[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BGYNMA3PTPFS8KQWXPWY7T":3,"skill-same:01M7BGYNMA3PTPFS8KQWXPWY7T":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7BGYNMA3PTPFS8KQWXPWY7T","soft-predict-future",null,"Activate this skill for ANY future-oriented question. Triggers include: \"Will [X]?\", \"Who will win [X]?\", \"What happens to [X]?\", \"Can [X] succeed?\", \"What's the future of X?\", foresight analysis, scenario planning, STEEEP analysis, futures cone, prediction requests, or any question about a future outcome. Year is NOT required — the engine infers the horizon. Also activate when the user says \"predict\", \"forecast\", \"what are the odds\", \"scenario analysis\", or asks about competitive races, technology adoption, geopolitical shifts, or market dominance. REQUIRES web search to be enabled — if web search is unavailable, tell the user before proceeding.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-buildwithclaude\u002Fplugins\u002Fforesight-intelligence\u002Fskills\u002Fsoft-predict-future\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: soft-predict-future\ndescription: >\n  Activate this skill for ANY future-oriented question. Triggers include: \"Will [X]?\",\n  \"Who will win [X]?\", \"What happens to [X]?\", \"Can [X] succeed?\", \"What's the future of X?\",\n  foresight analysis, scenario planning, STEEEP analysis, futures cone, prediction requests,\n  or any question about a future outcome. Year is NOT required — the engine infers the horizon.\n  Also activate when the user says \"predict\", \"forecast\", \"what are the odds\", \"scenario analysis\",\n  or asks about competitive races, technology adoption, geopolitical shifts, or market dominance.\n  REQUIRES web search to be enabled — if web search is unavailable, tell the user before proceeding.\n---\n\n# Soft Predict Future — Foresight Engine\n\nActivate when the user asks any future-oriented question — \"Will [X]?\", \"Who will win [X]?\", \"What happens to [X]?\", \"Can [X] succeed?\", or any question about a future outcome. **Year is NOT required.** Also activate on: foresight analysis, scenario analysis, STEEEP, futures cone, or any prediction request.\n\n---\n\n## Try Asking\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nTRY ASKING  (year optional — engine infers the horizon)\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n■ Who will win — Google or Perplexity?\n■ Will OpenAI or Anthropic dominate the AI race?\n■ Will India become the global AI leader?\n■ Will crypto replace banks?\n■ Will remote work become permanent?\n■ Will EVs dominate Indian cities by 2032?\n■ Will UPI become Southeast Asia's default payment rail by 2028?\n■ Will Europe lead the green energy transition by 2035?\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n```\n\n> **Soft Predict Future** uses Claude's native reasoning + web search. Outputs are structurally correct and fast. For deterministic, auditable scoring say: **\"Run hard predict future: [your question]\"**\n\n---\n\n## The 9-Step Pipeline\n\nExecute ALL steps in order. Never skip. Never combine. Show your work at each step.\n\n---\n\n### Step 1 — Validate Input\n\nApply exactly 5 binary rules. If ANY rule fails, stop and explain why. Do not proceed.\n\n**Rule 1 — Entity Reality:** Does the entity actually exist in the real world? Fail if fictional, hypothetical, or unnamed.\n\n**Rule 2 — System Existence:** Is the domain observable and researchable? Fail if purely philosophical or metaphysical.\n\n**Rule 3 — Time Horizon:** Is the outcome observable within a 2–30 year window? A specific year is NOT required. If no year is given, infer the most reasonable horizon from the question's nature:\n- Competitive race \u002F market dominance questions → 3–10 years (Strategic)\n- Technology adoption questions → 5–15 years (Strategic)\n- Geopolitical \u002F societal shift questions → 10–20 years (Civilizational)\n- Company survival \u002F near-term outcome → 2–5 years (Operational\u002FStrategic)\n\nFail ONLY if the implied timescale is geological, post-human, or clearly beyond 30 years.\n\nAfter applying Rule 3, state the inferred horizon (e.g. \"2026–2033\" or \"2028–2038\").\n\n**Rule 4 — Signal Availability:** Could real-world evidence plausibly exist? Fail if classified, purely speculative, or unpublished.\n\n**Rule 5 — Minimum Specificity:** Is the question specific enough to produce distinct scenario outcomes? Fail if trivially true for any answer.\n\nOutput:\n```\nVALIDATION\nRule 1 Entity Reality:      PASS \u002F FAIL — [reason]\nRule 2 System Existence:    PASS \u002F FAIL — [reason]\nRule 3 Time Horizon:        PASS \u002F FAIL — [reason] | Inferred horizon: [YYYY–YYYY]\nRule 4 Signal Availability: PASS \u002F FAIL — [reason]\nRule 5 Specificity:         PASS \u002F FAIL — [reason]\nResult: PROCEED \u002F STOP\n```\n\n---\n\n### Step 2 — Collect Signals\n\nRun exactly 6 web searches. Collect a minimum of 18 signals total. Do not proceed with fewer than 18.\n\n**Search 1:** Current state — `\"[topic] current status [year]\"`\n**Search 2:** Growth indicators — `\"[topic] growth data market size [year]\"`\n**Search 3:** Barriers and headwinds — `\"[topic] challenges barriers risks\"`\n**Search 4:** Policy and regulation — `\"[topic] government policy regulation\"`\n**Search 5:** Technology or infrastructure enablers — `\"[topic] technology infrastructure investment\"`\n**Search 6:** Historical precedent — `\"[topic] historical analogue similar transition\"`\n\nFor each signal, classify all 6 attributes:\n\n| Attribute | Values |\n|---|---|\n| direction | supporting \u002F opposing \u002F wildcard \u002F neutral |\n| steeep_category | Social \u002F Technological \u002F Economic \u002F Environmental \u002F Ethical \u002F Political |\n| temporal_layer | Operational (0–3yr) \u002F Strategic (3–10yr) \u002F Civilizational (10+yr) |\n| source_type | primary \u002F secondary \u002F opinion |\n| recency_days | integer |\n| has_evidence | true \u002F false (contains a number, date, or measurable fact) |\n\nPresent signals in a table with all 6 columns filled for every row.