Claude Skills by MCPJam

Generate comprehensive eval tests for any MCP server using @mcpjam/sdk. Supports Jest and Vitest with deterministic and LLM-driven test patterns.

Convert MCPJam Playground-generated test cases into @mcpjam/sdk eval tests. Produces one test per case, exactly matching the user's prompts and expectations.

Interpret and use `mcpjam` probe, doctor, OAuth, apps conformance, tools, resources, and prompts output conservatively against MCP 2025-11-25. Use when interacting with MCP servers, executing tools, triaging findings, performing security reviews, deciding whether a CLI finding is real or overstated, or turning inspection output into an engineer-facing report with severity and confidence.

Convert an existing test corpus (promptfoo YAML, pytest, Jest, CSV) into an MCPJam eval suite file at .mcpjam/evals/*.yaml, stamping every case with an honest import status, then validate it offline with `mcpjam cloud eval validate` until it exits 0. Use when asked to import, migrate, or port existing evals/tests into MCPJam, or when a repo already has prompt tests and needs an MCPJam suite.

Drive MCPJam's hosted eval tools end to end — check what a run will cost and disclose, launch it, poll it to a verdict, and triage a failure down to the step that failed. Use when connected to MCPJam's MCP server and asked to run, re-run, investigate, or compare eval results, rather than to author eval files locally.

Defines every member of MCPJam's user-value chain vocabulary — the six stages, the five stage states, the twenty-nine stage reasons, the seven failure categories, the four verdicts and the stage-analytics exclusion classes — plus the population rules that decide what a count means. Use when reading a `decisionSummary`, a stage chain, or stage analytics returned by MCPJam's eval tools and you need to know what a wire value means or whether a number can be compared.