Autonomous Agents Agentic Workflow
SD: Fill Skill Module — Autonomous Agents Automation Workflow
Find the lowest-coverage module, explore it in the browser, improve its skill files
sidebutton install Autonomous Agents Inputs
- type
- string
- default
- description
- Optional extra instructions for the agent
- type
- string
- default
- ~/workspace
- description
- Working directory for the agent
Allowed Domains
Unrestricted — no domain lock enforced.
Step Summary
2 steps using step types: terminal.openterminal.run
.
Workflow Definition
YAML source for the ops/agent_sd_coverage.yaml workflow. This is the complete definition executed by the SideButton MCP server when Autonomous Agents agents run this automation.
schema_version: 1
id: agent_sd_coverage
title: "SD: Fill Skill Module"
description: "Find the lowest-coverage module, explore it in the browser, improve its skill files"
category:
level: pipeline
domain: engineering
metadata:
agent: true
role: sd
params:
hint:
type: string
default: ""
description: "Optional extra instructions for the agent"
entry_path:
type: string
default: "~/workspace"
description: "Working directory for the agent"
steps:
- type: terminal.open
title: "Agent: SD Coverage"
cwd: "{{entry_path}}"
- type: terminal.run
cmd: >-
source ~/.agent-env && claude --dangerously-skip-permissions
"learn about the target app and Skill Discovery methodology.
review the skill pack coverage summary to find the module with lowest coverage or quality.
navigate to that module on the target app, snapshot all states and interactions.
update the module skill files, install with sidebutton registry update.
commit, push, and create a PR to the skill-packs repo.
{{hint}}
report which module was improved and what was added."
How To Run
Install the Autonomous Agents knowledge pack into your SideButton agent, then dispatch this workflow by its ID ops/agent_sd_coverage.yaml. Agents invoke it directly via the MCP protocol or through the portal.