\n\n---\n\n### Step 3 — Score Signals\n\nScore every signal individually using this formula:\n\n```\nscore = recency_weight × reliability_weight × type_weight × evidence_multiplier\n```\n\nCap at 1.0. Round to 2 decimal places.\n\n**Recency weights:**\n- 0–90 days: 1.00 · 91–365 days: 0.80 · 1–3 years: 0.60 · 3+ years: 0.40 · unknown: 0.50\n\n**Reliability weights:**\n- Primary (government\u002Fofficial): 1.00\n- Established news (Reuters, Bloomberg, FT, ET): 0.90\n- Industry report (McKinsey, Gartner, NASSCOM): 0.85\n- Analyst commentary: 0.70 · Opinion\u002Fblog\u002Fsocial: 0.50 · Unknown: 0.40\n\n**Type weights:**\n- Supporting: 1.00 · Opposing: 1.00 · Neutral: 0.60 · Wildcard: 1.30\n\n**Evidence multiplier:**\n- DATA \u002F STATISTIC: × 1.20 · EVENT \u002F INCIDENT: × 1.00 · ANALYSIS \u002F OPINION: × 0.70\n\nApply regional multiplier after base score:\n```\nfinal_score = min(1.0, base_score × regional_multiplier[steeep][temporal])\n```\n\nShow scoring table: Signal | recency_w | reliability_w | type_w | evidence_mult | base_score | regional_mult | final_score\n\n---\n\n### Step 4 — Extract Structural Drivers\n\nA **driver** is the deep structural force that explains WHY a cluster of signals exists. Signals are observable. Drivers are causal.\n\nAfter scoring, group signals by STEEEP category. For each cluster of 3+ signals in the same category, identify the underlying driver.\n\nExtract exactly **3 top drivers**, ranked by the sum of final_scores of the signals they explain.\n\nFor each driver state:\n- **Name:** 3–5 word label (e.g. \"India DPI Infrastructure Advantage\")\n- **Force:** One sentence — the structural reality this driver represents\n- **Signals it explains:** List the signal IDs it accounts for\n- **Temporal reach:** Operational \u002F Strategic \u002F Civilizational\n- **Stability:** LOCKED (unlikely to change in 10yr) \u002F SHIFTING (could change in 3–5yr) \u002F FRAGILE (could reverse in 1–2yr)\n\nOutput:\n```\nSTRUCTURAL DRIVERS\nD1 [Name] — [Force]\n   Explains: [signal list] | Temporal: [layer] | Stability: [tier]\n\nD2 [Name] — [Force]\n   Explains: [signal list] | Temporal: [layer] | Stability: [tier]\n\nD3 [Name] — [Force]\n   Explains: [signal list] | Temporal: [layer] | Stability: [tier]\n```\n\nDrivers feed directly into scenario writing in Step 8. Each scenario must be traceable to at least one driver.\n\n---\n\n### Step 5 — Build 6×3 STEEEP Matrix\n\nPopulate all 18 cells. Each cell value = average final_score of all signals mapped to that STEEEP × Temporal combination. Empty cells = 0.\n\n|  | Operational (0–3yr) | Strategic (3–10yr) | Civilizational (10+yr) |\n|---|---|---|---|\n| **Social** | | | |\n| **Technological** | | | |\n| **Economic** | | | |\n| **Environmental** | | | |\n| **Ethical** | | | |\n| **Political** | | | |\n\nApply regional multipliers to each cell. Then identify:\n- **Hot zones:** cells with score > 0.50\n- **Gap zones:** cells with score = 0.00\n- **Dominant zone:** single highest-scoring cell\n\n---\n\n### Step 6 — Cross-Impact Analysis\n\nSignals are scored independently in Step 3, but structural forces interact. This step identifies amplification effects across STEEEP categories.\n\n**Rule:** If 2 or more hot zones exist in the SAME temporal layer, a cross-impact convergence exists. Convergence means the probable outcome is structurally reinforced from multiple directions simultaneously.\n\nFor each temporal layer (Operational \u002F Strategic \u002F Civilizational):\n1. Count hot zones (score > 0.50)\n2. If count ≥ 2: flag as **CONVERGENCE** — state which categories are reinforcing each other and why\n3. If count = 1: flag as **ISOLATED** — single-category signal, more fragile\n4. If count = 0: flag as **BLIND LAYER** — no strong evidence in this time horizon\n\nAlso identify any **opposing cross-impacts**: where a hot zone in one STEEEP category directly contradicts or slows a hot zone in another (e.g. Technological\u002FStrategic hot but Political\u002FStrategic opposing). Flag these as **FRICTION POINTS**.\n\nOutput:\n```\nCROSS-IMPACT\nOperational:    [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nStrategic:      [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nCivilizational: [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\n\nFriction points: [list any STEEEP pairs in conflict, or \"None detected\"]\nConvergence bonus: [+X% to probable_pct if Strategic convergence exists]\n```\n\nApply convergence bonus: if Strategic layer has CONVERGENCE, add 5% to probable_pct before normalization in Step 7.\n\n---\n\n### Step 7 — Find 3 Historical Analogues\n\nIdentify exactly 3 real historical cases that parallel the question's trajectory.\n\nFor each:\n1. **Name:** Common name of the transition\n2. **Similarity (%):** Estimated % structural similarity (0–100)\n3. **Tipping event:** Single event or policy that caused acceleration\n4. **Equivalent today:** YES \u002F NO \u002F PARTIAL\n5. **Which driver it validates:** Match to D1, D2, or D3 from Step 4\n\nPrefer analogues with similarity ≥ 60%. If none exceed 60%, note as a confidence penalty.\n\n---\n\n### Step 8 — Compute Probabilities + Confidence\n\n#### Predictions — Independent Confidence Scores\n\nEach future type is scored independently (0–100). They do NOT sum to 100%.\nFutures cone methodology: a scenario can be 80% Probable AND 60% Plausible simultaneously.