Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Knowledge about AI agent API compatibility. Use when user asks about API readiness, agent compatibility, or wants to improve their API for AI consumption.
.claude/skills/kunanonj-cursor-plugin-postman-agent-ready-apis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -10% | 0% |
Knowledge about what makes an API "agent-ready" for AI agent consumption.
An agent-ready API is one that an AI agent can:
Most APIs are built for human developers who can read docs, interpret ambiguous errors, and make judgment calls. AI agents can't do that. They need explicit metadata, structured errors, and predictable patterns.
Agent-readiness is measured across 8 pillars with 48 total checks. See pillars.md for the complete reference.
| Pillar | What It Measures | |--------|-----------------| | Metadata | operationIds, summaries, descriptions, tags | | Errors | Error schemas, HTTP codes, messages, retry guidance | | Introspection | Parameter types, required fields, enums, examples | | Naming | Consistent casing, RESTful paths, HTTP method semantics | | Predictability | Response schemas, pagination patterns, date formats | | Documentation | Auth docs, rate limits, external references | | Performance | Response times, caching headers, rate limit headers | | Discoverability | OpenAPI version, server URLs, contact info, license |
Suggest running the readiness analyzer when:
| Score | Verdict | What It Means | |-------|---------|---------------| | 90-100 | Excellent | API is highly agent-compatible. Minor improvements only. | | 70-89 | Agent Ready | Meets the bar. Some improvements recommended. | | 50-69 | Needs Work | Agents will struggle. Address critical and high issues. | | 0-49 | Not Ready | Significant gaps. Agents will fail frequently. |
These fixes have the highest impact-to-effort ratio:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,855 | 4,359 | -56% | 1 | 1 | 0% | 1,618 | 1,553 | -4% | 0 | 0 | — |
case-02 | fail→fail | 12,142 | 10,407 | -14% | 1 | 1 | 0% | 1,845 | 2,644 | +43% | 0 | 0 | — |
case-03 | fail→pass | 11,196 | 4,628 | -59% | 1 | 1 | 0% | 1,906 | 1,602 | -16% | 0 | 0 | — |
case-04 | pass→pass | 9,192 | 4,965 | -46% | 1 | 1 | 0% | 1,426 | 1,667 | +17% | 0 | 0 | — |
case-05 | fail→pass | 18,363 | 1,658 | -91% | 1 | 1 | 0% | 1,116 | 1,012 | -9% | 0 | 0 | — |
case-10 | fail→pass | 9,693 | 2,695 | -72% | 1 | 1 | 0% | 1,559 | 1,154 | -26% | 0 | 0 | — |
case-06 | fail→pass | 11,938 | 5,353 | -55% | 1 | 1 | 0% | 1,784 | 1,607 | -10% | 0 | 0 | — |
case-07 | fail→pass | 9,553 | 6,287 | -34% | 1 | 1 | 0% | 1,739 | 1,858 | +7% | 0 | 0 | — |
case-08 | fail→pass | 11,536 | 2,662 | -77% | 1 | 1 | 0% | 2,006 | 1,140 | -43% | 0 | 0 | — |
case-09 | pass→pass | 17,458 | 1,176 | -93% | 1 | 1 | 0% | 2,950 | 915 | -69% | 0 | 0 | — |
case-11 | fail→pass | 5,531 | 1,967 | -64% | 1 | 1 | 0% | 1,021 | 1,061 | +4% | 0 | 0 | — |
case-12 | pass→pass | 5,505 | 1,607 | -71% | 1 | 1 | 0% | 867 | 986 | +14% | 0 | 0 | — |
case-13 | fail→pass | 5,706 | 1,872 | -67% | 1 | 1 | 0% | 1,005 | 1,062 | +6% | 0 | 0 | — |
case-14 | pass→pass | 6,679 | 1,464 | -78% | 1 | 1 | 0% | 1,116 | 937 | -16% | 0 | 0 | — |
case-15 | fail→pass | 8,331 | 1,525 | -82% | 1 | 1 | 0% | 1,391 | 1,014 | -27% | 0 | 0 | — |
case-16 | fail→pass | 7,225 | 2,146 | -70% | 1 | 1 | 0% | 1,062 | 1,150 | +8% | 0 | 0 | — |
case-17 | fail→pass | 6,359 | 2,148 | -66% | 1 | 1 | 0% | 965 | 1,072 | +11% | 0 | 0 | — |
case-18 | fail→pass | 9,834 | 1,551 | -84% | 1 | 1 | 0% | 1,684 | 993 | -41% | 0 | 0 | — |
case-19 | fail→pass | 12,427 | 1,637 | -87% | 1 | 1 | 0% | 2,291 | 982 | -57% | 0 | 0 | — |
case-20 | pass→pass | 2,623 | 1,812 | -31% | 1 | 1 | 0% | 403 | 1,059 | +163% | 0 | 0 | — |
case-21 | pass→pass | 2,326 | 3,129 | +35% | 1 | 1 | 0% | 415 | 1,293 | +212% | 0 | 0 | — |
case-22 | pass→pass | 3,452 | 2,610 | -24% | 1 | 1 | 0% | 600 | 1,200 | +100% | 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.