Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automate Folk tasks via Rube MCP (Composio). Always search tools first for current schemas.
.claude/skills/composiohq-folk-automation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-18 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -17% | 0% |
Automate Folk operations through Composio's Folk toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/folk
RUBE_MANAGE_CONNECTIONS with toolkit folkRUBE_SEARCH_TOOLS first to get current tool schemasGet Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit folkAlways discover available tools before executing workflows:
RUBE_SEARCH_TOOLS
queries: [{use_case: "Folk operations", known_fields: ""}]
session: {generate_id: true}This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Folk task"}]
session: {id: "existing_session_id"}RUBE_MANAGE_CONNECTIONS
toolkits: ["folk"]
session_id: "your_session_id"RUBE_MULTI_EXECUTE_TOOL
tools: [{
tool_slug: "TOOL_SLUG_FROM_SEARCH",
arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"RUBE_SEARCH_TOOLSRUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing toolsmemory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})| Operation | Approach | |-----------|----------| | Find tools | RUBE_SEARCH_TOOLS with Folk-specific use case | | Connect | RUBE_MANAGE_CONNECTIONS with toolkit folk | | Execute | RUBE_MULTI_EXECUTE_TOOL with discovered tool slugs | | Bulk ops | RUBE_REMOTE_WORKBENCH with run_composio_tool() | | Full schema | RUBE_GET_TOOL_SCHEMAS for tools with schemaRef |
Powered by Composio
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | fail→fail | 8,835 | 1,897 | -79% | 1 | 1 | 0% | 1,520 | 1,036 | -32% | 0 | 0 | — |
case-18 | fail→pass | 8,066 | 1,967 | -76% | 1 | 1 | 0% | 1,541 | 1,075 | -30% | 0 | 0 | — |
case-01 | fail→fail | 5,020 | 4,401 | -12% | 1 | 1 | 0% | 365 | 958 | +162% | 0 | 0 | — |
case-02 | fail→fail | 5,034 | 5,268 | +5% | 1 | 1 | 0% | 946 | 1,065 | +13% | 0 | 0 | — |
case-03 | fail→fail | 3,046 | 2,789 | -8% | 1 | 1 | 0% | 444 | 1,217 | +174% | 0 | 0 | — |
case-04 | fail→fail | 4,455 | 9,164 | +106% | 1 | 1 | 0% | 781 | 1,388 | +78% | 0 | 0 | — |
case-05 | fail→pass | 5,379 | 3,819 | -29% | 1 | 1 | 0% | 1,195 | 1,505 | +26% | 0 | 0 | — |
case-06 | fail→pass | 6,683 | 6,005 | -10% | 1 | 1 | 0% | 1,300 | 1,873 | +44% | 0 | 0 | — |
case-07 | pass→pass | 6,415 | 3,629 | -43% | 1 | 1 | 0% | 1,126 | 1,502 | +33% | 0 | 0 | — |
case-08 | pass→pass | 3,966 | 2,552 | -36% | 1 | 1 | 0% | 630 | 1,210 | +92% | 0 | 0 | — |
case-09 | fail→pass | 5,068 | 2,071 | -59% | 1 | 1 | 0% | 843 | 1,125 | +33% | 0 | 0 | — |
case-10 | pass→pass | 6,294 | 5,374 | -15% | 1 | 1 | 0% | 1,078 | 1,766 | +64% | 0 | 0 | — |
case-11 | fail→pass | 10,585 | 3,968 | -63% | 1 | 1 | 0% | 1,840 | 1,522 | -17% | 0 | 0 | — |
case-12 | fail→pass | 4,581 | 2,566 | -44% | 1 | 1 | 0% | 829 | 1,176 | +42% | 0 | 0 | — |
case-13 | pass→pass | 3,588 | 1,843 | -49% | 1 | 1 | 0% | 573 | 1,107 | +93% | 0 | 0 | — |
case-14 | pass→pass | 4,866 | 3,705 | -24% | 1 | 1 | 0% | 787 | 1,489 | +89% | 0 | 0 | — |
case-15 | fail→pass | 8,707 | 1,664 | -81% | 1 | 1 | 0% | 1,658 | 1,098 | -34% | 0 | 0 | — |
case-16 | pass→pass | 4,819 | 7,581 | +57% | 1 | 1 | 0% | 407 | 1,039 | +155% | 0 | 0 | — |
case-19 | pass→pass | 9,473 | 7,625 | -20% | 1 | 1 | 0% | 1,937 | 2,217 | +14% | 0 | 0 | — |
case-20 | pass→pass | 2,882 | 1,606 | -44% | 1 | 1 | 0% | 449 | 1,025 | +128% | 0 | 0 | — |
case-21 | pass→pass | 1,870 | 2,048 | +10% | 1 | 1 | 0% | 299 | 1,132 | +279% | 0 | 0 | — |
case-22 | fail→pass | 5,544 | 4,530 | -18% | 1 | 1 | 0% | 1,136 | 1,559 | +37% | 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 +36 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.