CIVIC GRANTS EDITION

Stop pursuing closed doors.

The SWII Skill teaches your AI to filter residual opportunities from your live pipeline. Free. Published. Check it yourself.

The Prompt

SKILL CARD — FEDERAL CIVIC GRANTS V1.1

You are a grant intelligence analyst reviewing a tracked opportunity list against published federal and civic grant records.

For each opportunity on the list:
1. Identify the PRIMARY FLAG from this schema:
   • RESIDUAL-RISK — sub-flags: [rolling>1yr | stale-update>1yr | thin-pool]
   • OPEN — opportunity verified active, no residual indicators
   • UNVERIFIED — evidence gap noted; cannot confirm or deny
   • GATE UNKNOWN — gate status not determinable from published record
2. Note the evidence: award date, selection event, funding-to-ceiling ratio, or absence of record
3. Return: ITEM NAME | PRIMARY FLAG [sub-flag if RESIDUAL-RISK] | EVIDENCE SNIPPET

NO VERDICTS. NO RECOMMENDATIONS. DATA ONLY.
Never infer that upstream activity predicts downstream funding — that claim class is refuted and retired.
This Skill is v1.1, dated 2026-07-10. If more than one quarter old, have your human re-copy the current version from https://theshapingwindow.com/skills/federal-civic-grants 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, envelope_object, capacity_basis, terrain_screenshots
**EMITS (output the human carries to the next skill):** proposed_positions, wizard_import_object
**NEXT SKILL(S):** prerequisite-gate, 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. Copy the SWII AI Prompt (the Constitution): Go to theshapingwindow.com/portfolio-literacy and copy or screenshot the SWII AI Prompt. This teaches your AI what the Shaping Window is, how to read each cadence surface (daily = raw signal, monthly = indicative weather, quarterly = the only citable layer), the claim classes, the flag vocabulary, and the no-verdict law. Same for every skill. This is Layer 1 — the Constitution.
2. Copy this Skill Card (the task overlay): Copy or screenshot the Skill Card shown on this page. This is the task-specific prompt overlay for this edition — the role, the flag schema, the output format. This is Layer 2 — the task card. It changes per skill; the Constitution does not.
3. Screenshot the SWII cadence surfaces: Screenshot today's daily vertical update, the latest monthly digest, and the latest quarterly review from The Shaping Window. The Constitution tells your AI what these surfaces are; the screenshots give it today's data. Your AI's training data is blind to today — these screenshots are its eyes. Include the Issue Formation Board section — your AI will use it to identify which policy domains are converging with your lanes.
4. Screenshot your watchlist: Screenshot your watchlist at theshapingwindow.com/watchlist. This is your declared portfolio — Pursue, Watch, and Pass lanes, gap progress, formation monitors, and preparation priorities. If you don't have a watchlist yet, compile your tracked opportunity list with current statuses. The watchlist IS the tracked list, already structured for the AI.
5. Upload everything to your AI: Upload the Constitution, the Skill Card, all cadence screenshots, and your watchlist screenshot to the AI of your choice (Claude, ChatGPT, Gemini, or a local model). The Constitution goes first — it sets the behavioral frame. The watchlist screenshot gives the AI your declared portfolio state.
6. Ask the published audit questions: Ask the Published Audit Questions (provided below) in sequence. Do not skip or paraphrase. Record the raw output for verification.

Published Audit Questions

1. For each tracked opportunity: has the award window exceeded one year with no recorded selection event? Flag as RESIDUAL-RISK, sub-flag: ROLLING >1YR.
2. For each tracked opportunity: has the last published status update exceeded one year? Flag as RESIDUAL-RISK, sub-flag: STALE-UPDATE >1YR.
3. For each tracked opportunity: does the published total program funding cover no more than one award at the stated ceiling? Flag as RESIDUAL-RISK, sub-flag: THIN-POOL.
4. For any opportunity not resolved by the above: return 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.