Update to Postman

{
  "description": "Scores a Postman collection or an OpenAPI spec for how well an AI agent can discover, understand, call, and recover from errors with it — missing examples, undocumented errors, and ambiguous parameters all cost points. Use when the user asks \"is my API agent-ready,\" \"can AI agents use my API,\" \"how agent-friendly is my API,\" or wants to scan, score, or improve a collection or spec for AI/agent consumption. Covers `postman collection ai-readiness` and `postman spec ai-readiness`.",
  "included_files": [],
  "name": "ai-readiness",
  "skill_md_contents": "---\nname: ai-readiness\ndescription: Scores a Postman collection or an OpenAPI spec for how well an AI agent can discover, understand, call, and recover from errors with it — missing examples, undocumented errors, and ambiguous parameters all cost points. Use when the user asks \"is my API agent-ready,\" \"can AI agents use my API,\" \"how agent-friendly is my API,\" or wants to scan, score, or improve a collection or spec for AI/agent consumption. Covers `postman collection ai-readiness` and `postman spec ai-readiness`.\n---\n\n# AI Readiness\n\n## Overview\n\nAn \"agent-ready\" API is one that an AI agent can discover, understand, call correctly, and recover from errors without human intervention. Most APIs aren't there yet.\n\nTwo ways to run this check, same rubric family, different target — pick by what exists:\n\n- `collection ai-readiness <collectionId/path>` scores a Postman collection\n  — by cloud ID, local file path, or a `postman/collections/<name>`\n  local-mode directory.\n- `spec ai-readiness <spec>` scores an OpenAPI specification directly — by\n  cloud ID or local file path — with no collection involved at all.\n\n\n\n## Scoring\n\nThe command computes and prints the score itself — read the fields it\ngives you, don't recompute them:\n\n- **`readiness`** (score 0-100 + bucket) is the headline number. Buckets,\n  low to high: **Limited → Fair → Good → Excellent**.\n- **`confidence`** (`high`/`medium`/`low`) says how many signals it\n  could actually measure vs. had to mark `unknown` — a data-quality\n  caveat, not part of the score.\n\n## Interpreting Results\n\nReport the bucket, score, and confidence the command actually printed\n— don't infer a percentage band. Doc coverage is a modifier via its\nadjustment, not a separate gate; call it out by name when it's `low`,\nsince recommendations flag that first. Also state which verb ran\n(`collection` vs. `spec` `ai-readiness`), which target was scored\n(local path vs. cloud ID), the output mode, and — if `--min-score` was\nset — the resulting exit code, not just \"it passed.\"\n\nYou can ask user if they would like to set this check with a min score guarantee to run on their CI.\n\n## Reference\n\n- `collection-schema-v3` skill — what saved examples and descriptions look\n  like in the git-synced format this command reads.\n- `ci-integration` skill — where `--min-score` fits as a pipeline gate\n  alongside `spec lint`/`collection lint`/`workspace lint`.\n"
}