\n\n```\nR_probable  = (supporting signals with score > 0.70) × 3\n            + (best analogue similarity \u002F 100) × 4\n            + (hot zone count) × 2\n            + convergence_bonus (5 if Strategic CONVERGENCE, else 0)\n\nR_plausible = (supporting signals with score 0.40–0.70) × 2\n            + (second analogue similarity \u002F 100) × 3\n\nR_possible  = (wildcard signals) × 2\n            + (opposing signals with score > 0.60) × 2\n            + (gap zones \u002F 18) × 3\n```\n\nConvert to independent scores (exponential curve, not normalization):\n```\nprobable_score  = min(100, round((1 - e^(-R_probable  \u002F 18)) × 100))\nplausible_score = min(100, round((1 - e^(-R_plausible \u002F 9))  × 100))\npossible_score  = min(100, round((1 - e^(-R_possible  \u002F 5))  × 100))\n```\n\n#### Confidence\n\n```\nsignal_count_score = min(100, total_signals \u002F 25 × 100) × 0.30\nsignal_diversity   = (unique STEEEP categories covered \u002F 6 × 100) × 0.30\nrecency_score      = (signals with recency_days ≤ 90 \u002F total) × 100 × 0.20\nevidence_score     = (signals with has_evidence=true \u002F total) × 100 × 0.20\n\nconfidence = round(signal_count_score + signal_diversity + recency_score + evidence_score)\n```\n\n---\n\n### Step 9 — Write Scenarios + Assemble Report\n\n#### Scenario Rules\n\n**PROBABLE, PLAUSIBLE, POSSIBLE** — each must:\n- Be traceable to at least one structural driver (cite D1\u002FD2\u002FD3)\n- Have no narrative overlap with the others\n- Include PROOF with a number or date\n- Write IF and BUT in one sentence each — no hedging (\"might\", \"could\")\n\n**PREFERABLE — IFTF Backcasting Structure**\n\nDo not write PREFERABLE as a probability-weighted outcome. Write it as a designed future, then backcast to today.\n\nFormat:\n```\n■ PREFERABLE — [Short title]\n[2–3 sentences: describe the desired state as already achieved]\n\nBACKCAST\nCivilizational (10+yr): [What must be structurally true by the far horizon]\nStrategic (3–10yr):     [What must be built or decided in the medium horizon]\nOperational (0–3yr):    [What must happen NOW to set the trajectory]\n\nLEVERAGE: [The single highest-leverage action available today — specific, not generic]\nDRIVER:   [Which structural driver (D1\u002FD2\u002FD3) this path depends on most]\n```\n\n#### Decision Guidance (deterministic logic)\n\n```\nIF probable_score > 60:\n    stance = \"Align with probable scenario trajectory\"\n    low_regret = \"Invest in capability building in the dominant hot zone\"\n\nELIF plausible_score > 50:\n    stance = \"Hedge between probable and plausible scenarios\"\n    low_regret = \"Choose reversible commitments that work in both\"\n\nELIF possible_score > 40:\n    stance = \"Maintain optionality — signal environment is ambiguous\"\n    low_regret = \"Invest in monitoring and early-warning indicators\"\n\nELSE:\n    stance = \"Defer commitment — insufficient signal clarity\"\n    low_regret = \"Reduce uncertainty before acting\"\n```\n\nConfidence qualifier:\n- ≥ 70: prefix \"High conviction —\"\n- \u003C 40: prefix \"Low conviction —\" and add \"Expand signal collection before acting\"\n\nRisk trigger: the opposing signal with the highest final_score.\n\n#### Canonical Output Template\n\n**MANDATORY: Output ALL sections below, every single run, no exceptions. Never skip a section. Never produce a partial report.**\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nSOFT PREDICT FUTURE  ·  FORESIGHT ENGINE\n[Query]\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nPREDICTIONS\n■ Probable  [[X]\u002F100] [████████████░░░░░░░░] — [one sentence, no hedging]\n■ Plausible [[X]\u002F100] [████████░░░░░░░░░░░░] — [one sentence, no hedging]\n■ Possible  [[X]\u002F100] [████░░░░░░░░░░░░░░░░] — [one sentence, no hedging]\n■ Preferable          [stakeholder analysis below]\n\nConfidence: [X]\u002F100  |  Signals: [N]  |  Horizon: [YYYY–YYYY]  |  [YYYY-MM-DD]\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nSIGNAL PULSE\n— How many pieces of real-world evidence support, oppose, or complicate this question\nSupporting [N] [████████████░░░░░░░░]  Opposing [N] [████░░░░░░░░░░░░░░░░]  Wild [N]\nNet: [SUPPORTING LEADS \u002F OPPOSING LEADS \u002F NEUTRAL]\nHot zone: [The single STEEEP category with strongest evidence]\nGap: [STEEEP categories with no signals, or \"None — full coverage\"]\n\nSTRUCTURAL DRIVERS\n— The 3 deep causal forces (not events) explaining WHY the signals exist. Stability = likelihood of change.\nD1 [Name] — [Force] ([LOCKED \u002F SHIFTING \u002F FRAGILE])\nD2 [Name] — [Force] ([LOCKED \u002F SHIFTING \u002F FRAGILE])\nD3 [Name] — [Force] ([LOCKED \u002F SHIFTING \u002F FRAGILE])\n\nCROSS-IMPACT\n— Whether multiple STEEEP domains reinforce or contradict each other in the same time layer\nOperational:    [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nStrategic:      [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nCivilizational: [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nFriction:       [Conflicting domain pairs, or \"None detected\"]\n\nHISTORICAL MATCH\n— Real past transition most structurally similar to this question. Higher % = stronger precedent.\n[Best analogue] ([similarity]% similar)\nTipped by: [The specific event or policy that caused the shift]\nEquivalent now: [EXISTS \u002F PARTIAL \u002F ABSENT]\nValidates: [D1 \u002F D2 \u002F D3]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n■ PROBABLE [[X]%] — [Title]\n— The most evidence-backed outcome given current signal strength\n[2–3 sentence narrative. No hedging.]