consolidated-reporting-spec

name	consolidated-reporting-spec
description	Family office: Produce a specification for consolidated family-office reporting across entities, accounts, and asset classes.

Family Office · Consolidated Reporting Specification

For Claude: How to Use This Skill

Skill instructions are preloaded in context when this skill is active. Do not perform filesystem searches or tool-driven exploration to rediscover them; use the guidance below directly.

When to Use

Invoke when the advisor asks about:

• consolidated reporting
• reporting spec
• family-office reporting
• portfolio reporting requirements

Customer Pain (VOC)

Synthesized from family-office operator interviews (see references/voc-evidence.md for full provenance):

• Operators openly ask why consolidated reporting matters at all — buy-in is not a given — [_4_z6Rs7350 @ 00:14]
• Insourcing performance reporting only pencils out around the billion-dollar mark; below that, families need a packaged spec — [HV86G3RCPV0 @ 22:39]
• Customized dashboards are the visibility-and-transparency surface families actually pay for — [_URp9ryeUlQ @ 52:01]
• Dashboards must be built to walk the principal through their day, not just display data — [f4vwiAXPj3s @ 21:52]

Artifact Specification

This skill produces a single named deliverable:

• Artifact: Consolidated Reporting Specification
• Format at this iteration: markdown (artifact.md) plus a structured interview.json capturing every advisor input. PDF / DOCX / XLSX companion renders and DMS / Snowflake push land in the execution-pipeline PR tracked under issue #427.

The artifact is written to a skill-local path, not a global directory:

<invocation-cwd>/artifacts/family-office/consolidated-reporting-spec/<YYYYMMDD-HHMMSS>/
  artifact.md
  interview.json
  manifest.json

Interview Inputs

Minimum-viable interview — the skill asks only what is needed to personalize the deliverable. Pre-fill rules against family memory land in the execution- pipeline PR.

• reporting_platform — Reporting platform (Addepar / Masttro / Eton / spreadsheet)?
• entities_to_consolidate — Entities to consolidate?
• asset_classes_in_scope — Asset classes in scope?
• reporting_cadence — Reporting cadence?
• key_metrics — Key metrics to surface?
• recipient_list — Recipient list and their views?

Workflow

1. Run python scripts/agent.py --config config.json (or invoke via Claude Code with a config blob).
2. The agent validates config, runs the interview (TTY or fixture-driven), and produces the artifact under the canonical local path.
3. The agent writes manifest.json with artifact metadata (name, version, content hash, pillar, skill_name, created_at).
4. The agent optionally writes memory entries to the knowledge skill's memory_objects table via psycopg if config.memory_dsn is provided. Without a DSN, memory writes are skipped cleanly.

Memory Conventions

Memories written by this skill are tagged with:

• subject = the artifact name
• source = "consolidated-reporting-spec"
• memory_type ∈ {decision, assumption, commitment, open_question}

Security & Confidentiality

• Never log interview answers or artifact contents at INFO level.
• Never include SSN, EIN, account numbers, or full financial amounts in log lines. If a WHERE-clause field carries such data, log only a sha256 hash.
• The artifact directory is local-only at this iteration. DMS push (with confidentiality-label routing) is handled by the execution-pipeline PR.

Reference

• Design spec: 20260419_Family_Office_Skill_Claude_Desigh.md
• Implementation plan: 20260420_FamilyOffice_Skills_Plan.md
• Catalog rebuild tracking: https://github.com/serenorg/seren-skills/issues/427