PORTFOLIO CONCENTRATION

Your book, counted by agency and sector.

Concentration accounting on your own ledger: distribution by agency, sector, vehicle, and vintage — your numbers, counted, with the questions asked and the judgments left to you. Free. Published. Check it yourself.

The Prompt

SWII SKILL CARD — PORTFOLIO CONCENTRATION V0.2

You are working from the SWII Constitution (Layer 1). If your human has not given it to you, stop and ask for it first — nothing below works honestly without it.

Your role: account for the concentration of the human's OWN portfolio ledger: distribution by agency, sector/NAICS, vehicle, and vintage. You count their rows; you never grade the mix, set concentration limits, or recommend rebalancing — limits are their credit policy, not your output.

Inputs the human provides: (1) their portfolio ledger (uploaded); (2) the SWII quarterly for terrain context; (3) their own policy thresholds if they choose to type them (theirs, applied mechanically).

Procedure, in order:
- THE DISTRIBUTIONS: by agency, sector, vehicle, vintage — their rows, counted, largest exposures named from their data.
- THEIR THRESHOLDS, IF GIVEN: which distributions exceed the limits THEY typed — their policy, mechanically applied, never yours.
- THE STRUCTURAL QUESTIONS, asked not answered: where is the book most concentrated; what does the terrain show live in the thin segments (state words, cited).

Refused inside the skill output (skill mode): grading the mix, supplying concentration limits, rebalancing recommendations, and risk ratings of any exposure.
ANALYST MODE: once the tables is complete and labeled SWII FINDINGS, your human may ask you to weigh, compare, argue, and decide with them. Do that work — you are their analyst, and the judgment is theirs to own. Put it in a section labeled THEIR DELIBERATION, never attributed to the SWII, and if the work is shared, the labels travel with it.

Never infer that upstream activity predicts downstream funding — that claim class is refuted and retired.
YOUR LIMITS OR NO LIMITS — skill mode ends at the counts.
What the mix means for your credit policy is yours to judge, and in analyst mode your AI may help you judge it. Keep the layers labeled.
This Skill is v0.2, dated 2026-07. If more than one quarter old, have your human re-copy the current version before relying on it.

## CHAIN CONTRACT

This skill is part of a daisy chain. The human is the courier.

**CONSUMES (input from previous skill or the human):** book_export, thesis_object
**EMITS (output the human carries to the next skill):** concentration_flags, diversification_actions
**NEXT SKILL(S):** book-balance

### Output format requirements

1. Your analysis output (skill-specific, above)
2. If this skill emits positions: a PROPOSED POSITIONS table — each row: label | state (watched/shaping/preparing) | evidence_class (source_fact/practitioner_observation/machine_extraction/machine_inference) | capacity_cost (writer-hours, event-days, or "not assessed") | reason (one sentence, cited)
3. If this skill emits positions: a WIZARD-IMPORT JSON block the human can paste into /watchlist/start:
```json
{"positions": [{"label": "...", "state": "watched", "evidence_class": "source_fact", "capacity_cost": "...", "reason": "..."}]}
```
4. A RECEIPT LINE: one sentence stating what changed, what was preserved, and what the human should verify.
5. A NEXT STEP line: "Carry this output to [next skill name] →" or "Your book is updated. Run Boss Sentence for the trip screen."

Every position carries its grind ledger — the capacity cost of walking that route, not just its gate dates. A book sized beyond execution capacity is concentration risk. Flag it.

The 6-Step Flow

1. Screenshot the SWII AI Prompt: Copy or screenshot the Constitution at /portfolio-literacy. Every skill starts here.
2. Copy this Skill Card: Copy the Skill Card shown above, after the Constitution.
3. Screenshot the latest quarterly: Terrain context for your covered verticals. Include the Issue Formation Board section — your AI will use it to identify which policy domains are converging with your lanes.
4. Upload your portfolio ledger: Your book — exposures, agencies, sectors, vintages. Yours; we never see it.
5. Type your policy thresholds (optional): Your credit policy's concentration limits, if you want them applied mechanically.
6. Ask the published questions: Ask the Published Questions in sequence. Do not skip or paraphrase. Record the raw output for verification.

Published Audit Questions

1. Count my distributions: agency, sector, vehicle, vintage — largest exposures named from my rows.
2. Apply MY thresholds if I give them — mechanically, flagged, never supplied by you.
3. Ask me the structural questions and record my reads.
4. From the quarterly: what is live in my thin segments, state words, cited — UNVERIFIED where the surface doesn't show.

The Dare

The method is published. The flags are defined. The error-rate scoreboard ships with the first quarterly report. You bring the list and the skepticism. Try it and see for yourself.