Recommendations
1 to acquire · 1 to dispose
| Ticker | Name | Close | Action | Action Price Where to act — a buy-limit on a pullback or a buy-stop above resistance, not the current price. Sanity-check vs Close: on a held name, an action price stranded above the close means the queued level was set when the stock was higher — stale, awaiting reprice. | Stop The risk-defined exit, set below the entry for a long (~1.2–1.8×ATR). A held long whose Stop sits at/above the Close is already below its stop — a stale box awaiting reprice. | 1wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. | 4wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. | 12wk Model estimate of the likely price at this horizon — a forward projection, not a guarantee, and separate from the trade's Action Price or Stop. Where the ML estimator is enabled these are per-ticker calibrated forecasts (~80% coverage band) that are refreshed periodically and can drift between refreshes; otherwise they're interpolated from the signal's swing target. Confirm against the settled close. | Rationale |
|---|---|---|---|---|---|---|---|---|---|
| XLE | Energy Select Sector SPDR | 65.31 | BUY — QUEUED @63.54 | 63.54 | 62.21 | 65.49 (+3.1%) | 66.46 (+4.6%) | 68.24 (+7.4%) | Energy is the only sector with both a trend and a catalyst right now. US strikes on five Iranian oil tankers pushed Brent through for the first time in two months and WTI to and XLE responded with a second consecutive STRONG BUY print, escalating to maximum conviction (100) and the board's best trend/momentum combination by a wide margin. We are buying it on a pullback rather than at market: the order rests 2.7% below the close, just above the anchored VWAP, on a properly sized stop, because the close sits within 1% of its 52-week high and the driver is a military-escalation premium that can unwind on a single de-escalation headline. Risk/reward at the limit is 2.2x, the best on the board and the only candidate clearing 1.5x. OPERATIONAL: repriced from the 09-08 card's limit per the action-price provenance rule -- that order never filled (session low after a 1.22% gap up) and is superseded, not carried. L1/SE-1 favoured: PullbackBuy_VWAP is the book's best live scorecard cell at bias +3 (n=15, hit_1w 0.636). SE-2 applies -- a +7.4% 12-week ETF view is a <=4-week tactical swing on the stop, not a position hold. SE-3/L5: calib_1w is -0.068 for a 13th week, so treat the 1wk estimate as directional only. Sized not the full model because the conservative branch governs until ADR-0019 reconciliation. Event gate: PPI 09-10 and CPI 09-11 both land inside the 1-week window and are two-sided for energy -- hot pass-through hurts the market multiple and helps the sector. Auto-withdraw if conviction drops below 65 or expires_on passes. · news |
| SKYY | First Trust Cloud Computing ETF | 158.14 | SELL ALL | 158.14 | 159.20 | 158.59 (+0.3%) | 159.48 (+0.8%) | 167.06 (+5.6%) | The stop broke, so we are out. SKYY closed at, below the stop this book wrote down a session ago and below the engine's own level, closing in the bottom quartile of its range. The signal has collapsed 37 points across four prints (STRONG BUY 85 to WATCH 48) and -- the decisive number -- the model's own four-week estimate of sits below the cost, meaning the forecast itself says this position does not get back to breakeven. The news agrees: debt-heavy cloud and AI-infrastructure names absorb rate shocks harder than broad tech, and SKYY fell roughly twice as much as QQQ on the 10-year's move to a one-year high. Oracle reports after the close on 09-10 carrying a ~$70bn capex guide and a planned ~$40bn raise; exiting at that morning's open puts us out hours before a binary print we have no edge on. OPERATIONAL: this exit honours the 09-08 pre-commitment verbatim ('a close below is the exit, no discretion') per L3. Universal L2 is NOT the basis -- Est_12W is +5.64%, so the stop-break-plus-negative-12wk test is not met; the basis is the written stop, the conviction collapse, and the below-cost 4wk view. CLAUDE.md S9 trim-discipline gates G1/G2/G3 do not apply: they protect uptrending names from divergence and valuation trims, and this is the stop-loss-break contrast case they explicitly carve out. CONTINGENT ON ADR-0019 RECONCILIATION: the JSON still shows. Confirm the 09-03 fill ('trade buy sectoretf SKYY 76 162.51' then 'trade sell sectoretf SKYY 76 158.14') or 'trade skip sectoretf SKYY'. If it never filled the card lapses and SKYY is simply declined as a new entry -- its printed Buy Limit @is +3.28% above the close, chase geometry. Books - / -2.69% on a. · news |
