Autonomous Agents Skill Pack Files

schema_version: 1
id: agent_pm_research
title: "PM: Research"
description: "Investigate a research ticket and post structured findings"
overview: |
  A PM agent investigates the subject of a research ticket — competitive intelligence, customer or market research, due diligence, vendor evaluation, anything where the deliverable is structured findings rather than code. The ticket description defines investigation areas, success criteria, and the expected deliverable format.

  The agent pursues interesting leads beyond the original scope when warranted. Absence of public data is itself reported as a finding. Findings post as a single structured comment back to the ticket.

category:
  level: pipeline
  domain: research

metadata:
  agent: true
  role: pm

params:
  ticket_url:
    type: string
    description: "Jira ticket URL"
  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: PM Research"
    cwd: "{{entry_path}}"
  - type: terminal.run
    cmd: |
      source ~/.agent-env && claude --dangerously-skip-permissions "$(cat <<'SB_PROMPT'
      read ticket with attachments and all comments - {{ticket_url}}. also read the parent epic if any. if it fails, stop and report the error.
      load skill packs for relevant domains. investigate. for each finding capture source URL, verbatim quote where available, and confidence (High/Medium/Low). absence of public data is itself a finding.
      {{hint}}
      write one comment to the ticket with: findings organized per the deliverable spec, every claim cited, confidence ratings, surprises and counter-evidence flagged.
      SB_PROMPT
      )"