Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query LinkedIn API — profile info, posts (when approved), org stats. Supports multi-account via OAuth. Use when user asks about LinkedIn metrics, LinkedIn profile, LinkedIn posts, or any reference to LinkedIn analytics.
.claude/skills/evolution-foundation-int-linkedin/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -66% | 0% |
LinkedIn integration to monitor user profile and (future) Company Page. Multi-account via OAuth (Social Auth App).
Accounts configured via make social-auth. Saved in .env:
envSOCIAL_LINKEDIN_1_LABEL=Your Name SOCIAL_LINKEDIN_1_ACCESS_TOKEN=YOUR_TOKEN SOCIAL_LINKEDIN_1_PERSON_URN=urn:li:person:YOUR_URN
bashpython3 {project-root}/.claude/skills/int-linkedin/scripts/linkedin_client.py <command> [args]
bashlinkedin_client.py accounts # List accounts linkedin_client.py profile [account] # Profile (name, email, photo) linkedin_client.py my_posts [account] [N] # Recent posts (requires scope w_member_social) linkedin_client.py post_stats POST_URN # Reactions/comments of a post linkedin_client.py org_followers [account] # Org followers (requires Advertising API) linkedin_client.py summary # Summary of all accounts
| Scope | Status | LinkedIn Product | |-------|--------|-----------------| | openid profile email | Active | Sign In with OpenID Connect | | w_member_social | Active | Share on LinkedIn | | r_organization_social | Pending | Advertising API (request form) | | r_organization_admin | Pending | Advertising API (request form) |
https://api.linkedin.com/rest/ (org/analytics endpoints)Linkedin-Version: 202603, X-Restli-Protocol-Version: 2.0.0/v2/userinfo (OpenID Connect)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,428 | 6,982 | -6% | 1 | 1 | 0% | 1,093 | 862 | -21% | 0 | 0 | — |
case-02 | fail→fail | 5,843 | 6,723 | +15% | 1 | 1 | 0% | 960 | 1,003 | +4% | 0 | 0 | — |
case-03 | fail→fail | 2,861 | 5,717 | +100% | 1 | 1 | 0% | 388 | 711 | +83% | 0 | 0 | — |
case-04 | fail→pass | 12,088 | 1,951 | -84% | 1 | 1 | 0% | 2,067 | 770 | -63% | 0 | 0 | — |
case-05 | fail→pass | 8,369 | 2,256 | -73% | 1 | 1 | 0% | 1,273 | 818 | -36% | 0 | 0 | — |
case-06 | fail→pass | 11,418 | 2,952 | -74% | 1 | 1 | 0% | 1,843 | 925 | -50% | 0 | 0 | — |
case-07 | fail→pass | 11,986 | 2,507 | -79% | 1 | 1 | 0% | 1,983 | 749 | -62% | 0 | 0 | — |
case-08 | fail→pass | 14,110 | 1,977 | -86% | 1 | 1 | 0% | 2,237 | 752 | -66% | 0 | 0 | — |
case-09 | pass→pass | 5,377 | 2,288 | -57% | 1 | 1 | 0% | 827 | 872 | +5% | 0 | 0 | — |
case-15 | fail→fail | 6,802 | 4,066 | -40% | 1 | 1 | 0% | 990 | 1,103 | +11% | 0 | 0 | — |
case-10 | fail→pass | 5,387 | 1,920 | -64% | 1 | 1 | 0% | 822 | 766 | -7% | 0 | 0 | — |
case-11 | pass→pass | 3,434 | 1,817 | -47% | 1 | 1 | 0% | 569 | 757 | +33% | 0 | 0 | — |
case-12 | fail→pass | 8,123 | 1,619 | -80% | 1 | 1 | 0% | 1,320 | 682 | -48% | 0 | 0 | — |
case-13 | pass→pass | 10,030 | 3,466 | -65% | 1 | 1 | 0% | 1,637 | 987 | -40% | 0 | 0 | — |
case-14 | fail→pass | 6,942 | 3,009 | -57% | 1 | 1 | 0% | 898 | 879 | -2% | 0 | 0 | — |
case-16 | pass→pass | 7,725 | 2,420 | -69% | 1 | 1 | 0% | 1,256 | 856 | -32% | 0 | 0 | — |
case-17 | pass→pass | 13,389 | 1,653 | -88% | 1 | 1 | 0% | 1,927 | 740 | -62% | 0 | 0 | — |
case-18 | fail→pass | 2,986 | 2,056 | -31% | 1 | 1 | 0% | 380 | 630 | +66% | 0 | 0 | — |
case-19 | fail→fail | 12,287 | 5,053 | -59% | 1 | 1 | 0% | 2,017 | 1,247 | -38% | 0 | 0 | — |
case-20 | fail→pass | 5,413 | 4,551 | -16% | 1 | 1 | 0% | 824 | 1,246 | +51% | 0 | 0 | — |
case-21 | fail→pass | 9,911 | 5,788 | -42% | 1 | 1 | 0% | 1,880 | 1,531 | -19% | 0 | 0 | — |
case-22 | fail→pass | 3,671 | 3,103 | -15% | 1 | 1 | 0% | 529 | 1,156 | +119% | 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. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +55 percentage points is the difference between those two pass rates over the 19 comparable cases.
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.