\nPROOF: [Fact with number or date]\nIF:    [The condition that activates this scenario]\nBUT:   [The constraint or bottleneck that could slow it]\nDRIVER: D[n]\n\n■ PLAUSIBLE [[X]%] — [Title]\n— A realistic alternative if moderate signals strengthen or dominant ones weaken\n[2–3 sentence narrative]\nPROOF: [Fact with number or date]\nIF:    [Activation condition]\nBUT:   [Constraint]\nDRIVER: D[n]\n\n■ POSSIBLE [[X]%] — [Title]\n— A lower-probability outcome driven by wildcards or high-scoring opposing signals\n[2–3 sentence narrative]\nPROOF: [Fact with number or date]\nIF:    [Activation condition]\nBUT:   [Constraint]\nDRIVER: D[n]\n\n■ PREFERABLE — [Title]\n— Not a prediction. A designed future: what the best achievable outcome looks like, traced back to today.\n[2–3 sentences: desired state as already achieved. No hedging.]\nBACKCAST\n  Civilizational: [What must be structurally true by the far horizon]\n  Strategic:      [What must be built or decided in the medium term]\n  Operational:    [What must begin NOW to set the trajectory]\nLEVERAGE: [Single highest-leverage action today — specific actor, specific action]\nDRIVER: D[n]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nPREFERABLE FUTURES  ·  Per major stakeholder\n— For each major player in the query, state the conditions required for their preferred outcome\n\n[Player A]:\n  Wins IF  → [specific condition that must be created or occur]\n  BUT ONLY → [binding constraint that must also be satisfied]\n  ONLY THEN → [the outcome that becomes possible]\n\n[Player B]:\n  Wins IF  → [specific condition]\n  BUT ONLY → [binding constraint]\n  ONLY THEN → [outcome]\n\n[Users\u002FSociety — always include]:\n  Wins IF  → [condition for best collective outcome]\n  BUT ONLY → [constraint]\n  ONLY THEN → [outcome]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nTHE ONE THING\n— The single variable whose presence or absence determines which scenario actually unfolds\n[One sentence naming the deciding variable]\nINCIDENT: [Real past event showing this variable's power]\nWATCH:    [Leading indicator — a milestone, metric, or policy action to monitor]\nIF YES → [What accelerates]\nIF NO  → [What stalls]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nDECISION GUIDANCE\nRecommended stance: [From deterministic probability logic]\nLow-regret move:    [Action that pays off in multiple scenarios simultaneously]\nRisk trigger:       [Highest-scored opposing signal — the one that could invalidate Probable]\n\n[REGIONAL LENS — [REGION]]\nTop multipliers: [STEEEP\u002Ftemporal (Xx)]  [STEEEP\u002Ftemporal (Xx)]\nKey local variable: [One sentence on the dominant local structural factor]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nMETHODOLOGY KEY\nSignal score (0–1)     Recency × source reliability × signal type × evidence strength — higher = fresher, better-sourced, stronger evidence\nConfidence (0–100)     Signal density (0–40) + evidence balance (0–30) + historical grounding (0–30) − blind spot penalty (0–15)\nPredictions            PROBABLE \u002F PLAUSIBLE \u002F POSSIBLE are independent scores (0–100 each, do NOT sum to 100)\n                       Futures cone: a scenario can score high on multiple types simultaneously\nSTEEEP matrix          6 domains × 3 time horizons — ★ hot (>1.0) ● warm (>0.5) ✗ blind spot (0)\nHistorical similarity   Structural pattern match to real past transitions — 60%+ is reliable precedent; below 40% is weak grounding\nConvergence bonus      +5 added to Probable score when 2+ STEEEP domains reinforce each other in the Strategic layer\nStability tiers        LOCKED = unlikely to change in 10yr | SHIFTING = could change in 3–5yr | FRAGILE = could reverse in 1–2yr\nPreferable futures     Per stakeholder: Wins IF [condition] BUT ONLY [constraint] ONLY THEN [outcome]\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n---\n\n## Visual Output (claude.ai with Artifacts)\n\nIf running on claude.ai and Artifacts are enabled, after the text report generate an HTML Artifact:\n\n```html\n\u003C!-- Render a visual foresight report with:\n  1. Predictions bar chart — horizontal bars for Probable\u002FPlausible\u002FPossible scores\n  2. STEEEP matrix — 6×3 color-coded table (darker green = hotter cell, red = blind spot)\n  3. Futures cone — SVG diagram showing 4 scenario bands expanding from present to horizon\n  4. Stakeholder preferable cards — one card per player with Wins IF \u002F BUT ONLY \u002F ONLY THEN\n  Use inline CSS only. No external dependencies. Dark background (#0f0f0f), accent color #00d4aa.\n-->\n```\n\n---\n\n## Regional Multiplier Tables\n\nApply in Step 3 and Step 5.\n\n### India\n| | Operational | Strategic | Civilizational |\n|---|---|---|---|\n| **Social** | 1.10 | 1.30 | 1.20 |\n| **Technological** | 1.40 | 1.30 | 1.10 |\n| **Economic** | 1.20 | 1.25 | 1.15 |\n| **Environmental** | 0.90 | 1.00 | 1.10 |\n| **Ethical** | 0.95 | 1.00 | 1.05 |\n| **Political** | 0.85 | 0.90 | 1.00 |\n\n**India note:** UPI\u002FDPI gives asymmetric advantage in Technological\u002FOperational. Political\u002FOperational discounted by regulatory fragmentation across states.\n\n### USA\n| | Operational | Strategic | Civilizational |\n|---|---|---|---|\n| **Social** | 1.00 | 1.10 | 1.05 |\n| **Technological** | 1.20 | 1.40 | 1.20 |\n| **Economic** | 1.10 | 1.30 | 1.10 |\n| **Environmental** | 0.95 | 1.00 | 1.05 |\n| **Ethical** | 1.05 | 1.10 | 1.10 |\n| **Political** | 0.90 | 0.95 | 1.00 |\n\n**USA note:** Deep capital markets amplify Technological\u002FStrategic. Political\u002FOperational discounted by legislative gridlock.\n\n### Europe\n| | Operational | Strategic | Civilizational |\n|---|---|---|---|\n| **Social** | 1.00 | 1.05 | 1.10 |\n| **Technological** | 1.00 | 1.10 | 1.05 |\n| **Economic** | 0.95 | 0.90 | 0.90 |\n| **Environmental** | 1.20 | 1.40 | 1.30 |\n| **Ethical** | 1.10 | 1.20 | 1.20 |\n| **Political** | 1.05 | 1.10 | 1.10 |\n\n**Europe note:** Regulatory leadership (GDPR, EU AI Act, Green Deal) amplifies Environmental\u002FStrategic. Economic\u002FCivilizational discounted by demographic headwinds.