You asked
How do I take my turn?
Answered counted as answeredAt the end of each turn, perform the following steps: 1. Players discard all Power Cards played during that turn into their personal discard piles [1]. 2. All Damage done during the turn is removed; if any pieces were turned to note partial Damage, they are turned back [1]. 3. All Elements are cleared (they do not persist from turn to turn) [1][2]. 4. Remove any Reminder Tokens used to mark lands for temporary effects [1][3].
Strategy guides → — community tips, kept separate from rulings
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:12b think:false 4eb23ef187e2
- timings
- search 206 ms · ask 8740 ms · total 8956 ms
- single-flight (PR-5)
- queued 0 ms · generation 8956 ms
- retrieval refs (raw)
- [{"page": 6, "score": 0.032522, "snippet": "Each player takes all Spirit Presence and Single-Turn Effect Markers of one color, then chooses a Spirit by taking a Spirit Panel and its four Unique Power Cards, which is their starting hand. New players should choose a low-complexity Spirit and take its Power Progression Card, as described on page", "headingPath": "PLAYER SETUP", "sharpsignalDocId": 58}, {"page": 20, "score": 0.03055, "snippet": "You suddenly realize that for the past 4 turns you've been using a Power Card on lands it can't actually target. What to do? The answer is: don't sweat it. Especially on your first play or two, you'll likely make minor mistakes here and there. They're unlikely to break anything: the game will just b", "headingPath": "WHOOPS!", "sharpsignalDocId": 58}, {"page": 14, "score": 0.029116, "snippet": "Spirit Name Art: An image of this Spirit. Backstory: The story and history of the Spirit. Setup: Inital Presence placement and any special instructions. Play Style/Complexity: A brief description of the Spirit's strategy and comparison of its strengths and weaknesses, as well as a summary of Powers.", "headingPath": "ANATOMY OF A SPIRIT PANEL", "sharpsignalDocId": 58}, {"page": 20, "score": 0.028577, "snippet": "As you play Power Cards, put the required Energy on top of them. This will help you remember to pay for them. When you resolve a Power Card, you can push it forward or turn it sideways to note that it has been used. Don't discard it until end of turn, because you may be making use of its Elements fo", "headingPath": "STREAMLINING GAMEPLAY", "sharpsignalDocId": 58}, {"page": 21, "score": 0.027237, "snippet": "Blight spreads quickly once it starts cascading. Try to clean up lands before a second Blight is added. If you are having trouble finding good targets for your Powers, that can mean one of two things: That you are winning! If you have the Invaders on the ropes, focus on achieving victory! That your ", "headingPath": "MISCELLANEOUS", "sharpsignalDocId": 58}, {"page": 15, "score": 0.026916, "snippet": "Towns take 2 Damage to destroy. The model has 2 buildings to remind you of this. This Town has taken 1 Damage (1 more will destroy it). It has been laid on its side. When a piece has taken Damage equal to or exceeding its Health, it is destroyed. Return it to the supply, and earn 1 Fear for a Town o", "headingPath": "TOWNS: 2 Health", "sharpsignalDocId": 58}, {"page": 16, "score": 0.022903, "snippet": "Energy Cost (Power Cards only) Name Elements Gained (Power Cards only): There are eight Elements: Sun, Moon, Fire, Air, Water, Earth, Plant, and Animal. When you play a Power Card, you gain the Elements shown. Some Powers have extra effects if you have gained specific Elements (see #8 on the next pa", "headingPath": "ANATOMY OF POWERS", "sharpsignalDocId": 58}, {"page": 30, "score": 0.02216, "snippet": "[p. 18] Defend: Guard a land against the Invaders. Reduces the Damage done by the Invaders to the land and Dahan by the specified amount. [p. 18] Effect: The text instructions of a card or other game element. Element: Affinity with an aspect of nature, usually granted by a Power Card. Lets you use t", "headingPath": "GLOSSARY/INDEX", "sharpsignalDocId": 58}]
- citations (raw)
- [{"page": 10, "quote": null, "headingPath": "TIME PASSES", "sharpsignalDocId": 58}, {"page": 14, "quote": null, "headingPath": "ELEMENTAL THRESHOLDS", "sharpsignalDocId": 58}, {"page": 17, "quote": null, "headingPath": "SINGLE-TURN EFFECTS", "sharpsignalDocId": 58}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base-rulebook boost: not recorded (this ruling predates it); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base-rulebook boost: not recorded (this ruling predates it)
- answered-before recall
-
this ruling was answered, so past rulings were not offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- debug row retained until
- Oct 22, 2026 01:16
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.
per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| fused rank | document | heading | page | fused RRF score | snippet chars |
|---|---|---|---|---|---|
| #1 | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | PLAYER SETUP | p.6 | 0.032522 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #2 | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | WHOOPS! | p.20 | 0.03055 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #3 | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | ANATOMY OF A SPIRIT PANEL | p.14 | 0.029116 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #4 | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | STREAMLINING GAMEPLAY | p.20 | 0.028577 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #5 | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | MISCELLANEOUS | p.21 | 0.027237 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #6 | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | TOWNS: 2 Health | p.15 | 0.026916 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #7 | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | ANATOMY OF POWERS | p.16 | 0.022903 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #8 | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | GLOSSARY/INDEX | p.30 | 0.02216 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
chosen chunks — what the answer actually cited
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | TIME PASSES | p.10 | no quote on the wire |
| [2] | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | ELEMENTAL THRESHOLDS | p.14 | no quote on the wire |
| [3] | RULEBOOK Spirit Island — Rulebook (corpus doc 58) | SINGLE-TURN EFFECTS | p.17 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 206 ms · first delta n/a · total 8956 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 206 ms · ask 8740 ms · gateway work 8956 ms · total 8956 ms
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 40s ago)
- stream path
- not recorded — this ruling predates the stream-path column (V41)
- watchdog
- first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
- num_ctx · think posture
- both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.
disposition
- outcome
- ANSWERED — Answered
- abstain rationale (n/a — this ruling answered)
- answered — no abstain rationale applies
setup-shape — why the checklist band did or didn't render
- decision
- NOT_SETUP_SHAPED — no setup-shape pattern matched this question
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 7), so "no registered errata card matched" above could never have matched one
Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.