skill-meeting

name	skill-meeting
description	Investor meeting note processing and CSV tracking
allowed-tools	Agent, Bash, Edit, Read, Write

Meeting Skill

Thin wrapper that routes investor meeting note processing requests to the meeting-agent.

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 Pointers

Reference (do not load eagerly):

• Path: .claude/context/formats/subagent-return.md
• Purpose: Return validation
• Load at: Subagent execution only

Note: This skill is a thin wrapper. Context is loaded by the delegated agent, not this skill.

Trigger Conditions

This skill activates when:

Direct Invocation

• User explicitly runs /meeting command with task number
• User runs /research on a founder task with task_type: "meeting"

Implicit Invocation (during task implementation)

When an implementing agent encounters any of these patterns:

Plan step language patterns:

• "Process meeting notes"
• "Create investor meeting file"
• "Update investor CSV"
• "Meeting report"

Target mentions:

• "meeting notes"
• "investor meeting"
• "CSV tracker"
• "investor profile"

When NOT to trigger

Do not invoke for:

• Market sizing (use skill-market)
• Competitive analysis (use skill-analyze)
• GTM strategy (use skill-strategy)
• Contract review (use skill-legal)
• Financial analysis (use skill-finance)

---

Execution Flow

Stage 1: Input Validation

Validate required inputs:

• task_number - Must be provided and exist in state.json
• notes_path - Optional, file path to meeting notes or structured meeting file
• update_only - Optional, boolean (default: false)

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

# Extract notes_path from task metadata (stored at task creation)
stored_notes_path=$(echo "$task_data" | jq -r '.notes_path // null')

# Use provided notes_path or fall back to stored one
notes_path="${notes_path:-$stored_notes_path}"

if [ -z "$notes_path" ] || [ "$notes_path" = "null" ]; then
  return error "No notes_path found. Provide a file path or ensure task has notes_path stored."
fi

# Validate file exists
if [ ! -f "$notes_path" ]; then
  return error "File not found: $notes_path"
fi

---

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

Source skill-base.sh once, then 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-meeting"
operation="research"

---

Stage 4: Prepare Delegation Context

{
  "task_context": {
    "task_number": N,
    "project_name": "{project_name}",
    "description": "{description}",
    "task_type": "founder",
    "task_type": "meeting"
  },
  "notes_path": "/absolute/path/to/meeting-notes.md",
  "update_only": false,
  "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json",
  "metadata": {
    "session_id": "sess_{timestamp}_{random}",
    "delegation_depth": 1,
    "delegation_path": ["orchestrator", "meeting", "skill-meeting"]
  }
}

---

Stage 5: Invoke Agent

CRITICAL: You MUST use the Agent tool to spawn the agent.

Required Tool Invocation:

Tool: Agent (NOT Skill, NOT Plan)
Parameters:
  - subagent_type: "meeting-agent"
  - prompt: [Include task_context, notes_path, update_only, metadata_file_path, metadata]
  - description: "Investor meeting note processing"

The agent will:

• Read raw meeting notes from notes_path
• Web research the investor for profile data
• Generate structured meeting file with YAML frontmatter + markdown body
• Update CSV tracker in the same directory
• Write metadata file
• Return brief text summary

---

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

padded_num=$(printf "%03d" "$task_number")
metadata_file="specs/${padded_num}_${project_name}/.return-meta.json"

if [ -f "$metadata_file" ] && jq empty "$metadata_file" 2>/dev/null; then
    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
    status="failed"
fi

---

Stage 7: Update Task Status (Postflight)

If status is "researched", update state.json and TODO.md.

Update state.json:

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 "researched"

Update TODO.md: Use Edit tool to change status marker to [RESEARCHED].

---

Stage 8: Link Artifacts

Add artifact to state.json with summary.

IMPORTANT: Use two-step jq pattern to avoid escaping issues.

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

    # Step 2: Add new research 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

Apply the research scope from .claude/context/standards/git-staging-scope.md — targeted staging, never a repo-wide add:

git add \
  "specs/${padded_num}_${project_name}/reports/" \
  "specs/${padded_num}_${project_name}/.return-meta.json" \
  "specs/TODO.md" \
  "specs/state.json"
git commit -m "task ${task_number}: complete research

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

Meeting notes processed for task {N}:
- Investor: {investor_name}
- Meeting date: {meeting_date}
- Meeting file: {output_path}
- Action items: {count}
- CSV tracker: {updated|created|skipped}
- Update-only mode: {yes|no}
- Research report: {artifact_path}
- Status updated to [RESEARCHED]
- Changes committed
- Next: Review meeting file for accuracy

---

MUST NOT (Postflight Boundary)

After the agent returns -- whether with status researched, partial, or failed -- this skill MUST proceed immediately to postflight (Stage 6). The skill MUST NOT:

1. Edit source/report files - All research work is done by agent
2. Run domain analysis or calculations - Analysis is agent work
3. Use MCP or WebSearch tools - Research tools are for agent use only
4. Analyze or grep source - Analysis is agent work
5. Write reports - 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 /research to resume.

The postflight phase is LIMITED TO:

• Reading agent metadata file
• Calling update-task-status.sh for status updates (state.json + TODO.md)
• Linking artifacts in state.json
• Git commit
• Cleanup of temp/marker files

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

---

Return Format

Brief text summary (NOT JSON).

---

Error Handling

Input Validation Errors

Return immediately if task not found or notes_path missing.

File Not Found

Return error if notes_path does not exist on disk.

Metadata File Missing

Keep status as "researching" for resume.

User Abandonment

Return partial status with progress made.

Git Commit Failure

Non-blocking: Log failure but continue.