Agent Skills: research-quick-answer

  <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 [QA]):
  - One or more questions in natural language; scope and output shape
    elicited if the question is too vague to dispatch.

  Autonomous (dispatched from a workflow):
  - questions: array of entries, each with
    - question_text (required)
    - scope (optional; directory globs, file paths, or domain)
    - child_subagent_hint (optional; overrides shape inference)
    - expected_output_shape (required)
  - web_search_approved (boolean; required true for any question
    that routes to web-search-researcher)
</inputs>

<outputs>
  Inline synthesis only — no persisted document. Per question:
  answer with citations, confidence level, and gap note. Autonomous
  mode returns a structured signal (SUCCESS / ERROR /
  CLARIFICATION_NEEDED).
</outputs>

<key-discipline>
  Hide-the-intent: every child prompt carries the question alone —
  never the parent task's intent.

  Silence is data: "searched X, Y, Z; no matches" is a finding, not
  a failure. A negative finding ships as a cited answer.

  No persistence: if a lookup turns out to be load-bearing, the
  caller escalates to [FS] Focused Study or [CI] Comprehensive
  Investigation, which persist.
</key-discipline>

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

<step n="2" title="Plan Dispatch">
  <action>Load and execute: references/steps/step-02-plan-dispatch.xml</action>
</step>

<step n="3" title="Dispatch and Synthesize">
  <action>Load and execute: references/steps/step-03-dispatch-synthesize.xml</action>
</step>

<step n="4" title="Return">
  <action>Load and execute: references/steps/step-04-return.xml</action>
</step>