\n\n### China\n| | Operational | Strategic | Civilizational |\n|---|---|---|---|\n| **Social** | 1.00 | 1.10 | 1.05 |\n| **Technological** | 1.20 | 1.50 | 1.30 |\n| **Economic** | 1.10 | 1.20 | 1.10 |\n| **Environmental** | 0.90 | 1.00 | 1.05 |\n| **Ethical** | 0.70 | 0.75 | 0.80 |\n| **Political** | 1.10 | 1.15 | 1.00 |\n\n**China note:** State-directed capital amplifies Technological\u002FStrategic strongly. Ethical\u002FOperational discounted by limited transparency.\n\n### Global (default)\nAll multipliers = 1.0. Apply when no region is detectable.\n","# Soft Predict Future — Foresight Engine\n\nActivate when the user asks any future-oriented question — \"Will [X]?\", \"Who will win [X]?\", \"What happens to [X]?\", \"Can [X] succeed?\", or any question about a future outcome. **Year is NOT required.** Also activate on: foresight analysis, scenario analysis, STEEEP, futures cone, or any prediction request.\n\n---\n\n## Try Asking\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nTRY ASKING  (year optional — engine infers the horizon)\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n■ Who will win — Google or Perplexity?\n■ Will OpenAI or Anthropic dominate the AI race?\n■ Will India become the global AI leader?\n■ Will crypto replace banks?\n■ Will remote work become permanent?\n■ Will EVs dominate Indian cities by 2032?\n■ Will UPI become Southeast Asia's default payment rail by 2028?\n■ Will Europe lead the green energy transition by 2035?\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n```\n\n> **Soft Predict Future** uses Claude's native reasoning + web search. Outputs are structurally correct and fast. For deterministic, auditable scoring say: **\"Run hard predict future: [your question]\"**\n\n---\n\n## The 9-Step Pipeline\n\nExecute ALL steps in order. Never skip. Never combine. Show your work at each step.\n\n---\n\n### Step 1 — Validate Input\n\nApply exactly 5 binary rules. If ANY rule fails, stop and explain why. Do not proceed.\n\n**Rule 1 — Entity Reality:** Does the entity actually exist in the real world? Fail if fictional, hypothetical, or unnamed.\n\n**Rule 2 — System Existence:** Is the domain observable and researchable? Fail if purely philosophical or metaphysical.\n\n**Rule 3 — Time Horizon:** Is the outcome observable within a 2–30 year window? A specific year is NOT required. If no year is given, infer the most reasonable horizon from the question's nature:\n- Competitive race \u002F market dominance questions → 3–10 years (Strategic)\n- Technology adoption questions → 5–15 years (Strategic)\n- Geopolitical \u002F societal shift questions → 10–20 years (Civilizational)\n- Company survival \u002F near-term outcome → 2–5 years (Operational\u002FStrategic)\n\nFail ONLY if the implied timescale is geological, post-human, or clearly beyond 30 years.\n\nAfter applying Rule 3, state the inferred horizon (e.g. \"2026–2033\" or \"2028–2038\").\n\n**Rule 4 — Signal Availability:** Could real-world evidence plausibly exist? Fail if classified, purely speculative, or unpublished.\n\n**Rule 5 — Minimum Specificity:** Is the question specific enough to produce distinct scenario outcomes? Fail if trivially true for any answer.\n\nOutput:\n```\nVALIDATION\nRule 1 Entity Reality:      PASS \u002F FAIL — [reason]\nRule 2 System Existence:    PASS \u002F FAIL — [reason]\nRule 3 Time Horizon:        PASS \u002F FAIL — [reason] | Inferred horizon: [YYYY–YYYY]\nRule 4 Signal Availability: PASS \u002F FAIL — [reason]\nRule 5 Specificity:         PASS \u002F FAIL — [reason]\nResult: PROCEED \u002F STOP\n```\n\n---\n\n### Step 2 — Collect Signals\n\nRun exactly 6 web searches. Collect a minimum of 18 signals total. Do not proceed with fewer than 18.\n\n**Search 1:** Current state — `\"[topic] current status [year]\"`\n**Search 2:** Growth indicators — `\"[topic] growth data market size [year]\"`\n**Search 3:** Barriers and headwinds — `\"[topic] challenges barriers risks\"`\n**Search 4:** Policy and regulation — `\"[topic] government policy regulation\"`\n**Search 5:** Technology or infrastructure enablers — `\"[topic] technology infrastructure investment\"`\n**Search 6:** Historical precedent — `\"[topic] historical analogue similar transition\"`\n\nFor each signal, classify all 6 attributes:\n\n| Attribute | Values |\n|---|---|\n| direction | supporting \u002F opposing \u002F wildcard \u002F neutral |\n| steeep_category | Social \u002F Technological \u002F Economic \u002F Environmental \u002F Ethical \u002F Political |\n| temporal_layer | Operational (0–3yr) \u002F Strategic (3–10yr) \u002F Civilizational (10+yr) |\n| source_type | primary \u002F secondary \u002F opinion |\n| recency_days | integer |\n| has_evidence | true \u002F false (contains a number, date, or measurable fact) |\n\nPresent signals in a table with all 6 columns filled for every row.\n\n---\n\n### Step 3 — Score Signals\n\nScore every signal individually using this formula:\n\n```\nscore = recency_weight × reliability_weight × type_weight × evidence_multiplier\n```\n\nCap at 1.0. Round to 2 decimal places.\n\n**Recency weights:**\n- 0–90 days: 1.00 · 91–365 days: 0.80 · 1–3 years: 0.60 · 3+ years: 0.40 · unknown: 0.50\n\n**Reliability weights:**\n- Primary (government\u002Fofficial): 1.00\n- Established news (Reuters, Bloomberg, FT, ET): 0.90\n- Industry report (McKinsey, Gartner, NASSCOM): 0.85\n- Analyst commentary: 0.70 · Opinion\u002Fblog\u002Fsocial: 0.50 · Unknown: 0.40\n\n**Type weights:**\n- Supporting: 1.00 · Opposing: 1.00 · Neutral: 0.60 · Wildcard: 1.30\n\n**Evidence multiplier:**\n- DATA \u002F STATISTIC: × 1.20 · EVENT \u002F INCIDENT: × 1.00 · ANALYSIS \u002F OPINION: × 0.70\n\nApply regional multiplier after base score:\n```\nfinal_score = min(1.0, base_score × regional_multiplier[steeep][temporal])\n```\n\nShow scoring table: Signal | recency_w | reliability_w | type_w | evidence_mult | base_score | regional_mult | final_score\n\n---\n\n### Step 4 — Extract Structural Drivers\n\nA **driver** is the deep structural force that explains WHY a cluster of signals exists. Signals are observable. Drivers are causal.