Kjell Tore Guttormsen
0c9c02a2b1
Closes the S8 re-review (BLOCK 3/4/1). The S8 fix patched only the 2 strings S7 named; the re-review found 6 more same-class survivors. Per the systemic read, this is a comprehensive sweep, not a per-line patch. Reconciled every retired engagement-coefficient + model-fact survivor against the canonical references/algorithm-signals-reference.md (order, not coefficients; comment ≈ 2x a like; no model name/params): - glossary.md: coefficient table + Save-Signal '10x weight' → canonical ordering (citation now true) - engagement-frameworks.md, analytics-interpreter.md, content-optimizer.md, pipeline.md, engagement-coach.md: the 10x/8x/7-9x/2.5x/0.2x system (incl. 4 survivors the re-review did not cite) → ordering - playbook: '15x more algorithmic boost' + video '5x more conversations' → directional, sourced - profile.md + linkedin-voice/SKILL.md: '150B parameter foundation model' → '2026 relevance-ranking model' - quality-scorecard.md: '360Brew Validation' → topic-relevance framing - setup.md: 'thought leadership plugin' → 'LinkedIn Studio plugin' Lint (MAJOR 4): rebuilt scripts/test-runner.sh STALE_STATS to forbid EVERY retired-class phrasing (not the 2 S7 strings) + widened scope to assets/checklists/. Targets retired phrasings (7-9x, (10x), '10x weight', '5x more conversations'), NOT bare 10x/15x/5x (legit 5x5x5 / cadence / pixel-dims / '10x your reach' hyperbole). Proven non-vacuous: catches all 10 retired strings, ignores all 10 legit uses. Tests (MAJOR 7): added no-anchor fall-through tests for recordFirstHourPlan + recordOutreachContact (date scalar not written/reported, section still appended). MINOR 8: reflowed newsletter.md content-repurposer wiring onto one line. test-runner.sh 66/0/0; node --test 94/94 (was 92, +2). NO push until /trekreview re-clears the gate. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
203 lines
7.1 KiB
Markdown
203 lines
7.1 KiB
Markdown
---
|
|
name: linkedin-voice
|
|
description: |
|
|
LinkedIn voice training, profile optimization, content differentiation, and authenticity
|
|
checking. Covers voice profile building, drift detection, topic-relevance profile alignment,
|
|
originality scoring, and maintaining authentic presence on LinkedIn.
|
|
|
|
This skill should be used when the user wants to optimize their LinkedIn profile, train their voice,
|
|
check content originality, detect voice drift, build a voice profile, or ensure
|
|
their content is differentiated from commodity content.
|
|
|
|
Triggers on: "optimize my LinkedIn profile", "topic-relevance", "profile optimization",
|
|
"analyze my voice", "build voice profile", "voice audit", "does this sound like me",
|
|
"voice drift", "is this original", "differentiation check", "originality check",
|
|
"commodity content", "unique angle", "am I authentic", "my writing style",
|
|
"train my voice", "headline optimization".
|
|
---
|
|
|
|
## Voice and Profile Domain
|
|
|
|
This skill covers voice identity, profile optimization for the topic-relevance ranking, content differentiation, and authenticity maintenance.
|
|
|
|
---
|
|
|
|
## Commands
|
|
|
|
| Command | Purpose | When to Use |
|
|
|---------|---------|-------------|
|
|
| `/linkedin:profile` | profile/topic-relevance optimization | Profile setup and audit |
|
|
|
|
## Agents
|
|
|
|
| Agent | Model | Responsibility |
|
|
|-------|-------|----------------|
|
|
| `voice-trainer` | Sonnet | Voice profile building + drift detection |
|
|
| `differentiation-checker` | Sonnet | Originality scoring + commodity detection |
|
|
|
|
---
|
|
|
|
## Profile/Topic Relevance Validation
|
|
|
|
**This is the most significant LinkedIn algorithm change since the platform launched.**
|
|
|
|
### The Fundamental Shift
|
|
|
|
**In the older feed model:** Post something -> Goes to 10% of your audience -> LinkedIn tracks engagement -> Decides if more people should see it.
|
|
|
|
**In the 2026 relevance model:** profile/topic relevance is weighed alongside engagement — content matched to your demonstrated expertise is distributed more widely (including beyond your network), so an off-topic post from a misaligned profile tends to underperform.
|
|
|
|
### The Profile/Topic Relevance Factors
|
|
|
|
The 2026 relevance-ranking model evaluates **five criteria** before your post reaches anyone:
|
|
|
|
| Criteria | What It Checks | Impact if Missing |
|
|
|----------|----------------|-------------------|
|
|
| **About Section** | Does it establish expertise on this topic? | High - first signal of credibility |
|
|
| **Experience Section** | Do you have relevant background with impact statements? | High - proves you've done the work |
|
|
| **Content History** | Have you posted about this topic before? | Medium - consistency signal |
|
|
| **Network** | Are you connected to other professionals in this space? | Medium - social proof |
|
|
| **Engagement Patterns** | Do you comment on posts about this topic? | Medium - active participation |
|
|
|
|
**If these don't align with your post topic, your reach gets throttled. Hard.**
|
|
|
|
### Strategic Implications
|
|
|
|
**Before you post again, audit your profile:**
|
|
|
|
Ask yourself: "If LinkedIn's AI read this, would it believe I'm an expert on the topics I post about?"
