CADENCE RECEIPTS

This door has opened every fall for six years. That's a receipt, not a promise.

Read a door's posting history from the published record: N postings in M years, dated. A receipt is evidence a door recurs — never a guarantee it will. Free. Published. Check it yourself.

The Prompt

SWII SKILL CARD — CADENCE RECEIPTS V0.1

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: compute cadence receipts from PUBLISHED posting history the human provides. A cadence receipt is the SWII's mechanism (c): "this door has opened each cycle for N of the last M years" — computed from dated posting records, stated with its dates, never extended into a promise.

Inputs: (1) the human's list of doors (programs, offices, opportunity families) under review; (2) posting-history extracts they pull from the public record (Grants.gov posting archives, agency program pages, SAM.gov archive search) and the SWII's free cadence tables where published for their vertical.

For each door:
- THE RECEIPT: N postings in the last M years, each posting dated and cited from the extracts. State the receipt exactly: "posted in N of the last M cycles: [dates]." If the extract shows fewer than 3 cycles of history, render RECEIPT-THIN with what exists.
- THE PATTERN, DESCRIBED NOT PROJECTED: the months/season the postings historically landed, as dates on the record. You may say "historically posted in the fall" with the dates; you may NOT say "will post this fall" or assign likelihood.
- THE CALENDAR GAP: whether the human's tracked list contains this door's historical season — calendar awareness, not a prediction.

Refused: converting a receipt into a forecast, probabilities of reposting, "expect this in October," extrapolating from activity levels, and any receipt not backed by dated postings in evidence.

Never infer that upstream activity predicts downstream funding — that claim class is refuted and retired.
NO VERDICTS. RECEIPTS ARE HISTORY WITH DATES — NEVER A PROMISE.
This Skill is v0.1, 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, cadence_screenshots
**EMITS (output the human carries to the next skill):** receipt_entries, state_transition_log
**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 SWII AI Prompt (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 free cadence tables for your vertical: Where the SWII publishes cadence tables for your vertical, capture them — they are the governed posting-history layer. Include the Issue Formation Board section — your AI will use it to identify which policy domains are converging with your lanes.
4. Pull posting-history extracts: From Grants.gov archives, agency program pages, or SAM.gov archive search: the door's dated posting history — paste the extracts to your AI.
5. Upload your door list: The programs and opportunity families you want receipts for.
6. Ask the published questions: Ask the Published Questions (below) in sequence. Do not skip or paraphrase. Record the raw output for verification.

Published Audit Questions

1. For each door: the receipt — posted in N of the last M cycles, every posting dated and cited from my extracts — or RECEIPT-THIN if fewer than 3 cycles are in evidence.
2. Describe each door's historical season as dates on the record — described, never projected.
3. Which of my tracked doors' historical seasons fall inside the next two quarters of my calendar — as calendar awareness, not prediction?
4. For any door whose history I could not evidence: return RECEIPT-THIN or UNVERIFIED with the evidence gap noted.

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.