# Send Backend 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": "backend", "name": "Backend", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ivangdavila/backend", "canonicalUrl": "https://clawhub.ai/ivangdavila/backend", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/backend", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=backend", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "backend", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T09:13:25.362Z", "expiresAt": "2026-05-07T09:13:25.362Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=backend", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=backend", "contentDisposition": "attachment; filename=\"backend-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "backend" }, "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/backend" }, "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/backend", "downloadUrl": "https://openagent3.xyz/downloads/backend", "agentUrl": "https://openagent3.xyz/skills/backend/agent", "manifestUrl": "https://openagent3.xyz/skills/backend/agent.json", "briefUrl": "https://openagent3.xyz/skills/backend/agent.md" } } ``` ## Documentation ### Error Handling Never expose stack traces to clients—log internally, return generic message Structured error responses: code, message, request ID—enables debugging without leaking Fail fast on bad input—validate at entry point, not deep in business logic Unexpected errors: 500 + alert—expected errors: appropriate 4xx ### Input Validation Validate everything from outside—query params, headers, body, path params Whitelist valid input, don't blacklist bad—reject unknown fields Validate early, before any processing—save resources, clearer errors Size limits on all inputs—prevent memory exhaustion attacks ### Timeouts Everywhere Database queries: set timeout, typically 5-30s External HTTP calls: connect timeout + read timeout—don't wait forever Overall request timeout—gateway or middleware level Background jobs: max execution time—prevent zombie processes ### Retry Patterns Exponential backoff: 1s, 2s, 4s, 8s...—prevents thundering herd Add jitter: randomize delay—prevents synchronized retries Idempotency keys for non-idempotent operations—safe to retry Circuit breaker for failing dependencies—stop hammering, fail fast ### Database Practices Connection pooling: reuse connections—creating is expensive Transactions scoped minimal—hold locks briefly Read replicas for read-heavy workloads—separate read/write traffic Prepared statements always—SQL injection prevention, query plan cache ### Caching Strategy Cache invalidation strategy decided upfront—TTL, event-based, or both Cache at right layer: query result, computed value, HTTP response Cache stampede prevention—lock or probabilistic early expiration Monitor hit rate—low hit rate = wasted resources ### Rate Limiting Per-user/IP limits on expensive operations—login, signup, search Different limits for different operations—read vs write Return Retry-After header—tell clients when to retry Rate limit early in request pipeline—save resources ### Health Checks Liveness: is process running—restart if fails Readiness: can handle traffic—remove from load balancer if fails Startup probe for slow-starting services—don't kill during init Health checks fast and cheap—don't hit database on every probe ### Graceful Shutdown Stop accepting new requests first—drain load balancer Wait for in-flight requests to complete—with timeout Close database connections cleanly—prevent connection leaks SIGTERM handling: graceful; SIGKILL after timeout ### Logging Structured logs (JSON)—parseable by log aggregators Request ID in every log—trace request across services Log level appropriate: debug for dev, info/error for prod Sensitive data never logged—passwords, tokens, PII ### API Design Versioning strategy from day one—path (/v1/) or header Pagination for list endpoints—cursor or offset; include total count Consistent response format—same envelope everywhere Meaningful status codes—201 for create, 204 for delete, 404 for not found ### Security Hygiene Secrets from environment or vault—never in code or config files Dependencies updated regularly—automated with Dependabot/Renovate Principle of least privilege—service accounts with minimal permissions Authentication and authorization separated—who you are vs what you can do ### Observability Metrics: request count, latency percentiles, error rate—the RED method Distributed tracing for microservices—follow request across services Alerting on symptoms, not causes—high error rate, not CPU usage Dashboards for operational visibility—know normal to spot abnormal ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ivangdavila - 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: 2026-04-30T09:13:25.362Z - Expires at: 2026-05-07T09:13:25.362Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/backend) - [Send to Agent page](https://openagent3.xyz/skills/backend/agent) - [JSON manifest](https://openagent3.xyz/skills/backend/agent.json) - [Markdown brief](https://openagent3.xyz/skills/backend/agent.md) - [Download page](https://openagent3.xyz/downloads/backend)