Use this skill to organize application LLM generation workflows: reusable versioned prompts, structured outputs, service-level model selection, and tracing. It helps keep workflow identity and prompt identity distinct so generation behavior can be validated and observed consistently.
Use for application prompts, generateObject/generateText, model selection and generation tracing. Excludes provider adapters and agent snapshots.
Run score Not tested
See how to installThis skill guides the design of application LLM calls as reusable, traceable workflows. It recommends managing reusable prompts together with their JSON schemas, schema names, and prompt versions, while keeping model configuration, input validation, storage, and error handling in the owning service. For workflows using generateObject or generateText, it distinguishes the business scenario, prompt version, and schema name in tracing, and keeps model selection independent of prompt version. It also covers validating generated results, handling failures, and checking for reuse of old prompts or scenarios.
Use it when adding an LLM generation workflow to a service, sharing a long prompt instead of embedding it in the service, or tracking generation quality, duration, and cost by business workflow.
Provider adapter conventions and agent execution snapshots are outside this skill’s scope.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 26, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Implement business-facing LLM calls as explicit, independently observable workflows. Keep prompt identity, model policy, structured output, and tracing responsibilities separate.
Before editing a call, inspect:
packages/prompts for reusable application prompts;apps/server/src/services/aiGeneration for the server-side structured generation wrapper;packages/const/src/llmGenerationTracing.ts for scenario names;packages/llm-generation-tracing for tracing option and registry behavior;Use agent-tracing for execution-snapshot diagnosis and agent-runtime-hooks for lifecycle hook behavior. Neither owns application LLM generation conventions.
packages/prompts/src/chains: the message builder, JSON schema, schema name, and prompt version should be exported together. Do not leave substantial system prompts or model-facing input serialization embedded in a service.AiGenerationService, tracing entity IDs, Zod validation, persistence, and business error handling do not belong in the prompt chain.*_PROMPT_VERSION beside the prompt it versions and export both from the same module.v<major> or v<major>.<minor>, for example v1 or v1.2.promptVersion. Do not include a feature or scenario prefix such as expertise-ingestion-v1; scenario carries workflow identity.export const EXAMPLE_PROMPT_VERSION = 'v1';
export const EXAMPLE_SYSTEM_PROMPT = `...`;
Treat scenario as the stable product workflow and lifecycle-stage partition, not as a label for a prompt, schema, model, or helper.
TRACING_SCENARIOS before adding a call.schemaName for structured generation and relevant entity IDs when available.For every new or corrected generation workflow:
scenario, promptVersion, and schemaName where applicable.bun run check <changed-files...> and bun run check --type for cross-package changes.Use the testing skill for test mechanics and the typescript skill for TypeScript changes.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use this skill to verify a delivery by exercising the real product through a suitable surface such as a CLI, web app, desktop app, or iOS Simulator. It helps create or find a verification plan, capture evidence, and publish an acceptance report.
Use this skill to add an AI model provider to LobeHub across runtime integration, model cards, settings, branding, documentation, and acceptance checks. It also covers provider documentation updates and distinguishes new providers from models added to an existing provider.
Use this skill to add a server-side environment variable that sets a default for a user setting. It walks through validation, server configuration and store merging, plus updating the example environment file and self-hosting documentation.
Provides guidance for registering hooks around an agent’s execution steps, tool calls, human approvals, context compression, and sub-agent calls. Hooks can observe events, supply local mock tool results, or use webhooks to allow or deny tool results under configured policies.
Build event-driven background workflows for agents by defining sources, interpreting them as signals, and running actions through policies. It also guides asynchronous handoffs, deduplication, scoped execution, completion receipts, and observability.
Use this skill to run end-to-end acceptance checks for bot channels in real desktop chat apps. It drives apps such as Discord, Slack, Telegram, WeChat, Lark, and QQ to send a message, wait for a response, and capture the result.