\n\nAfter scoring, group signals by STEEEP category. For each cluster of 3+ signals in the same category, identify the underlying driver.\n\nExtract exactly **3 top drivers**, ranked by the sum of final_scores of the signals they explain.\n\nFor each driver state:\n- **Name:** 3–5 word label (e.g. \"India DPI Infrastructure Advantage\")\n- **Force:** One sentence — the structural reality this driver represents\n- **Signals it explains:** List the signal IDs it accounts for\n- **Temporal reach:** Operational \u002F Strategic \u002F Civilizational\n- **Stability:** LOCKED (unlikely to change in 10yr) \u002F SHIFTING (could change in 3–5yr) \u002F FRAGILE (could reverse in 1–2yr)\n\nOutput:\n```\nSTRUCTURAL DRIVERS\nD1 [Name] — [Force]\n   Explains: [signal list] | Temporal: [layer] | Stability: [tier]\n\nD2 [Name] — [Force]\n   Explains: [signal list] | Temporal: [layer] | Stability: [tier]\n\nD3 [Name] — [Force]\n   Explains: [signal list] | Temporal: [layer] | Stability: [tier]\n```\n\nDrivers feed directly into scenario writing in Step 8. Each scenario must be traceable to at least one driver.\n\n---\n\n### Step 5 — Build 6×3 STEEEP Matrix\n\nPopulate all 18 cells. Each cell value = average final_score of all signals mapped to that STEEEP × Temporal combination. Empty cells = 0.\n\n|  | Operational (0–3yr) | Strategic (3–10yr) | Civilizational (10+yr) |\n|---|---|---|---|\n| **Social** | | | |\n| **Technological** | | | |\n| **Economic** | | | |\n| **Environmental** | | | |\n| **Ethical** | | | |\n| **Political** | | | |\n\nApply regional multipliers to each cell. Then identify:\n- **Hot zones:** cells with score > 0.50\n- **Gap zones:** cells with score = 0.00\n- **Dominant zone:** single highest-scoring cell\n\n---\n\n### Step 6 — Cross-Impact Analysis\n\nSignals are scored independently in Step 3, but structural forces interact. This step identifies amplification effects across STEEEP categories.\n\n**Rule:** If 2 or more hot zones exist in the SAME temporal layer, a cross-impact convergence exists. Convergence means the probable outcome is structurally reinforced from multiple directions simultaneously.\n\nFor each temporal layer (Operational \u002F Strategic \u002F Civilizational):\n1. Count hot zones (score > 0.50)\n2. If count ≥ 2: flag as **CONVERGENCE** — state which categories are reinforcing each other and why\n3. If count = 1: flag as **ISOLATED** — single-category signal, more fragile\n4. If count = 0: flag as **BLIND LAYER** — no strong evidence in this time horizon\n\nAlso identify any **opposing cross-impacts**: where a hot zone in one STEEEP category directly contradicts or slows a hot zone in another (e.g. Technological\u002FStrategic hot but Political\u002FStrategic opposing). Flag these as **FRICTION POINTS**.\n\nOutput:\n```\nCROSS-IMPACT\nOperational:    [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nStrategic:      [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nCivilizational: [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\n\nFriction points: [list any STEEEP pairs in conflict, or \"None detected\"]\nConvergence bonus: [+X% to probable_pct if Strategic convergence exists]\n```\n\nApply convergence bonus: if Strategic layer has CONVERGENCE, add 5% to probable_pct before normalization in Step 7.\n\n---\n\n### Step 7 — Find 3 Historical Analogues\n\nIdentify exactly 3 real historical cases that parallel the question's trajectory.\n\nFor each:\n1. **Name:** Common name of the transition\n2. **Similarity (%):** Estimated % structural similarity (0–100)\n3. **Tipping event:** Single event or policy that caused acceleration\n4. **Equivalent today:** YES \u002F NO \u002F PARTIAL\n5. **Which driver it validates:** Match to D1, D2, or D3 from Step 4\n\nPrefer analogues with similarity ≥ 60%. If none exceed 60%, note as a confidence penalty.\n\n---\n\n### Step 8 — Compute Probabilities + Confidence\n\n#### Predictions — Independent Confidence Scores\n\nEach future type is scored independently (0–100). They do NOT sum to 100%.\nFutures cone methodology: a scenario can be 80% Probable AND 60% Plausible simultaneously.\n\n```\nR_probable  = (supporting signals with score > 0.70) × 3\n            + (best analogue similarity \u002F 100) × 4\n            + (hot zone count) × 2\n            + convergence_bonus (5 if Strategic CONVERGENCE, else 0)\n\nR_plausible = (supporting signals with score 0.40–0.70) × 2\n            + (second analogue similarity \u002F 100) × 3\n\nR_possible  = (wildcard signals) × 2\n            + (opposing signals with score > 0.60) × 2\n            + (gap zones \u002F 18) × 3\n```\n\nConvert to independent scores (exponential curve, not normalization):\n```\nprobable_score  = min(100, round((1 - e^(-R_probable  \u002F 18)) × 100))\nplausible_score = min(100, round((1 - e^(-R_plausible \u002F 9))  × 100))\npossible_score  = min(100, round((1 - e^(-R_possible  \u002F 5))  × 100))\n```\n\n#### Confidence\n\n```\nsignal_count_score = min(100, total_signals \u002F 25 × 100) × 0.30\nsignal_diversity   = (unique STEEEP categories covered \u002F 6 × 100) × 0.30\nrecency_score      = (signals with recency_days ≤ 90 \u002F total) × 100 × 0.20\nevidence_score     = (signals with has_evidence=true \u002F total) × 100 × 0.20\n\nconfidence = round(signal_count_score + signal_diversity + recency_score + evidence_score)\n```\n\n---\n\n### Step 9 — Write Scenarios + Assemble Report\n\n#### Scenario Rules\n\n**PROBABLE, PLAUSIBLE, POSSIBLE** — each must:\n- Be traceable to at least one structural driver (cite D1\u002FD2\u002FD3)\n- Have no narrative overlap with the others\n- Include PROOF with a number or date\n- Write IF and BUT in one sentence each — no hedging (\"might\", \"could\")\n\n**PREFERABLE — IFTF Backcasting Structure**\n\nDo not write PREFERABLE as a probability-weighted outcome. Write it as a designed future, then backcast to today.