agently-agent-extensions
Agently Agent Extensions
Use this skill when the problem is agent-side extension rather than prompt shape, output contract, or workflow control.
Native-First Rules
- prefer built-in extension surfaces before handwritten wrappers
- keep extension choice explicit: tools, MCP, FastAPIHelper,
auto_func,KeyWaiter, oragently-devtools - treat
agently-devtoolsas an optional companion package installed from PyPI, not as a required source checkout - keep observation or evaluation bridge wiring in the app layer through
Agently.event_center - combine with
agently-model-responseoragently-triggerflowonly when the scenario needs those layers - prefer built-in Browse support with Playwright or PyAutoGUI before writing browser or desktop-driving wrappers from scratch
Anti-Patterns
- do not build a parallel tool dispatcher before checking native tool and MCP support
- do not create a custom waiter or auto-function shim first
- do not ask users to clone or editable-install DevTools when
pip install agently-devtoolsis the supported public path - do not build a custom runtime upload bridge before checking
ObservationBridge
Read Next
references/overview.mdreferences/devtools.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.
29agently-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.
29agently-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.
29agently-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.
27agently-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.
27agently-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.
27