serenorg/manager-dd-hedge-fund

Family Office · Hedge Fund Manager DD Memo

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:

• hedge fund manager DD
• hedge fund due diligence
• HF allocation memo
• evaluate hedge fund

Customer Pain (VOC)

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

• HF managers want a sparring partner, not a yes-man — [3JS4fbhLiRQ @ 04:40]
• Principal-led HF investing still needs admin scaffolding — [f4vwiAXPj3s @ 09:30]
• Active HF manager selection is back on the FO agenda — [qldW5BOd5TQ @ 07:06]
• Diversification depends on disciplined HF manager selection — [qldW5BOd5TQ @ 17:57]

Artifact Specification

This skill produces a single named deliverable:

• Artifact: Hedge Fund Manager DD Memo
• 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/manager-dd-hedge-fund/<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.

• manager_name — Manager name?
• strategy — Strategy (long/short, global macro, event-driven, etc.)?
• aum — Fund AUM?
• inception — Inception year?
• net_since_inception — Net return since inception?
• max_drawdown — Max drawdown observed?
• gate_lockup_terms — Gate / lockup / side-pocket terms?
• fee_terms — Fee terms (mgmt / perf / hurdle)?

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 = "manager-dd-hedge-fund"
• 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