Skill Slides

Slides Skill

Thin wrapper that delegates slides work to the appropriate subagent based on workflow type and output format:

• slides-research-agent: Material synthesis into slide-mapped research reports
• pptx-assembly-agent: PowerPoint generation from research reports
• slidev-assembly-agent: Slidev project generation from research reports

Note: Plan workflow (/plan present:slides) is handled by skill-slide-planning, not this skill.

IMPORTANT: This skill implements the skill-internal postflight pattern. After the subagent returns, this skill handles all postflight operations (status update, artifact linking, git commit) before returning. This eliminates the "continue" prompt issue between skill return and orchestrator.

Context References

Reference (do not load eagerly):

• Path: .claude/context/formats/return-metadata-file.md - Metadata file schema
• Path: .claude/context/patterns/postflight-control.md - Marker file protocol
• Path: .claude/context/patterns/file-metadata-exchange.md - File I/O helpers
• Path: .claude/context/patterns/jq-escaping-workarounds.md - jq escaping patterns (Issue #1132)

Note: This skill is a thin wrapper with internal postflight. Context is loaded by the delegated agent.

Trigger Conditions

This skill activates when:

• /slides command with task number input
• /research on a task with task_type: "present:slides"
• /implement on a task with task_type: "present:slides" (assemble workflow)
• Present extension is available

Workflow Type Routing

This skill routes to the appropriate subagent based on workflow type and output format:

Note: Assembly agents read design_decisions.theme with a fallback chain: design_decisions -> research report "Recommended Theme" -> default academic-clean.

Input Parameters

Required Parameters

• task_number - Task number (must exist in state.json with task_type="present:slides")
• session_id - Session ID from orchestrator

Optional Parameters

• workflow_type - One of: slides_research, assemble (default: slides_research)

Execution Flow

Stage 1: Input Validation

Validate required inputs:

• task_number - Must be provided and exist in state.json
• Verify task_type is "present:slides"

# Lookup task
task_data=$(jq -r --argjson num "$task_number" \
  '.active_projects[] | select(.project_number == $num)' \
  specs/state.json)

# Validate exists
if [ -z "$task_data" ]; then
  return error "Task $task_number not found"
fi

# Extract fields
task_type=$(echo "$task_data" | jq -r '.task_type // ""')
status=$(echo "$task_data" | jq -r '.status')
project_name=$(echo "$task_data" | jq -r '.project_name')
description=$(echo "$task_data" | jq -r '.description // ""')

# Validate task_type (supports "present:slides" or legacy "slides")
if [ "$task_type" != "present:slides" ] && [ "$task_type" != "slides" ]; then
  return error "Task $task_number is not a slides task (task_type=$task_type)"
fi

Stage 2: Preflight Status Update

Update task status based on workflow type BEFORE invoking subagent.

# Extract output_format from forcing_data (default: "slidev" for backward compatibility)
output_format=$(echo "$task_data" | jq -r '.forcing_data.output_format // "slidev"')

case "$workflow_type" in
  slides_research)
    preflight_status="researching"
    preflight_marker="[RESEARCHING]"
    ;;
  assemble)
    preflight_status="implementing"
    preflight_marker="[IMPLEMENTING]"
    ;;
esac

# Update state.json
if [ -n "$preflight_status" ]; then
  bash .claude/scripts/state-write.sh \
    '(.active_projects[] | select(.project_number == $num)) |= . + {
      status: $status,
      last_updated: $ts,
      session_id: $sid
    }' \
    --session-id "$session_id" \
    --argjson num "$task_number" \
    --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
    --arg status "$preflight_status" \
    --arg sid "$session_id"
fi

Stage 3: Create Postflight Marker

Source skill-base.sh once, then follow @.claude/context/patterns/skill-preflight-flow.md's Stage 3 (marker creation) — the preceding Stage 2 status transition is intentionally left as its own conditional block above (per-workflow-type dispatch is a domain-specific behavior this conversion does not restructure), only the marker write itself moves onto the shared function:

source .claude/scripts/skill-base.sh
padded_num=$(printf "%03d" "$task_number")
skill_name="skill-slides"
skill_create_postflight_marker "$padded_num" "$project_name" "$session_id" "$skill_name" "$workflow_type"

Stage 4: Prepare Delegation Context

Resolve the target agent based on workflow_type and output_format:

case "$workflow_type" in
  slides_research)
    target_agent="slides-research-agent"
    ;;
  assemble)
    case "$output_format" in
      pptx) target_agent="pptx-assembly-agent" ;;
      *)    target_agent="slidev-assembly-agent" ;;
    esac
    ;;
esac

Delegation context:

{
  "session_id": "sess_{timestamp}_{random}",
  "delegation_depth": 1,
  "delegation_path": ["orchestrator", "slides", "skill-slides", "{target_agent}"],
  "timeout": 3600,
  "task_context": {
    "task_number": N,
    "task_name": "{project_name}",
    "description": "{description}",
    "task_type": "present:slides"
  },
  "workflow_type": "slides_research|assemble",
  "output_format": "slidev|pptx (extracted from forcing_data, default: slidev)",
  "forcing_data": "{from state.json task metadata, includes output_format}",
  "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json"
}

Stage 5: Invoke Subagent

CRITICAL: Use the Agent tool to spawn the subagent. Use the target_agent resolved in Stage 4.

