agently-triggerflow-playbook
Agently TriggerFlow Playbook
This skill is the scenario-routing entry point for TriggerFlow work in Agently. Use it when the request starts from business workflow requirements rather than specific TriggerFlow APIs. It helps choose the right implementation skill or skill combination. It does not replace the implementation skills themselves.
Prerequisite: Agently >= 4.0.8.5.
Scope
Use this skill for:
- deciding whether a business requirement should be implemented with TriggerFlow
- mapping a workflow requirement to the correct TriggerFlow skill
- deciding when TriggerFlow should be combined with
agently-model-setuporagently-output-control - selecting between general orchestration work, workflow-pattern work, state-and-resource work, sub-flow work, model-integration work, config work, execution-state work, and explicit interrupt or runtime-stream work
Do not use this skill for:
- direct API-level TriggerFlow implementation details
- provider setup or model-request configuration details
- standalone model output parsing without a TriggerFlow workflow
Workflow
- Start with references/scenario-router.md to map the business requirement to the right capability area.
- Read references/current-skill-map.md to choose the implementation skill or skill combination.
- Switch to the selected implementation skill and do the actual coding there.
Routing Rules
- signal-driven workflow primitives, event routing, execution entrypoints, or result semantics ->
agently-triggerflow-orchestration - router patterns, fan-out and fan-in, item-wise worker flows, safe loops, evaluator-optimizer, ReAct loops, or approval-gate workflow design ->
agently-triggerflow-patterns - state placement, flow-versus-execution sharing, runtime-resource boundaries, or restart-safe state design ->
agently-triggerflow-state-and-resources - isolated child workflow, explicit parent-child handoff, or
to_sub_flow(...)boundary ->agently-triggerflow-subflows - workflow step sends model requests, fans out model calls, or uses
delta/instantinside the flow ->agently-triggerflow-model-integration - specialized agent teams, planner-worker, reviewer-reviser, or parallel experts as the main workflow concern ->
agently-multi-agent-patterns - flow definition should be exported, imported, copied, or visualized ->
agently-triggerflow-config - a running execution should be saved, restored, resumed, or rehydrated with resources ->
agently-triggerflow-execution-state - a suspended workflow or conversation should be resumed after restart -> combine
agently-triggerflow-config+agently-triggerflow-execution-state, and addagently-session-memoif memory lives outside the execution - human approval, external resume, waiting execution, or live runtime stream ->
agently-triggerflow-interrupts-and-stream - workflow step needs provider setup -> combine with
agently-model-setup - workflow step needs detailed output-schema or structured-streaming semantics -> combine with
agently-output-control
References
references/scenario-router.mdreferences/current-skill-map.md
More from agentera/agently-skills
agently-playbook
Use when the user wants to build, initialize, validate, optimize, or refactor a model-powered assistant, internal tool, automation, evaluator, or workflow from a business scenario or common problem statement, including project-structure refactors or starter skeletons that may separate model setup, prompt config, and orchestration, even if the request also mentions a UI, app shell, or local model service such as Ollama, and it is still unclear whether the solution should stay a single request, add supporting capabilities, or become orchestration. The user does not need to mention Agently explicitly.
30agently-prompt-management
Use when the user is shaping how one model request or request family should be instructed or templated, including prompt slots, input/instruct/info layering, mappings, recursive placeholder injection, prompt config, YAML or config-file-driven prompt behavior, and reusable prompt structure.
30agently-model-setup
Use when the request is already narrowed to wiring a model endpoint, env vars, settings-file-based model config, `${ENV.xxx}` placeholders, `auto_load_env=True`, or connectivity check for a model-powered feature, including local Ollama, dotenv-loaded DeepSeek or other OpenAI-compatible settings, plugin namespace placement, auth, request options, and minimal verification.
30agently-langchain-to-agently
Use when a migration is already known to stay on the LangChain agent side, including agent setup, tools, structured output, retrieval, and short-term memory.
28agently-triggerflow
Use when the user needs workflow orchestration such as branching, concurrency, approvals, waiting and resume, runtime stream, restart-safe execution, mixed sync/async function or module orchestration, event-driven fan-out, process-clarity refactors that make stages explicit, performance-oriented refactors that collapse split requests, or workflow definitions and chunk-level runtime metadata that must stay visible for debugging and visualization. The user does not need to say TriggerFlow explicitly.
28agently-output-control
Use when the user wants stable structured fields, required keys, reliable machine-readable sections, or downstream-consumable output from one model request, including prompt-config-owned output contracts, `.output(...)`, field ordering, `ensure_keys`, and structured streaming.
28