Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automatically routes Postman and API-related requests to the correct command. Use when user mentions APIs, collections, specs, testing, mocks, docs, security, or Postman.
.claude/skills/kunanonj-cursor-plugin-postman-postman-routing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | -71% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -30% | 0% |
When a user mentions anything related to APIs, Postman, collections, specs, or API development, automatically route to the correct command. Do not ask the user to pick a command. Just invoke the right one.
| User intent patterns | Route to | Command | |---------------------|----------|---------| | "sync", "update collection", "create collection", "import spec", "push to postman", "keep in sync", "deploy spec" | Sync collections with code | /postman:sync | | "generate", "client", "code for", "wrapper", "SDK", "consume", "typed client", "api client" | Generate client code | /postman:codegen | | "find", "search", "what endpoints", "is there an API for", "show me", "what's available", "discover", "list APIs" | Discover APIs | /postman:search | | "test", "run tests", "check if", "validate", "test results", "failing tests" | Run collection tests | /postman:test | | "mock", "fake API", "stub", "mock server", "frontend needs", "mock URL" | Create mock server | /postman:mock | | "docs", "documentation", "describe", "document", "API reference", "missing descriptions" | Improve documentation | /postman:docs | | "security", "audit", "OWASP", "vulnerabilities", "secure", "auth check", "exposed" | Security audit | /postman:security | | "agent-ready", "AI compatible", "scan my API", "grade my API", "readiness", "agent friendly" | API readiness analysis | Invoke readiness-analyzer agent | | "set up", "configure", "connect postman", "API key", "get started" | First-run setup | /postman:setup |
/postman:sync, run that command directly/postman:codegen/postman:syncgetWorkspaces).Some requests span multiple commands:
| Request | Workflow | |---------|----------| | "Set up my API from scratch" | /postman:sync (create collection) -> /postman:mock (create mock) -> /postman:docs (generate docs) | | "Is my API production-ready?" | /postman:security (audit) + /postman:test (run tests) + readiness-analyzer (if agent-readiness asked) | | "I updated my spec, sync and re-test" | /postman:sync (push changes) -> /postman:test (run collection) |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | fail→pass | 16,507 | 1,443 | -91% | 1 | 1 | 0% | 3,518 | 1,018 | -71% | 0 | 0 | — |
case-02 | fail→fail | 18,108 | 12,460 | -31% | 1 | 1 | 0% | 2,934 | 1,620 | -45% | 0 | 0 | — |
case-01 | fail→pass | 10,616 | 2,330 | -78% | 1 | 1 | 0% | 1,726 | 1,155 | -33% | 0 | 0 | — |
case-03 | fail→pass | 8,144 | 2,734 | -66% | 1 | 1 | 0% | 1,551 | 1,323 | -15% | 0 | 0 | — |
case-04 | fail→fail | 4,478 | 2,126 | -53% | 1 | 1 | 0% | 706 | 1,134 | +61% | 0 | 0 | — |
case-05 | fail→fail | 10,560 | 3,434 | -67% | 1 | 1 | 0% | 2,085 | 1,295 | -38% | 0 | 0 | — |
case-06 | fail→pass | 5,592 | 2,035 | -64% | 1 | 1 | 0% | 826 | 1,142 | +38% | 0 | 0 | — |
case-07 | fail→pass | 8,474 | 2,187 | -74% | 1 | 1 | 0% | 1,616 | 1,129 | -30% | 0 | 0 | — |
case-08 | fail→pass | 7,866 | 2,377 | -70% | 1 | 1 | 0% | 1,247 | 1,114 | -11% | 0 | 0 | — |
case-09 | fail→fail | 14,417 | 3,360 | -77% | 1 | 1 | 0% | 2,425 | 1,419 | -41% | 0 | 0 | — |
case-10 | fail→fail | 10,074 | 2,390 | -76% | 1 | 1 | 0% | 2,091 | 1,247 | -40% | 0 | 0 | — |
case-11 | pass→pass | 5,253 | 2,328 | -56% | 1 | 1 | 0% | 942 | 1,195 | +27% | 0 | 0 | — |
case-12 | fail→fail | 2,578 | 3,008 | +17% | 1 | 1 | 0% | 371 | 933 | +151% | 0 | 0 | — |
case-13 | fail→pass | 11,298 | 5,789 | -49% | 1 | 1 | 0% | 2,278 | 1,908 | -16% | 0 | 0 | — |
case-14 | fail→pass | 14,409 | 5,550 | -61% | 1 | 1 | 0% | 2,406 | 1,889 | -21% | 0 | 0 | — |
case-15 | fail→pass | 16,815 | 2,824 | -83% | 1 | 1 | 0% | 1,241 | 1,343 | +8% | 0 | 0 | — |
case-16 | fail→pass | 11,107 | 1,406 | -87% | 1 | 1 | 0% | 1,826 | 981 | -46% | 0 | 0 | — |
case-18 | fail→pass | 6,597 | 2,197 | -67% | 1 | 1 | 0% | 1,020 | 1,118 | +10% | 0 | 0 | — |
case-19 | fail→pass | 9,689 | 7,921 | -18% | 1 | 1 | 0% | 1,109 | 1,739 | +57% | 0 | 0 | — |
case-20 | pass→pass | 4,718 | 2,822 | -40% | 1 | 1 | 0% | 923 | 1,339 | +45% | 0 | 0 | — |
case-21 | pass→pass | 7,714 | 5,849 | -24% | 1 | 1 | 0% | 1,483 | 1,846 | +24% | 0 | 0 | — |
case-22 | pass→pass | 3,310 | 2,995 | -10% | 1 | 1 | 0% | 645 | 1,439 | +123% | 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 20 counted toward the lift figure. The other 2 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 20 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.