|
|
|
|
If the answer is no, fix that first.
|
|
|
|
For detailed algorithm mechanics, see `references/algorithm-signals-reference.md`.
|
|
|
|
---
|
|
|
|
## Profile Optimization Checklist
|
|
|
|
### About Section (CRITICAL)
|
|
|
|
Your About section is the **first signal** telling topic-relevance what you're qualified to discuss.
|
|
|
|
**Structure for optimization:**
|
|
|
|
**First 2-3 lines (visible without "see more"):**
|
|
- Front-load your specific expertise claim
|
|
- Use domain-specific terminology
|
|
- State WHO you help with WHAT problem
|
|
|
|
**Full About section:**
|
|
```
|
|
[Specific expertise claim with domain terminology]
|
|
[WHO you help + specific RESULT you deliver]
|
|
|
|
[Your story - brief, relevant to your expertise]
|
|
[Credentials that validate your expertise]
|
|
[Frameworks/approaches you use]
|
|
[How to connect/work with you]
|
|
```
|
|
|
|
### Experience Section (HIGH IMPACT)
|
|
|
|
Transform each role with impact statements, not task lists:
|
|
|
|
- "Deployed first Copilot Studio agent handling 40% of internal inquiries"
|
|
- "Built RAG solution processing 12,000+ feedback entries"
|
|
- "Achieved documented 968% ROI on AI initiatives"
|
|
|
|
### Headline Formula
|
|
|
|
WHO you help + RESULT you deliver
|
|
|
|
Strong: "Helping public sector leaders implement AI that actually works | AI Advisor @ [your organization]"
|
|
|
|
---
|
|
|
|
## Voice Training
|
|
|
|
### Building a Voice Profile
|
|
|
|
The voice-trainer agent analyzes your writing samples to identify:
|
|
|
|
1. **Sentence structure patterns** -- Short/long mix, fragments, questions
|
|
2. **Word choice signatures** -- Technical depth, jargon level, unique phrases
|
|
3. **Hook style** -- How you naturally open posts
|
|
4. **Storytelling approach** -- How you construct narratives
|
|
5. **Tone signature** -- Formal/informal, humorous/serious, provocative/measured
|
|
|
|
### Voice Drift Detection
|
|
|
|
Over time, content can drift from your authentic voice -- especially when using AI tools.
|
|
|
|
**Warning signs:**
|
|
- Posts feel "corporate" or "polished but generic"
|
|
- Comments don't match your post voice
|
|
- Engagement drops despite consistent posting
|
|
- You wouldn't say this out loud
|
|
|
|
**Prevention:**
|
|
- Quarterly voice audits (use voice-trainer agent)
|
|
- Read posts aloud before publishing
|
|
- Maintain voice samples in `assets/voice-samples/`
|
|
- Compare drafts against your voice profile
|
|
|
|
### Voice Samples
|
|
|
|
**Rule:** Always read `assets/voice-samples/` before generating content. This directory contains reference posts that represent the user's authentic voice.
|
|
|
|
---
|
|
|
|
## Content Differentiation
|
|
|
|
### The Originality Framework
|
|
|
|
The differentiation-checker agent evaluates content across five dimensions:
|
|
|
|
1. **Angle uniqueness** -- Is this perspective novel?
|
|
2. **Evidence quality** -- Are you citing unique sources/experiences?
|
|
3. **Framework originality** -- Are you creating or borrowing frameworks?
|
|
4. **Voice distinctiveness** -- Would readers know this is you without the byline?
|
|
5. **Value density** -- Is every sentence earning its place?
|
|
|
|
### Commodity Content Detection
|
|
|
|
**Red flags for commodity content:**
|
|
- Could be written by anyone in your field
|
|
- Contains only widely-known advice
|
|
- Uses the same examples everyone uses
|
|
- Lacks personal experience or data
|
|
- No contrarian or unique angle
|
|
|
|
**Fix strategies:**
|
|
- Add personal data/experience
|
|
- Take a contrarian position (and defend it)
|
|
- Combine two seemingly unrelated domains
|
|
- Go deeper than surface-level advice
|
|
- Share what you learned from failure, not just success
|
|
|
|
---
|
|
|
|
## Common Patterns
|
|
|
|
**User: "Does this sound like me?"**
|
|
1. Load voice profile and samples
|
|
2. Compare draft against voice signatures
|
|
3. Identify specific drift points
|
|
4. Suggest targeted edits to restore voice
|
|
|
|
**User: "Is this original enough to post?"**
|
|
1. Run differentiation check
|
|
2. Search for similar published content
|
|
3. Score across five dimensions
|
|
4. Suggest strategies to increase uniqueness
|
|
|
|
---
|
|
|
|
## Reference Files
|
|
|
|
| File | When to Read |
|
|
|------|--------------|
|
|
| `references/algorithm-signals-reference.md` | Profile optimization, topic-relevance |
|
|
| `references/linkedin-visual-style.md` | Visual identity consistency |
|
|
| `assets/voice-samples/` | Voice reference (always read before content creation) |
|
|
| `config/user-profile.template.md` | User personalization setup |
|