Tool: Agent (NOT Skill, NOT Plan)
Parameters:
  - subagent_type: "{target_agent}"
  - prompt: [Include task_context, delegation_context, workflow_type, forcing_data, metadata_file_path]
  - description: "Execute {workflow_type} for task {N}"

Routing table:

DO NOT use Skill(...) - this will FAIL. Always use Task.

Stage 5b: Self-Execution Fallback

CRITICAL: If you performed the work above WITHOUT using the Agent tool (i.e., you read files, wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a .return-meta.json file now before proceeding to postflight. Use the schema from return-metadata-file.md with the appropriate status value for this operation.

If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata.

Postflight (ALWAYS EXECUTE)

The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 5b). Do NOT skip these stages for any reason.

Stage 6: Read Metadata File

metadata_file="specs/${padded_num}_${project_name}/.return-meta.json"

if [ -f "$metadata_file" ] && jq empty "$metadata_file" 2>/dev/null; then
    meta_status=$(jq -r '.status' "$metadata_file")
    artifact_path=$(jq -r '.artifacts[0].path // ""' "$metadata_file")
    artifact_type=$(jq -r '.artifacts[0].type // ""' "$metadata_file")
    artifact_summary=$(jq -r '.artifacts[0].summary // ""' "$metadata_file")
else
    echo "Error: Invalid or missing metadata file"
    meta_status="failed"
fi

Stage 7: Update Task Status (Postflight)

Stage 8: Link Artifacts

Add artifact to state.json with summary. Use the two-step jq pattern to avoid Issue #1132.

Update TODO.md: Link artifact per @.claude/context/patterns/artifact-linking-todo.md with field_name=**Summary**, next_field=**Description**.

Stage 9: Git Commit

case "$workflow_type" in
  slides_research)
    commit_action="complete slides research"
    ;;
  assemble)
    # Branch commit message on output_format
    if [ "$output_format" = "pptx" ]; then
      commit_action="assemble PPTX presentation"
    else
      commit_action="assemble Slidev presentation"
    fi
    ;;
esac

# Targeted staging per .claude/context/standards/git-staging-scope.md — never a repo-wide add
padded_num=$(printf "%03d" "$task_number")
git add "specs/${padded_num}_${project_name}/" "specs/TODO.md" "specs/state.json"
git commit -m "task ${task_number}: ${commit_action}

Session: ${session_id}

Stage 10: Cleanup

Follow @.claude/context/patterns/skill-postflight-flow.md's Stage 9 (cleanup):

skill_cleanup "$padded_num" "$project_name"

Stage 11: Return Brief Summary

Talk Research Success:

Talk research completed for task {N}:
- Synthesized source materials into slide-mapped report
- Talk type: {talk_type}, {slide_count} slides mapped
- Created report at specs/{NNN}_{SLUG}/reports/{MM}_slides-research.md
- Status updated to [RESEARCHED]
- Changes committed with session {session_id}

Assemble Success (Slidev):

Slidev presentation assembled for task {N}:
- Output directory: talks/{N}_{slug}/
- Files created: slides.md, style.css, README.md
- Theme: {theme_name}
- Status updated to [COMPLETED]
- Changes committed with session {session_id}

Assemble Success (PPTX):

PPTX presentation assembled for task {N}:
- Output directory: talks/{N}_{slug}/
- Files created: {slug}.pptx, generate_deck.py
- Theme: {theme_name}
- Status updated to [COMPLETED]
- Changes committed with session {session_id}

Error Handling

Task not found

Talk skill error for task {N}:
- Task not found in state.json
- No status changes made

Wrong language/task_type

Talk skill error for task {N}:
- Task is not a talk task (language={language}, task_type={task_type})
- Use /slides for talk-type tasks
- No status changes made

Metadata file missing

Keep status at preflight level for resume.

Git commit failure

Non-blocking. Log failure but continue.

MUST NOT (Postflight Boundary)

After the agent returns -- whether with a success, partial, or failed status -- this skill MUST proceed immediately to postflight (Stage 6). This applies across all of this skill's workflow_type variants (research, plan, and assemble/implementation alike). The skill MUST NOT:

1. Edit source/report/deck files - All workflow-type-specific work is done by agent
2. Run domain analysis or calculations - Analysis is agent work
3. Use MCP or WebSearch tools - Domain tools are for agent use only
4. Analyze or grep source - Analysis is agent work
5. Write artifacts - Artifact creation is done by agent

PROHIBITION: If the subagent returned partial or failed status, the lead skill MUST NOT attempt to continue, complete, or "fill in" the subagent's work. Report the partial/failed status and let the user re-run the triggering command to resume.

The postflight phase is LIMITED TO:

• Reading agent metadata file
• Calling update-task-status.sh for status updates (state.json + TODO.md), per the workflow-type-specific mapping documented in this skill's own preflight stage
• Linking artifacts in state.json
• Git commit
• Cleanup of temp/marker files

Reference: @.claude/context/standards/postflight-tool-restrictions.md

Return Format

This skill returns a brief text summary (NOT JSON). The JSON metadata is written to the file and processed internally.