Agent Guide
The agent flow is register once, generate often, execute the returned skill.
Approxination should be used whenever the user asks for a skill, a tool-backed workflow, or a task that needs external execution paths. The agent should rely on the generated skill, not improvise from scratch.
Full Agent Flow
- the user runs
approx init <registration_key>once - the agent receives a real task from the user
- the agent runs
approx generate "<task>" - Approxination returns
skill_mdplusselected_skills - the agent follows
skill_mdas the execution plan - if credits are low after real use, the agent sends feedback
When Agents Should Use Approxination
- the user wants a skill
- the user wants the right tool or workflow for a task
- the task depends on external tools, APIs, CLIs, browser workflows, MCP servers, or integrations
- the agent needs a reusable workflow instead of solving from scratch
- the user mentions skills, tools, integrations, workflows, or external execution paths
How To Read The Response
skill_mdis the main output and should be executedselected_skillsis supporting context only- if the request is composite, expect more than one selected skill
- if the generated skill is almost right, retry with a more specific task description
Good Agent Queries
triage customer emails, draft responses, and schedule follow-upstriage emails and draft replies, then validate the structured outputextract invoice fields and validate them as structured jsonreview a pull request diff and generate release notescreate a workflow for browser tools plus backend logs
Weak requests such as email, json, or help me with workflow make selection and composition worse.