| XLK | Tech Select Sector SPDR | 187.87 | HOLD | — | 186.59 | n/a | n/a | n/a | Held on a decayed but still-valid signal. XLK slipped from STRONG BUY 85 to BUY 69 and closed exactly unchanged on a broadly red tape -- above its 20-, 50- and 200-day averages, still above the conviction floor, and still the cleanest large-cap tech proxy in the book. Not re-issued as an acquire because it already carries an unreconciled 09-04 card for @; buying it again would commit the same dollars twice. OPERATIONAL: stop raised -> (live engine level), though note it is only 0.50 ATR / 0.68% below the close -- inside one session's noise, the FailedBreakdown family's structural stop defect. Disposition required: 'trade buy sectoretf XLK 26 188.64' or 'trade skip sectoretf XLK'. |
| QQQ | Invesco QQQ (Nasdaq-100) | 716.31 | HOLD | — | 715.15 | n/a | n/a | n/a | Held, but this is the next name at risk. QQQ dropped below the conviction floor for the first time in a week (BUY 69 to WATCH 63) and closed just -- 0.16% -- above its stop, so a single soft session takes it out. It still carries the best forward view in the book at +8.6% over twelve weeks, which is why it is held rather than cut on a conviction reading alone. OPERATIONAL: stop HELD at; the live engine prints and we never lower a stop. Not re-issued -- unreconciled 09-04 card for @. Stop is 0.50 ATR, the same sub-ATR defect as XLK. Disposition required: 'trade buy sectoretf QQQ 7 720.97' or 'trade skip sectoretf QQQ'. |
| AIQ | Global X AI & Tech ETF | 64.11 | HOLD | — | 63.90 | n/a | n/a | n/a | Held on the stop, one session from an exit. AIQ printed its first NO TRADE of the run ('Consensus conflict + low conviction') after collapsing from STRONG BUY 90 four sessions ago, and closed -- just, or 0.33%, above its stop. One more soft session breaks it. OPERATIONAL: stop held at (no live stop prints on a NO TRADE row). PRE-COMMITMENT for the next EOD, on exactly the terms MAGS was held to: a second consecutive NO TRADE print, or a close below, is an exit. Disposition required: 'trade buy sectoretf AIQ 136 64.51' or 'trade skip sectoretf AIQ'. WARNING: AIQ is listed TWICE in input/sectoretfportfolio.json (rows 9 and 11) -- de-dupe before recording the fill or exposure will double-count. |
| — | Destiny Tech100 Inc | — | NO ACTION | — | — | n/a | n/a | n/a | Blocked, and the day proved the reason right. DXYZ fell 4.79% on precisely the date the event calendar flagged: the SpaceX Day-90 underwriter lock-up expiry, releasing up to 319 million shares of the fund's largest holding. It is a closed-end fund trading at a premium to net asset value, running a live $1bn at-the-market share offering, that failed the quality screen outright -- so it cannot be a new entry no matter how the chart looks. OPERATIONAL: hard quality gate (Quality_Pass=False, OVERVALUED_VS_RI, MoS_FV -0.78 -> val_adj -4); also below the 65 floor on its own at adj 63. Gate applied with the caveat that the valuation is 90 days stale and marked at against today's -- the reason stands independently of the mark. Only priced row in an otherwise all-NA_ETF book. |
| — | SPY | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | DIA | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | IWM | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | GLD | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | XLF | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | XLV | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | XBI | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | IBB | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | XLI | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | XLP | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | XLY | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | SOXX | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | SMH | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | UFO | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
| — | QTUM | — | NO ACTION | — | — | n/a | n/a | n/a | Below the conviction floor or non-actionable on the anchor snapshot; long-only book, so AVOID prints carry no action. |
Outcome & track record
Accuracy at the time of this record.
47 Graded decisions Past recommendations old enough to score against what actually happened (target hit / stopped out / closed). This is the evidence base — the bigger the number, the more history behind the calls. Click to inspect every one. See the decisions →
-0.068 1-week calibration How much of the eventual 4-week move typically shows up in the first week (0 = almost none, 1 = most of it). Use it to read the 1-week estimates: a low number means prices drift toward the target slowly, so don't over-read a soft week-1.
50 Published records How many dated end-of-day verdicts exist for this book — the length of the public track record you can browse in the Archive below.