Agent Skills: ticket-plan

  <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>

<output>
  A Writing Plan section in the ticket body containing:
  - Section writing order (which to draft first, which depend on others)
  - Per-section subagent dispatch (for sections that need additional
    research to fill — typically when a section's scope note
    requires evidence not yet in the research file)
  - Review checkpoints (where to pause during ticket-write for
    user review — especially at Part boundaries for heavy tickets)
  - Per-section length estimates (rough guidance; ticket-write
    treats these as targets, not hard limits)

  Bundle state after this skill: ready for ticket-write.
</output>

<key-responsibility>
  The Writing Plan is the schedule for ticket-write. It exists
  because:
  - Some sections need fresh research before they can be written
    (e.g., "Acceptance Criteria" may need codebase pattern-finder
    dispatched to find test conventions)
  - Heavy tickets cannot be written end-to-end without pause
    points; the user reviews after each Part
  - Some sections depend on others (e.g., "Out of Scope" reads
    cleanest after the main behavior sections are drafted; the
    scope contrast is more visible)

  Per spec §3, this is a soft transition from S to P (no firm
  checkpoint), but the Plan itself is presented to the user once
  drafted — they confirm before ticket-write begins.
</key-responsibility>

<step n="1" title="Load Bundle">
  <action>Load and execute: references/steps/step-01-load-bundle.xml</action>
  <note>
    Read the ticket (Readiness, Design, Structure sections),
    research, questions, linked DRs. The Structure Outline is
    the primary input — every section in the outline gets a
    plan entry.
  </note>
</step>

<step n="2" title="Draft Writing Plan">
  <action>Load and execute: references/steps/step-02-draft-plan.xml</action>
  <note>
    For each section: assign writing order, identify whether
    subagent dispatch is needed for content, estimate length.
    Define review checkpoints (typically at Part boundaries
    for heavy tickets).
  </note>
</step>

<step n="3" title="Align with User">
  <action>Load and execute: references/steps/step-03-align.xml</action>
  <note>
    Present the Writing Plan. Lighter checkpoint than D-phase
    or S-phase (P is tactical, not foundational), but still get
    explicit confirmation before ticket-write begins.
  </note>
</step>

<step n="4" title="Finalize and Handoff">
  <action>Load and execute: references/steps/step-04-finalize-and-handoff.xml</action>
  <note>
    Write the Writing Plan to ticket body, stamp last_updated,
    re-validate, recommend ticket-write.
  </note>
</step>