Agent Skills: research-scout-extern

  <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 [SC]):
  - A repo to study (URL, org/repo, or clone command) and a topic;
    cleanup confirmed at the end.

  Autonomous (dispatched from a workflow, e.g., a Scout follow-up
  recommended by Precedent Reconnaissance):
  - repo (required): URL, org/repo, or clone command
  - topic (required): what to study in the repo
  - context (optional): why — the prompting need, recorded in the catalog
</inputs>

<outputs>
  A research document persisted to the global extern store
  (repos/{org-repo}/), the catalog updated via script, and the clone
  either left in .extern/ (autonomous) or cleaned up (interactive,
  confirmed). Autonomous mode returns a structured signal carrying
  the document path and whether prior research was reused.
</outputs>

<key-discipline>
  Catalog-first: never clone what has already been studied
  sufficiently. Search the catalog before touching the network; reuse
  or note the gap.

  Disposable clone, permanent research: clones live under .extern/
  (gitignored, deletable); findings persist to the global extern
  store and the catalog. Never store value in .extern/.

  Manage the catalog only through scripts/catalog.py — never
  hand-edit catalog.md.

  Hide-the-intent: every child prompt studying the clone carries the
  study question alone — never the parent task's intent.

  Transfer is factual: "Applicable Patterns" states what matches and
  what differs from our work, not a recommendation to adopt.
</key-discipline>

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

<step n="2" title="Workspace and Clone">
  <action>Load and execute: references/steps/step-02-workspace-clone.xml</action>
</step>

<step n="3" title="Study the Clone">
  <action>Load and execute: references/steps/step-03-study.xml</action>
</step>

<step n="4" title="Synthesize and Persist">
  <action>Load and execute: references/steps/step-04-synthesize-persist.xml</action>
</step>

<step n="5" title="Cleanup and Return">
  <action>Load and execute: references/steps/step-05-cleanup-return.xml</action>
</step>