Skill Timeline

Timeline Skill

Thin wrapper that delegates timeline research to timeline-agent subagent.

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.

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:

• Task type is "present" and task_type is "timeline"
• Timeline workflow requested via /timeline command or /research routing
• Present extension is available

Workflow Type Routing

This skill routes to timeline-agent with one of two workflow types:

Input Parameters

Required Parameters

• task_number - Task number (must exist in state.json with language="present" and task_type="timeline")
• workflow_type - One of: timeline_research, timeline_plan
• session_id - Session ID from orchestrator

Optional Parameters

• forcing_data - Pre-gathered forcing question responses from /timeline command

Execution Flow

Stage 1: Input Validation

Validate required inputs:

• task_number - Must be provided and exist in state.json
• workflow_type - Must be one of: timeline_research, timeline_plan

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

# Extract pre-gathered forcing_data (if present from Stage 0)
forcing_data=$(echo "$task_data" | jq -r '.forcing_data // null')

# Validate language is "present"
if [ "$task_type" != "present" ]; then
  return error "Task $task_number has language '$task_type', expected 'present'"
fi

Stage 2 + Stage 3: Preflight Status Update and Postflight Marker

Map workflow_type onto update-task-status.sh's research/plan vocabulary, then source skill-base.sh once and follow @.claude/context/patterns/skill-preflight-flow.md in full for Stage 2 (preflight status update) and Stage 3 (marker creation):

source .claude/scripts/skill-base.sh
padded_num=$(printf "%03d" "$task_number")
skill_name="skill-timeline"
case "$workflow_type" in
  timeline_research)
    operation="research"
    ;;
  timeline_plan)
    operation="plan"
    ;;
esac

operation (not the raw "${workflow_type}") is required here: update-task-status.sh's target_status vocabulary has no timeline_research/timeline_plan values, so this skill maps onto the plain research/plan operations. The marker's operation field now reads "research" or "plan" rather than the raw workflow-type string.

Stage 3a: Artifact Number Calculation

Calculate the artifact sequence number following the same pattern as skill-planner:

padded_num=$(printf "%03d" "$task_number")
task_dir="specs/${padded_num}_${project_name}"

# Get current artifact number from state.json
artifact_num=$(jq -r --argjson num "$task_number" \
  '(.active_projects[] | select(.project_number == $num)).next_artifact_number // 1' \
  specs/state.json)

# For research: use current number (advances it)
# For plan: use current round (artifact_num - 1)
case "$workflow_type" in
  timeline_research)
    current_mm=$(printf "%02d" "$artifact_num")
    # Increment next_artifact_number
    bash .claude/scripts/state-write.sh \
      '(.active_projects[] | select(.project_number == $num)).next_artifact_number = ($cur + 1)' \
      --session-id "$session_id" \
      --argjson num "$task_number" \
      --argjson cur "$artifact_num"
    ;;
  timeline_plan)
    current_mm=$(printf "%02d" "$((artifact_num - 1))")
    if [ "$current_mm" = "00" ]; then current_mm="01"; fi
    ;;
esac

Stage 4: Prepare Delegation Context

{
  "session_id": "sess_{timestamp}_{random}",
  "delegation_depth": 1,
  "delegation_path": ["orchestrator", "timeline", "skill-timeline"],
  "timeout": 3600,
  "task_context": {
    "task_number": N,
    "task_name": "{project_name}",
    "description": "{description}",
    "task_type": "present",
    "task_type": "timeline"
  },
  "workflow_type": "timeline_research",
  "forcing_data": { "...pre-gathered data if available..." },
  "artifact_number": "{MM}",
  "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json"
}

Stage 5: Invoke Subagent

CRITICAL: Use the Agent tool to spawn the subagent.

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

DO NOT use Skill(timeline-agent) - this will FAIL.

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)

case "$workflow_type" in
  timeline_research)
    if [ "$meta_status" = "researched" ]; then
      postflight_status="researched"
      postflight_marker="[RESEARCHED]"
    fi
    ;;
  timeline_plan)
    if [ "$meta_status" = "planned" ]; then
      postflight_status="planned"
      postflight_marker="[PLANNED]"
    fi
    ;;
esac

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

Update TODO.md: Use Edit tool to change status marker to the final success state.

Stage 8: Link Artifacts

if [ -n "$artifact_path" ]; then
    # Step 1: Filter out existing artifacts of same type
    bash .claude/scripts/state-write.sh \
      '(.active_projects[] | select(.project_number == $num)).artifacts =
        [(.active_projects[] | select(.project_number == $num)).artifacts // [] | .[] | select(.type == "report" | not)]' \
      --session-id "$session_id" \
      --argjson num "$task_number"

    # Step 2: Add new artifact
    bash .claude/scripts/state-write.sh \
      '(.active_projects[] | select(.project_number == $num)).artifacts += [{"path": $path, "type": $type, "summary": $summary}]' \
      --session-id "$session_id" \
      --argjson num "$task_number" \
      --arg path "$artifact_path" \
      --arg type "$artifact_type" \
      --arg summary "$artifact_summary"
fi

Update TODO.md: Link artifact using count-aware format. Apply the four-case Edit logic from @.claude/context/patterns/artifact-linking-todo.md with field_name=**Research**, next_field=**Plan**.

Stage 9: Git Commit

case "$workflow_type" in
  timeline_research)
    commit_action="complete timeline research"
    ;;
  timeline_plan)
    commit_action="create timeline plan"
    ;;
esac

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

Session: ${session_id}

On commit failure: Non-blocking. Log failure but continue.

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

Timeline Research Success:

Timeline research completed for task {N}:
- Project: {mechanism}, {years}-year, {aims} specific aims
- Critical path: {E} months (95% CI: {low}-{high})
- Regulatory milestones: {count}
- Created report at specs/{NNN}_{SLUG}/reports/{MM}_timeline-research.md
- Status updated to [RESEARCHED]
- Changes committed with session {session_id}

Partial Return:

Timeline research partially completed for task {N}:
- {completed_actions}
- {failed_action} failed: {reason}
- Partial report at specs/{NNN}_{SLUG}/reports/{MM}_timeline-research.md
- Status remains [{preflight_marker}] - run /timeline {N} to continue

Error Handling

Task Not Found

Timeline skill error for task {N}:
- Task not found in state.json
- Verify task exists with /task --sync
- No status changes made

Wrong Language

Timeline skill error for task {N}:
- Task has language '{language}', expected 'present'
- Use /timeline to create timeline tasks
- No status changes made

Metadata File Missing

Keep status at preflight level, preserve postflight marker, report error with resume guidance.

Git Commit Failure

Non-blocking. Log failure but continue with success response.

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.