## Must fix before publishing (remove tier)
| Rule | Text | Fix |
|------|------|-----|
| {RM-xx} | "{quoted text}" | {delete / fill with …} |
## Recommended changes (reduce tier)
Ordered by load. For each, the original, the proposed text, and the reason.
### {RD-xx} {rule name}
- **Original:** "{text}"
- **Proposed:** "{text}"
- **Why:** {one line; from `tell_rules.py --explain`}
- **Keep the original if:** {the catalogue's keep-when condition}
## Facts needed from the author
Nothing below has been invented or estimated. The draft cannot be finished
without these.
| Needed | Question | Answer |
|--------|----------|--------|
| {a figure} | {what was the number before and after, and over what period?} | {…} |
| {a name} | {who did this work, and can they be named?} | {…} |
## Left alone on purpose
Findings that were considered and not acted on.
| Rule | Text | Reason for leaving it |
|------|------|-----------------------|
| {RV-xx / RD-xx} | "{text}" | {author habit per fingerprint / under allowance / literal use} |
## Over-edit check (rewrites only)
- [ ] No new fragments
- [ ] No dash replaced by a full stop
- [ ] No added candor, hesitation or confession
- [ ] No figure, name or date that the author did not supply
- [ ] Contractions and at least one long sentence still present
- [ ] Claim strength unchanged
- [ ] Drift against the fingerprint is no worse than the original
## Proposed final text
```
{the full post, exactly as it should be pasted}
```
Character count: {n}. Re-run both gates on this text before handing it back.
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 |