Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to plan, implement, or optimize employee-generated content (EGC) or employee advocacy. Also use when the user mentions "EGC," "employee advocacy," "employee content," "internal brand ambassadors," "employee social media," "employee advocacy program," "staff advocacy," "LinkedIn employee posts," or "brand ambassador program." For LinkedIn, use linkedin-posts.
.claude/skills/kostja94-employee-generated-content/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 87% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 22% | 0% |
Guides EGC and employee advocacy strategy for AI/SaaS products. EGC is content created by employees (social posts, videos, blogs, testimonials) that reflects authentic workplace and product insights. Employee-shared content generates ~8x more engagement than brand posts; LinkedIn employee posts reach ~561% more than brand content.
When invoking: On first use, if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for product, audience, and brand voice.
Identify:
| Dimension | EGC | UGC | Creator Program | |-----------|-----|-----|-----------------| | Source | Employees | Customers | External creators | | Trust | Company experts (66% vs 47% for ads) | Peer reviews | Influencer reach | | Cost | Low; leverage workforce | Incentives, curation | Credits, payment | | Best for | B2B, SaaS, professional services | Social proof, reviews | Content scale, tutorials |
| Format | Use | Platform | |-------|-----|----------| | Day-in-the-life | Culture, behind-the-scenes | LinkedIn, TikTok, Instagram | | Industry insights | Thought leadership, expertise | LinkedIn | | Short-form video | Quick tips, demos | TikTok, LinkedIn, Instagram | | Testimonials | Product experience | Website, case studies | | Serialized content | Consistent presence | Personal + brand accounts |
Do not force participation. Recognize and nurture organic content from employees already sharing about work. Volunteer participation outperforms mandated programs.
| Practice | Purpose | |----------|---------| | Tiered framework | Map employees by engagement (nano, micro, macro); treat like internal influencer tiers | | Brief templates | Content objectives, brand voice, mandatory disclosures (FTC/ASA) | | Advocacy platforms | Sociabble, EveryoneSocial for brief distribution and tracking | | Incentives | Leaderboards, recognition; avoid heavy-handed quotas | | Training | Improve quality and consistency; keep approval simple | | Centralized hub | Branded hashtags, content library, approval workflow |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 19,155 | 13,865 | -28% | 1 | 1 | 0% | 3,036 | 2,983 | -2% | 0 | 0 | — |
case-02 | pass→pass | 13,502 | 11,073 | -18% | 1 | 1 | 0% | 2,127 | 2,882 | +35% | 0 | 0 | — |
case-03 | pass→pass | 15,746 | 12,164 | -23% | 1 | 1 | 0% | 2,318 | 2,741 | +18% | 0 | 0 | — |
case-04 | fail→fail | 14,749 | 11,914 | -19% | 1 | 1 | 0% | 2,597 | 3,137 | +21% | 0 | 0 | — |
case-05 | fail→pass | 13,662 | 16,797 | +23% | 1 | 1 | 0% | 2,154 | 3,342 | +55% | 0 | 0 | — |
case-06 | pass→pass | 17,012 | 12,677 | -25% | 1 | 1 | 0% | 2,532 | 2,941 | +16% | 0 | 0 | — |
case-07 | fail→fail | 17,046 | 12,443 | -27% | 1 | 1 | 0% | 2,510 | 2,906 | +16% | 0 | 0 | — |
case-08 | fail→pass | 14,268 | 18,922 | +33% | 1 | 1 | 0% | 2,130 | 3,986 | +87% | 0 | 0 | — |
case-09 | fail→pass | 15,398 | 14,765 | -4% | 1 | 1 | 0% | 2,400 | 3,170 | +32% | 0 | 0 | — |
case-10 | fail→fail | 16,124 | 13,544 | -16% | 1 | 1 | 0% | 2,376 | 3,058 | +29% | 0 | 0 | — |
case-11 | pass→pass | 16,555 | 12,856 | -22% | 1 | 1 | 0% | 2,664 | 2,909 | +9% | 0 | 0 | — |
case-12 | fail→pass | 13,505 | 11,154 | -17% | 1 | 1 | 0% | 2,160 | 2,633 | +22% | 0 | 0 | — |
case-13 | fail→pass | 15,041 | 12,772 | -15% | 1 | 1 | 0% | 2,562 | 3,124 | +22% | 0 | 0 | — |
case-14 | fail→fail | 11,017 | 8,184 | -26% | 1 | 1 | 0% | 2,044 | 2,212 | +8% | 0 | 0 | — |
case-15 | pass→fail | 12,372 | 9,883 | -20% | 1 | 1 | 0% | 2,287 | 2,560 | +12% | 0 | 0 | — |
case-16 | pass→pass | 13,895 | 12,100 | -13% | 1 | 1 | 0% | 2,343 | 2,913 | +24% | 0 | 0 | — |
case-17 | fail→fail | 13,042 | 11,889 | -9% | 1 | 1 | 0% | 2,234 | 3,069 | +37% | 0 | 0 | — |
case-18 | pass→pass | 13,372 | 10,298 | -23% | 1 | 1 | 0% | 2,082 | 2,680 | +29% | 0 | 0 | — |
case-19 | fail→fail | 14,207 | 14,318 | +1% | 1 | 1 | 0% | 2,465 | 3,395 | +38% | 0 | 0 | — |
case-20 | fail→pass | 20,308 | 17,223 | -15% | 1 | 1 | 0% | 3,441 | 4,001 | +16% | 0 | 0 | — |
case-21 | pass→pass | 17,707 | 12,374 | -30% | 1 | 1 | 0% | 3,126 | 3,170 | +1% | 0 | 0 | — |
case-22 | pass→pass | 13,538 | 12,785 | -6% | 1 | 1 | 0% | 2,495 | 3,136 | +26% | 0 | 0 | — |
case-23 | pass→pass | 16,323 | 13,630 | -16% | 1 | 1 | 0% | 2,831 | 3,560 | +26% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +22 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.