\n\nFormat:\n```\n■ PREFERABLE — [Short title]\n[2–3 sentences: describe the desired state as already achieved]\n\nBACKCAST\nCivilizational (10+yr): [What must be structurally true by the far horizon]\nStrategic (3–10yr):     [What must be built or decided in the medium horizon]\nOperational (0–3yr):    [What must happen NOW to set the trajectory]\n\nLEVERAGE: [The single highest-leverage action available today — specific, not generic]\nDRIVER:   [Which structural driver (D1\u002FD2\u002FD3) this path depends on most]\n```\n\n#### Decision Guidance (deterministic logic)\n\n```\nIF probable_score > 60:\n    stance = \"Align with probable scenario trajectory\"\n    low_regret = \"Invest in capability building in the dominant hot zone\"\n\nELIF plausible_score > 50:\n    stance = \"Hedge between probable and plausible scenarios\"\n    low_regret = \"Choose reversible commitments that work in both\"\n\nELIF possible_score > 40:\n    stance = \"Maintain optionality — signal environment is ambiguous\"\n    low_regret = \"Invest in monitoring and early-warning indicators\"\n\nELSE:\n    stance = \"Defer commitment — insufficient signal clarity\"\n    low_regret = \"Reduce uncertainty before acting\"\n```\n\nConfidence qualifier:\n- ≥ 70: prefix \"High conviction —\"\n- \u003C 40: prefix \"Low conviction —\" and add \"Expand signal collection before acting\"\n\nRisk trigger: the opposing signal with the highest final_score.\n\n#### Canonical Output Template\n\n**MANDATORY: Output ALL sections below, every single run, no exceptions. Never skip a section. Never produce a partial report.**\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nSOFT PREDICT FUTURE  ·  FORESIGHT ENGINE\n[Query]\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nPREDICTIONS\n■ Probable  [[X]\u002F100] [████████████░░░░░░░░] — [one sentence, no hedging]\n■ Plausible [[X]\u002F100] [████████░░░░░░░░░░░░] — [one sentence, no hedging]\n■ Possible  [[X]\u002F100] [████░░░░░░░░░░░░░░░░] — [one sentence, no hedging]\n■ Preferable          [stakeholder analysis below]\n\nConfidence: [X]\u002F100  |  Signals: [N]  |  Horizon: [YYYY–YYYY]  |  [YYYY-MM-DD]\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nSIGNAL PULSE\n— How many pieces of real-world evidence support, oppose, or complicate this question\nSupporting [N] [████████████░░░░░░░░]  Opposing [N] [████░░░░░░░░░░░░░░░░]  Wild [N]\nNet: [SUPPORTING LEADS \u002F OPPOSING LEADS \u002F NEUTRAL]\nHot zone: [The single STEEEP category with strongest evidence]\nGap: [STEEEP categories with no signals, or \"None — full coverage\"]\n\nSTRUCTURAL DRIVERS\n— The 3 deep causal forces (not events) explaining WHY the signals exist. Stability = likelihood of change.\nD1 [Name] — [Force] ([LOCKED \u002F SHIFTING \u002F FRAGILE])\nD2 [Name] — [Force] ([LOCKED \u002F SHIFTING \u002F FRAGILE])\nD3 [Name] — [Force] ([LOCKED \u002F SHIFTING \u002F FRAGILE])\n\nCROSS-IMPACT\n— Whether multiple STEEEP domains reinforce or contradict each other in the same time layer\nOperational:    [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nStrategic:      [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nCivilizational: [CONVERGENCE \u002F ISOLATED \u002F BLIND LAYER] — [explanation]\nFriction:       [Conflicting domain pairs, or \"None detected\"]\n\nHISTORICAL MATCH\n— Real past transition most structurally similar to this question. Higher % = stronger precedent.\n[Best analogue] ([similarity]% similar)\nTipped by: [The specific event or policy that caused the shift]\nEquivalent now: [EXISTS \u002F PARTIAL \u002F ABSENT]\nValidates: [D1 \u002F D2 \u002F D3]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n■ PROBABLE [[X]%] — [Title]\n— The most evidence-backed outcome given current signal strength\n[2–3 sentence narrative. No hedging.]\nPROOF: [Fact with number or date]\nIF:    [The condition that activates this scenario]\nBUT:   [The constraint or bottleneck that could slow it]\nDRIVER: D[n]\n\n■ PLAUSIBLE [[X]%] — [Title]\n— A realistic alternative if moderate signals strengthen or dominant ones weaken\n[2–3 sentence narrative]\nPROOF: [Fact with number or date]\nIF:    [Activation condition]\nBUT:   [Constraint]\nDRIVER: D[n]\n\n■ POSSIBLE [[X]%] — [Title]\n— A lower-probability outcome driven by wildcards or high-scoring opposing signals\n[2–3 sentence narrative]\nPROOF: [Fact with number or date]\nIF:    [Activation condition]\nBUT:   [Constraint]\nDRIVER: D[n]\n\n■ PREFERABLE — [Title]\n— Not a prediction. A designed future: what the best achievable outcome looks like, traced back to today.\n[2–3 sentences: desired state as already achieved. No hedging.]