Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Add a new team member to Langfuse's canonical team data and shared team table. Use when onboarding a new employee who needs to appear on the website team, press, about, careers, or handbook pages.
.claude/skills/langfuse-add-yourself-to-team-langfuse/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 22% | 0% |
Add a new team member to Langfuse. Ask the user for the following information before proceeding:
public/images/people/<key>.jpgOnce you have the information, update the following source files:
data/authors.jsonAdd a new entry at the end (before the closing }). Use a lowercase, no-special-chars version of the name as the key (e.g. annabellschafer):
json"<key>": { "firstName": "<first name>", "name": "<full name>", "title": "<role>", "image": "/images/people/<key>.jpg", "twitter": "<twitter handle>", // omit if not provided "github": "<github username>", // omit if not provided "linkedin": "<linkedin handle>" // omit if not provided }
components-mdx/team-members.mdxThis is the canonical website team list. It is rendered by the press, about, careers, and handbook team pages. Append a new table row at the end:
md| **<Full Name>** | <Role> | [Twitter](https://x.com/<twitter>), [LinkedIn](https://www.linkedin.com/in/<linkedin>/), [GitHub](https://github.com/<github>) |
Omit any social links that were not provided.
Do not add team rows directly to any other page. Those pages should import and render the canonical component:
mdximport TeamMembers from "@/components-mdx/team-members.mdx"; <TeamMembers />
If a page has a hand-written team table or list, replace it with the shared TeamMembers import instead of adding another copy. Please do a quick search for some team members to confirm that there are no copies of this table.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 11,065 | 6,460 | -42% | 1 | 1 | 0% | 2,049 | 1,741 | -15% | 0 | 0 | — |
case-01 | fail→pass | 6,335 | 13,051 | +106% | 1 | 1 | 0% | 1,184 | 1,362 | +15% | 0 | 0 | — |
case-02 | fail→pass | 10,845 | 2,487 | -77% | 1 | 1 | 0% | 2,008 | 1,050 | -48% | 0 | 0 | — |
case-03 | fail→pass | 6,067 | 2,815 | -54% | 1 | 1 | 0% | 1,054 | 1,048 | -1% | 0 | 0 | — |
case-04 | pass→pass | 11,987 | 4,654 | -61% | 1 | 1 | 0% | 2,095 | 1,391 | -34% | 0 | 0 | — |
case-06 | fail→pass | 9,317 | 6,044 | -35% | 1 | 1 | 0% | 1,723 | 1,674 | -3% | 0 | 0 | — |
case-07 | fail→pass | 7,099 | 5,647 | -20% | 1 | 1 | 0% | 1,466 | 1,784 | +22% | 0 | 0 | — |
case-08 | fail→pass | 5,240 | 3,068 | -41% | 1 | 1 | 0% | 1,067 | 1,285 | +20% | 0 | 0 | — |
case-09 | fail→pass | 4,607 | 3,203 | -30% | 1 | 1 | 0% | 1,027 | 1,261 | +23% | 0 | 0 | — |
case-10 | fail→pass | 3,195 | 1,753 | -45% | 1 | 1 | 0% | 571 | 905 | +58% | 0 | 0 | — |
case-11 | fail→pass | 13,433 | 3,006 | -78% | 1 | 1 | 0% | 2,601 | 1,161 | -55% | 0 | 0 | — |
case-12 | fail→pass | 3,887 | 1,851 | -52% | 1 | 1 | 0% | 655 | 845 | +29% | 0 | 0 | — |
case-13 | fail→pass | 13,009 | 2,943 | -77% | 1 | 1 | 0% | 1,886 | 1,168 | -38% | 0 | 0 | — |
case-14 | fail→pass | 7,282 | 2,691 | -63% | 1 | 1 | 0% | 1,319 | 1,022 | -23% | 0 | 0 | — |
case-15 | pass→pass | 7,188 | 3,205 | -55% | 1 | 1 | 0% | 1,447 | 1,231 | -15% | 0 | 0 | — |
case-16 | pass→pass | 6,248 | 1,941 | -69% | 1 | 1 | 0% | 1,183 | 879 | -26% | 0 | 0 | — |
case-17 | fail→fail | 3,371 | 3,382 | +0% | 1 | 1 | 0% | 527 | 1,215 | +131% | 0 | 0 | — |
case-18 | pass→pass | 7,671 | 3,174 | -59% | 1 | 1 | 0% | 1,330 | 1,105 | -17% | 0 | 0 | — |
case-19 | pass→pass | 6,622 | 3,903 | -41% | 1 | 1 | 0% | 1,175 | 1,336 | +14% | 0 | 0 | — |
case-20 | fail→pass | 5,000 | 2,980 | -40% | 1 | 1 | 0% | 964 | 996 | +3% | 0 | 0 | — |
case-21 | fail→pass | 6,902 | 3,581 | -48% | 1 | 1 | 0% | 1,479 | 1,335 | -10% | 0 | 0 | — |
case-22 | fail→fail | 4,835 | 5,834 | +21% | 1 | 1 | 0% | 897 | 1,007 | +12% | 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 21 counted toward the lift figure. The other 1 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 +64 percentage points is the difference between those two pass rates over the 21 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.