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
/meetingcommand with task number - A research-phase dispatch (via
/orchestrate) on a founder task withtask_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.jsonnotes_path- Optional, file path to meeting notes or structured meeting fileupdate_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" "$task_number")
skill_name="skill-meeting"
operation="research"
Stage 4: Prepare Delegation Context
{
"task_context": {
"task_number": N,
"project_name": "{project_name}",
"description": "{description}",
"task_type": "founder",
"task_type": "meeting"
},
"notes_path": "/absolute/path/to/meeting-notes.md",
"update_only": false,
"metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json",
"metadata": {
"session_id": "sess_{timestamp}_{random}",
"delegation_depth": 1,
"delegation_path": ["orchestrator", "meeting", "skill-meeting"]
}
}
Stage 5: Invoke Agent
CRITICAL: You MUST use the Agent tool to spawn the agent.
Required Tool Invocation:
Tool: Agent (NOT Skill, NOT Plan)
Parameters:
- subagent_type: "meeting-agent"
- prompt: [Include task_context, notes_path, update_only, metadata_file_path, metadata]
- description: "Investor meeting note processing"
The agent will:
- Read raw meeting notes from
notes_path - Web research the investor for profile data
- Generate structured meeting file with YAML frontmatter + markdown body
- Update CSV tracker in the same directory
- Write metadata file
- Return brief text summary
Stage 5b: Self-Execution Fallback
See context/patterns/thin-wrapper-skill.md § "3b. Self-Execution Fallback" for the full
obligation: if you performed the work above WITHOUT using the Agent tool, write
.return-meta.json now per return-metadata-file.md's schema before proceeding to postflight.
If you DID use the Agent tool, skip this stage.
Postflight (ALWAYS EXECUTE)
The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 5b). Do NOT skip these stages for any reason.
Stage 6: Read Metadata File
padded_num=$(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:
bash .claude/scripts/git-commit-scoped.sh \
--message "task ${task_number}: complete research" \
--session "${session_id}" \
--honest-index-rows "${task_number}" \
-- "specs/${padded_num}_${project_name}/reports/" \
"specs/${padded_num}_${project_name}/.return-meta.json" \
"specs/TODO.md" \
"specs/state.json"
Stage 10: Cleanup
Follow @.claude/context/patterns/skill-postflight-flow.md's Stage 9 (cleanup):
skill_cleanup "$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:
- Edit source/report files - All research work is done by agent
- Run domain analysis or calculations - Analysis is agent work
- Use MCP or WebSearch tools - Research tools are for agent use only
- Analyze or grep source - Analysis is agent work
- 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 the research-phase dispatch (via
/orchestrate) to resume.
The postflight phase is LIMITED TO:
- Reading agent metadata file
- Calling
update-task-status.shfor 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.