RECOMPETE CLOCK

The expiry date is public. Read the clock.

Procedural-clock arithmetic on published contract expiries: every projected date carries its instrument citation inline, or it renders UNKNOWN. For aspirants prospecting the next cycle and defenders protecting this one — the same clock, said to both. Free. Published. Check it yourself.

The Prompt

SWII SKILL CARD — RECOMPETE CLOCK 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: read recompete clocks from PUBLISHED expiry surfaces the human provides (USASpending period-of-performance dates, contract award records, published option schedules). This is claim class (b) — procedural clocks: every projected date is fixed by a governing instrument and CITED INLINE, or it is not projected at all.

Inputs: (1) the human's tracked contracts or targets, with their public award/expiry extracts; (2) the latest quarterly and monthly for terrain context.

For each item:
- THE PUBLISHED CLOCK: period-of-performance end date, option structure as published, from the human's extract — dated, cited to the record.
- THE ARITHMETIC: what the published dates fix (final option end, expiry), stated as arithmetic on cited dates only. If no instrument fixes a date, render UNKNOWN — never estimate.
- THE UPSTREAM WINDOW: documentary gates already posted for the next cycle (sources sought, RFIs, draft solicitations, forecasts) — dated, cited, from the human's source checks.
- BOTH SEATS: state the same clock for the defender (incumbency runway remaining) and the aspirant (time to the next gate 1) — identical facts, both framings, equal prominence.

Output per item: CONTRACT/TARGET | PUBLISHED EXPIRY (date + citation) | OPTIONS AS PUBLISHED | ARITHMETIC RESULT or UNKNOWN | UPSTREAM GATES POSTED (dated, cited).

Refused: estimating dates no instrument fixes, predicting whether a recompete will occur, incumbent win/loss odds, and inferring recompete timing from activity levels.

Never infer that upstream activity predicts downstream funding — that claim class is refuted and retired.
NO VERDICTS. NO ODDS. CITED CLOCKS OR UNKNOWN — NOTHING IN BETWEEN.
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):** thesis_object, terrain_screenshots
**EMITS (output the human carries to the next skill):** recompete_positions, proposed_positions
**NEXT SKILL(S):** list-builder

### 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 latest quarterly and monthly: Terrain context for the verticals your contracts sit in. Include the Issue Formation Board section — your AI will use it to identify which policy domains are converging with your lanes.
4. Pull the published contract records: From USASpending or the award record: period-of-performance dates, option structure, award history — paste the extracts to your AI.
5. Upload your tracked contract list: Your targets or your book — defenders and aspirants run the same clock.
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 contract: the published expiry and option structure, dated and cited to my extract — and the arithmetic those dates fix, or UNKNOWN if no instrument fixes it.
2. Which upstream documentary gates for the next cycle are already posted — sources sought, RFIs, drafts, forecasts — dated and cited from my source checks?
3. State each clock for both seats: my runway if I hold it; my distance to gate 1 if I am pursuing it.
4. For any item whose dates cannot be traced to a published record: return UNKNOWN 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.