mcpField
A
agently-model-response

agently-model-response

github.com/agenteraDevelopment3140 installsUpdated 4d ago
Repository

About agently-model-response

agently-model-response is a skill for choosing how to consume and reuse a response in Agently once the output contract is set. It favors native response APIs and async-first handling over repeated requests or custom stream parsing.

Key features

  1. 01Reuse results through get_response()
  2. 02Prefer async response APIs
  3. 03Use built-in stream modes
  4. 04Avoid duplicate requests
  5. 05Avoid custom stream parsing

Use cases

  1. 01Consuming one result as text and parsed data
  2. 02Handling responses in streaming services
  3. 03Reusing response metadata or progressive updates

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/agentera/agently-skills --skill agently-model-response

After installing, type/agently-model-responsein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

examples/
minimal.py
outputs/
.gitkeep
expected.md
references/
overview.md
scripts/
check.py

Details

From the project README

Agently Model Response

Use this skill when the output contract is already chosen and the remaining issue is how the response instance should be consumed or reused.

The user does not need to say get_response(). Requests to reuse one result as text, parsed data, metadata, or progressive updates should route here.

Native-First Rules

  • prefer get_response() when one request result must be consumed more than once
  • default to async-first response APIs in services, streaming paths, TriggerFlow steps, and any integration that may overlap work
  • treat sync getters and generators as convenience wrappers for scripts, REPL use, or compatibility bridges
  • use delta, instant, specific, or all instead of custom stream splitting logic

Anti-Patterns

  • do not re-issue the same request to obtain text, data, and metadata separately
  • do not build ad hoc field-level stream parsers when instant or streaming_parse already fits

Read Next

  • references/overview.md

Comments

Markdown supported