skill-finance

# Finance Skill Thin wrapper that routes financial analysis requests to the `finance-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 `/finance` command with task number - User runs `/research` on a founder task with `task_type: "finance"` ### Implicit Invocation (during task implementation) When an implementing agent encounters any of these patterns: **Plan step language patterns**: - "Analyze financials" - "Verify revenue numbers" - "Financial model" - "Cash flow analysis" **Target mentions**: - "financial verification" - "revenue model" - "burn rate", "runway" - "unit economics", "CAC/LTV" ### 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) - Cost breakdown from scratch (use skill-spreadsheet) - General business research (use /orchestrate --research, task_type general) --- ## Execution Flow ### Stage 1: Input Validation Validate required inputs: - `task_number` - Must be provided and exist in state.json - `mode` - Optional, one of: AUDIT, MODEL, FORECAST, VALIDATE ```bash # 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 "$task_data" | jq -r '.description // ""') task_type=$(echo "$task_data" | jq -r '.task_type // "finance"') # Extract pre-gathered forcing_data (if present) forcing_data=$(echo "$task_data" | jq -r '.forcing_data // null') pre_gathered_mode=$(echo "$forcing_data" | jq -r '.mode // null' 2>/dev/null) # Validate mode if provided if [ -n "$mode" ]; then case "$mode" in AUDIT|MODEL|FORECAST|VALIDATE) ;; *) return error "Invalid mode: $mode. Must be AUDIT, MODEL, FORECAST, or VALIDATE" ;; esac fi ``` --- ### Stage 2 + Stage 3: Preflight Status Update and Postflight Marker Source `skill-base.sh` once, then follow `@.claude/context/patterns/skill-preflight-flow.md` in full for Stage 2 (preflight status update) and Stage 3 (marker creation): ```bash source .claude/scripts/skill-base.sh padded_num=$(printf "%03d" "$task_number") skill_name="skill-finance" operation="research" ``` --- ### Stage 4: Prepare Delegation Context Include pre-gathered forcing_data when available: ```json { "task_context": { "task_number": N, "project_name": "{project_name}", "description": "{description}", "task_type": "founder", "task_type": "finance" }, "forcing_data": { "mode": "{pre_gathered_mode}", "financial_document": "{pre_gathered_document}", "primary_objective": "{pre_gathered_objective}", "time_horizon": "{pre_gathered_horizon}", "key_assumptions": "{pre_gathered_assumptions}", "decision_context": "{pre_gathered_context}", "gathered_at": "{timestamp}" }, "mode": "AUDIT|MODEL|FORECAST|VALIDATE or use forcing_data.mode", "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json", "metadata": { "session_id": "sess_{timestamp}_{random}", "delegation_depth": 1, "delegation_path": ["orchestrator", "finance", "skill-finance"] } } ``` **Note**: If `forcing_data` is present from STAGE 0 of /finance command, pass it to the agent. The agent will use pre-gathered data and only ask follow-up questions for missing details. --- ### 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: "finance-agent" - prompt: [Include task_context, forcing_data, mode, metadata_file_path, metadata] - description: "Financial analysis and verification" ``` The agent will: - Use pre-gathered forcing_data if available (skip already-answered questions) - Present mode selection only if not pre-selected - Read financial documents if file path provided - Extract and validate numbers from source documents - Create verification spreadsheet (.xlsx with formulas) - Export JSON metrics for Typst integration - Create research report at specs/{NNN}_{SLUG}/reports/ - 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 ```bash 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 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. ```bash 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 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}_${project_name}/.return-meta.json" \ "specs/TODO.md" \ "specs/state.json" ``` --- ### Stage 10: Cleanup Follow `@.claude/context/patterns/skill-postflight-flow.md`'s Stage 9 (cleanup): ```bash skill_cleanup "$padded_num" "$project_name" ``` --- ### Stage 11: Return Brief Summary ``` Financial analysis research completed for task {N}: - Mode: {mode}, {questions_asked} forcing questions completed - Document: {financial_document} - Objective: {primary_objective} - Pre-gathered data used: {yes/no} - Verification spreadsheet: specs/{NNN}_{SLUG}/financial-verification.xlsx - Research report: specs/{NNN}_{SLUG}/reports/01_{short-slug}.md - Status updated to [RESEARCHED] - Changes committed - Next: Run /plan {N} to create implementation plan ``` --- ## 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). Expected successful return: ``` Financial analysis research completed for task {N}: - Mode: AUDIT, 7 forcing questions completed - Document: Q1 2026 P&L statement - Objective: Verify revenue projections for Series A deck - Pre-gathered data used: yes (5 questions from STAGE 0) - Verification spreadsheet: specs/330_financial_analysis_q1/financial-verification.xlsx - Research report: specs/330_financial_analysis_q1/reports/01_financial-analysis.md - Status updated to [RESEARCHED] - Changes committed with session sess_1736700000_abc123 - Next: Run /plan 330 to create implementation plan ``` --- ## Error Handling ### Input Validation Errors Return immediately if task not found. ### Metadata File Missing Keep status as "researching" for resume. ### User Abandonment Return partial status with progress made.