Agent Skills: research-compare

  <substep n="1a" title="Track Progress">
    <action if="first iteration">Create todo list from all instruction step titles (TodoWrite)</action>
    <action>Mark current step as in_progress (TodoWrite)</action>
  </substep>

  <substep n="1b" title="Handle Step Attributes">
    <check>If optional="true" and NOT YOLO -> Use Question tool to ask user whether to include (Yes/Skip)</check>
    <check>If if="condition" -> Evaluate condition</check>
    <check>If for-each="item" -> Repeat step for each item</check>
    <check>If repeat="n" -> Repeat step n times</check>
  </substep>

  <substep n="1c" title="Execute Step Content">
    <action>Process step instructions (markdown or XML tags)</action>
    <action>Replace {{variables}} with values (ask user if unknown)</action>
    <execute-tags>
      <tag>action -> Perform the action</tag>
      <tag>action type="script" -> Execute as shell command, capture output</tag>
      <tag>check if="condition" -> Conditional block wrapping actions (requires closing &lt;/check&gt;)</tag>
      <tag>ask -> Prompt user using Question tool and WAIT for response. When options exist, present them as selectable choices. For open-ended questions, provide helpful suggested options with custom input enabled</tag>
      <tag>invoke-skill name="skill-name" -> Execute another skill via OpenCode skill system</tag>
      <tag>invoke-agent name="subagent" prompt="task" -> Delegate to subagent via Task tool</tag>
      <tag>goto step="x" -> Jump to specified step (used for explicit loop-back in Q-R style flows)</tag>
    </execute-tags>
  </substep>

  <substep n="1d" title="Handle template-output Tags">
    <if tag="template-output">
      <mandate>Generate content for this section</mandate>
      <mandate>Save to file (Write first time, Edit subsequent)</mandate>
      <action>Display generated content</action>
      <action>Use Question tool to present checkpoint options. WAIT for response.
        <options>
          <option label="Continue" description="Approve this section and move to the next step" />
          <option label="Advanced Elicitation" description="Explore this section deeper before proceeding" />
          <option label="YOLO" description="Auto-complete the rest of this workflow without stopping" />
        </options>
        <if response="Advanced Elicitation">
          <action>Invoke advanced-elicitation skill</action>
        </if>
        <if response="Continue">
          <action>Continue to next step</action>
        </if>
        <if response="YOLO">
          <action>Enter YOLO mode for the rest of the workflow</action>
        </if>
      </action>
    </if>
  </substep>

  <substep n="1e" title="Step Completion">
    <action>Mark current step as completed (TodoWrite)</action>
    <check>If no special tags and NOT YOLO:</check>
    <action>Use Question tool to ask:
      <options>
        <option label="Continue" description="Proceed to the next step" />
        <option label="Edit" description="Revise this step before moving on" />
      </options>
    </action>
  </substep>
</step>

<step n="2" title="Completion">
  <check>Confirm all instruction steps have been executed</check>
  <output>Workflow complete.</output>
</step>

<inputs>
  Interactive (user invokes [CM]):
  - Two or more alternatives to compare; criteria proposed and
    confirmed; mentioned sources read first.

  Autonomous (dispatched from a workflow):
  - alternatives (required): array of two or more to compare
  - criteria (optional): comparison dimensions; derived from context
    when absent
  - decision_context (optional): what the comparison informs, used to
    derive criteria
  - web_search_approved (boolean): required true for external
    alternatives researched via web-search-researcher
  - output_location (optional): override for the research directory
</inputs>

<outputs>
  A tradeoff matrix persisted to the thoughts research directory:
  alternatives × criteria grid with an evidence-backed, cited cell
  per pairing; per-criterion tradeoff notes; a Summary stating the
  shape of the tradeoff — but no weighted score and no declared
  winner. Autonomous mode returns a structured signal carrying the
  matrix path.
</outputs>

<key-discipline>
  No winner. A comparison matrix tempts toward "and the best is" —
  that is a recommendation, and which alternative wins depends on
  weights the orchestrator owns. State per-criterion tradeoffs
  factually and the overall shape of the tradeoff; do NOT compute a
  weighted total or declare a choice.

  Evidence per cell. Every cell carries a citation. An uncited cell
  is an impression, not a comparison. "Could not determine" is a
  valid, honest cell.

  Hide-the-intent: every child prompt carries the alternative + the
  criteria to assess — never the parent task's intent or which
  alternative is hoped to win.
</key-discipline>

<step n="1" title="Orient">
  <action>Load and execute: references/steps/step-01-orient.xml</action>
</step>

<step n="2" title="Derive Criteria">
  <action>Load and execute: references/steps/step-02-derive-criteria.xml</action>
</step>

<step n="3" title="Dispatch per-Alternative Research">
  <action>Load and execute: references/steps/step-03-dispatch-research.xml</action>
</step>

<step n="4" title="Build Matrix">
  <action>Load and execute: references/steps/step-04-build-matrix.xml</action>
</step>

<step n="5" title="Persist">
  <action>Load and execute: references/steps/step-05-persist.xml</action>
</step>

<step n="6" title="Return">
  <action>Load and execute: references/steps/step-06-return.xml</action>
</step>