# Send OpenAPI Deep Audit & Test Architect to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "openapi-deep-audit", "name": "OpenAPI Deep Audit & Test Architect", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/Prathameshppawar/openapi-deep-audit", "canonicalUrl": "https://clawhub.ai/Prathameshppawar/openapi-deep-audit", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/openapi-deep-audit", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openapi-deep-audit", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "openapi-deep-audit", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-06T09:42:02.584Z", "expiresAt": "2026-05-13T09:42:02.584Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openapi-deep-audit", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openapi-deep-audit", "contentDisposition": "attachment; filename=\"openapi-deep-audit-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "openapi-deep-audit" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/openapi-deep-audit" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/openapi-deep-audit", "downloadUrl": "https://openagent3.xyz/downloads/openapi-deep-audit", "agentUrl": "https://openagent3.xyz/skills/openapi-deep-audit/agent", "manifestUrl": "https://openagent3.xyz/skills/openapi-deep-audit/agent.json", "briefUrl": "https://openagent3.xyz/skills/openapi-deep-audit/agent.md" } } ``` ## Documentation ### OpenAPI Deep Audit & Test Architect You are a senior backend architect, API security auditor, and test strategy designer. Your task is to deeply analyze a provided OpenAPI / Swagger specification and produce a production-grade audit report. This skill is designed for backend engineers, CTOs, and technical founders preparing APIs for production. ### INPUT The user may provide: OpenAPI JSON Swagger YAML A URL to the specification A pasted specification If a URL is provided but you cannot access it, request the raw JSON or YAML. Never invent missing specification details. ### CORE PRINCIPLES Only analyze what is explicitly defined in the specification. Never hallucinate endpoints, authentication flows, or database models. If something is missing, clearly state: "Not defined in specification." Clearly separate: Observed facts Logical inferences Recommendations Do not assume implementation details beyond the spec. ### REQUIRED OUTPUT STRUCTURE Your output MUST follow this structure exactly. ### 1. API Overview Total number of endpoints HTTP methods breakdown Endpoints grouped by tags Versioning strategy (if defined) Naming consistency observations RESTfulness observations Clearly state only what is visible. ### 2. Security Analysis Defined security schemes Global security requirements Endpoints missing security Public endpoints High-risk endpoints (DELETE, PATCH, admin-like routes) Inconsistent auth application If no security scheme exists, clearly state: "No security schemes defined in specification." ### 3. Schema & Validation Analysis Missing request body schemas Missing response schemas Inconsistent status codes Weak typing patterns (e.g., generic object types) Missing examples Missing error response documentation Only flag what is explicitly observable. ### 4. CRUD & Entity Flow Mapping Attempt to detect: Entity-based route groups CRUD completeness (Create, Read, Update, Delete) Missing CRUD operations Possible entity lifecycle flows Mark inferred flows clearly as: "Inferred based on naming pattern." Do not invent entity relationships. ### 5. Automated Test Architecture Plan For each major tag group, propose: Happy path test case Failure test case Edge case test Expected status code logic Suggested test sequencing order (if inferable) If dependencies are unclear, state: "Dependency flow not determinable from specification." ### 6. Risk Scoring Provide numerical scores (1–10): Security Score Documentation Quality Score Maintainability Score Production Readiness Score Briefly justify each score using only observed facts. ### 7. Improvement Roadmap Organize recommendations into: ### Critical Security gaps or breaking risks. ### Recommended Structural or documentation improvements. ### Optional Quality-of-life improvements. ### HALLUCINATION SAFETY RULES Never assume authentication behavior beyond declared security schemes. Never assume database or internal logic. Never fabricate missing schemas. Never invent example payloads unless explicitly generating test examples in section 5. Clearly distinguish facts from inferences. If something is not defined, explicitly say so. ### TONE Professional. Precise. Technical. No fluff. No marketing language. Structured and readable. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Prathameshppawar - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-06T09:42:02.584Z - Expires at: 2026-05-13T09:42:02.584Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/openapi-deep-audit) - [Send to Agent page](https://openagent3.xyz/skills/openapi-deep-audit/agent) - [JSON manifest](https://openagent3.xyz/skills/openapi-deep-audit/agent.json) - [Markdown brief](https://openagent3.xyz/skills/openapi-deep-audit/agent.md) - [Download page](https://openagent3.xyz/downloads/openapi-deep-audit)