\nBACKCAST\n  Civilizational: [What must be structurally true by the far horizon]\n  Strategic:      [What must be built or decided in the medium term]\n  Operational:    [What must begin NOW to set the trajectory]\nLEVERAGE: [Single highest-leverage action today — specific actor, specific action]\nDRIVER: D[n]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nPREFERABLE FUTURES  ·  Per major stakeholder\n— For each major player in the query, state the conditions required for their preferred outcome\n\n[Player A]:\n  Wins IF  → [specific condition that must be created or occur]\n  BUT ONLY → [binding constraint that must also be satisfied]\n  ONLY THEN → [the outcome that becomes possible]\n\n[Player B]:\n  Wins IF  → [specific condition]\n  BUT ONLY → [binding constraint]\n  ONLY THEN → [outcome]\n\n[Users\u002FSociety — always include]:\n  Wins IF  → [condition for best collective outcome]\n  BUT ONLY → [constraint]\n  ONLY THEN → [outcome]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nTHE ONE THING\n— The single variable whose presence or absence determines which scenario actually unfolds\n[One sentence naming the deciding variable]\nINCIDENT: [Real past event showing this variable's power]\nWATCH:    [Leading indicator — a milestone, metric, or policy action to monitor]\nIF YES → [What accelerates]\nIF NO  → [What stalls]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nDECISION GUIDANCE\nRecommended stance: [From deterministic probability logic]\nLow-regret move:    [Action that pays off in multiple scenarios simultaneously]\nRisk trigger:       [Highest-scored opposing signal — the one that could invalidate Probable]\n\n[REGIONAL LENS — [REGION]]\nTop multipliers: [STEEEP\u002Ftemporal (Xx)]  [STEEEP\u002Ftemporal (Xx)]\nKey local variable: [One sentence on the dominant local structural factor]\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nMETHODOLOGY KEY\nSignal score (0–1)     Recency × source reliability × signal type × evidence strength — higher = fresher, better-sourced, stronger evidence\nConfidence (0–100)     Signal density (0–40) + evidence balance (0–30) + historical grounding (0–30) − blind spot penalty (0–15)\nPredictions            PROBABLE \u002F PLAUSIBLE \u002F POSSIBLE are independent scores (0–100 each, do NOT sum to 100)\n                       Futures cone: a scenario can score high on multiple types simultaneously\nSTEEEP matrix          6 domains × 3 time horizons — ★ hot (>1.0) ● warm (>0.5) ✗ blind spot (0)\nHistorical similarity   Structural pattern match to real past transitions — 60%+ is reliable precedent; below 40% is weak grounding\nConvergence bonus      +5 added to Probable score when 2+ STEEEP domains reinforce each other in the Strategic layer\nStability tiers        LOCKED = unlikely to change in 10yr | SHIFTING = could change in 3–5yr | FRAGILE = could reverse in 1–2yr\nPreferable futures     Per stakeholder: Wins IF [condition] BUT ONLY [constraint] ONLY THEN [outcome]\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n---\n\n## Visual Output (claude.ai with Artifacts)\n\nIf running on claude.ai and Artifacts are enabled, after the text report generate an HTML Artifact:\n\n```html\n\u003C!-- Render a visual foresight report with:\n  1. Predictions bar chart — horizontal bars for Probable\u002FPlausible\u002FPossible scores\n  2. STEEEP matrix — 6×3 color-coded table (darker green = hotter cell, red = blind spot)\n  3. Futures cone — SVG diagram showing 4 scenario bands expanding from present to horizon\n  4. Stakeholder preferable cards — one card per player with Wins IF \u002F BUT ONLY \u002F ONLY THEN\n  Use inline CSS only. No external dependencies. Dark background (#0f0f0f), accent color #00d4aa.\n-->\n```\n\n---\n\n## Regional Multiplier Tables\n\nApply in Step 3 and Step 5.\n\n### India\n| | Operational | Strategic | Civilizational |\n|---|---|---|---|\n| **Social** | 1.10 | 1.30 | 1.20 |\n| **Technological** | 1.40 | 1.30 | 1.10 |\n| **Economic** | 1.20 | 1.25 | 1.15 |\n| **Environmental** | 0.90 | 1.00 | 1.10 |\n| **Ethical** | 0.95 | 1.00 | 1.05 |\n| **Political** | 0.85 | 0.90 | 1.00 |\n\n**India note:** UPI\u002FDPI gives asymmetric advantage in Technological\u002FOperational. Political\u002FOperational discounted by regulatory fragmentation across states.\n\n### USA\n| | Operational | Strategic | Civilizational |\n|---|---|---|---|\n| **Social** | 1.00 | 1.10 | 1.05 |\n| **Technological** | 1.20 | 1.40 | 1.20 |\n| **Economic** | 1.10 | 1.30 | 1.10 |\n| **Environmental** | 0.95 | 1.00 | 1.05 |\n| **Ethical** | 1.05 | 1.10 | 1.10 |\n| **Political** | 0.90 | 0.95 | 1.00 |\n\n**USA note:** Deep capital markets amplify Technological\u002FStrategic. Political\u002FOperational discounted by legislative gridlock.\n\n### Europe\n| | Operational | Strategic | Civilizational |\n|---|---|---|---|\n| **Social** | 1.00 | 1.05 | 1.10 |\n| **Technological** | 1.00 | 1.10 | 1.05 |\n| **Economic** | 0.95 | 0.90 | 0.90 |\n| **Environmental** | 1.20 | 1.40 | 1.30 |\n| **Ethical** | 1.10 | 1.20 | 1.20 |\n| **Political** | 1.05 | 1.10 | 1.10 |\n\n**Europe note:** Regulatory leadership (GDPR, EU AI Act, Green Deal) amplifies Environmental\u002FStrategic. Economic\u002FCivilizational discounted by demographic headwinds.\n\n### China\n| | Operational | Strategic | Civilizational |\n|---|---|---|---|\n| **Social** | 1.00 | 1.10 | 1.05 |\n| **Technological** | 1.20 | 1.50 | 1.30 |\n| **Economic** | 1.10 | 1.20 | 1.10 |\n| **Environmental** | 0.90 | 1.00 | 1.05 |\n| **Ethical** | 0.70 | 0.75 | 0.80 |\n| **Political** | 1.10 | 1.15 | 1.00 |\n\n**China note:** State-directed capital amplifies Technological\u002FStrategic strongly. Ethical\u002FOperational discounted by limited transparency.\n\n### Global (default)\nAll multipliers = 1.0. Apply when no region is detectable.\n",{"name":5,"description":7},"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-AI-应用工具\u002FYYC3-AI-应用工具-buildwithclaude\u002Fplugins\u002Fforesight-intelligence\u002Fskills\u002Fsoft-predict-future",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill soft-predict-future",{"tool":39,"command":40},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill soft-predict-future",{"tool":42,"command":43},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill soft-predict-future","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-buildwithclaude\u002Fplugins\u002Fforesight-intelligence\u002Fskills\u002Fsoft-predict-future\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]