{"skill":{"slug":"zeelin-us-iran-forecast","displayName":"Zeelin Us Iran Forecast","summary":"Collect, verify, and forecast war or geopolitical conflict developments using authoritative sources, cross-validation, and scenario-based prediction.","description":"---\nname: war-conflict-intel-and-forecast\ndescription: Collect, verify, and forecast war or geopolitical conflict developments using authoritative sources, cross-validation, and scenario-based prediction.\nversion: 1.0.0\nmetadata:\n  openclaw:\n    emoji: \"🛰️\"\n---\n\n# War / Geopolitical Conflict Intelligence & Forecast Skill\n\n## Purpose\nTurn a request like:\n\n- “Collect the latest battlefield situation”\n- “Use authoritative sources”\n- “Give a more precise assessment”\n- “Predict what the U.S., Iran, Israel, or other actors may do next”\n- “Estimate likely end-state trajectories”\n\ninto a stable workflow that is:\n- fact-first\n- source-ranked\n- cross-verified\n- explicit about uncertainty\n- disciplined in prediction\n\nThis skill is for open-source intelligence style synthesis, not classified intelligence, not propaganda, and not fantasy war writing.\n\n---\n\n## Core Rules\n\n### 1) Separate facts from judgments\nEvery answer must be split into:\n- Confirmed facts\n- Assessment / inference\n- Forecast\n\nNever present a forecast as if it were already confirmed reality.\n\n### 2) War information is adversarial by default\nIn war, every side has incentives to:\n- exaggerate success\n- hide losses\n- shape public opinion\n- pressure allies and markets\n- trigger psychological effects\n\nTherefore:\n- a single belligerent’s statement is not enough\n- strong claims require stronger verification\n- “destroyed”, “eliminated”, “full control”, “crippled”, “collapsed” should be treated as claims to verify, not instant facts\n\n### 3) Use concrete dates and time windows\nDo not write:\n- today\n- recently\n- just now\n\nWrite:\n- exact date\n- if needed, exact time and timezone\n- explicit forecast window such as next 24 hours / next 3–7 days / next 2–6 weeks\n\n### 4) Precision beats confidence theater\nDo not sound certain when evidence is thin.\nPrefer:\n- high probability\n- medium probability\n- low probability / high impact\n- too early to confirm\n- single-source claim\n- preliminary signal\n\n### 5) Every forecast needs a trigger and a disconfirming signal\nFor each prediction, state:\n- what evidence supports it\n- what new evidence would strengthen it\n- what evidence would weaken or overturn it\n\n---\n\n## What to Collect Every Time\n\nFor any armed conflict or fast-moving geopolitical crisis, collect at least these five buckets:\n\n### A. Battlefield / operational developments\n- strikes, missile launches, drone attacks, naval incidents\n- target sets\n- claimed damage\n- defensive interceptions\n- territorial / airspace / maritime control changes\n- underground or hardened facility status if relevant\n\n### B. Military capability changes\n- air defense degradation\n- missile inventory depletion\n- logistics and fuel strain\n- command-and-control damage\n- reserve mobilization\n- naval disruption capability\n- survivability of leadership and strategic assets\n\n### C. Political and diplomatic signaling\n- head of state statements\n- defense ministry / military spokesperson statements\n- legislative action\n- alliance commitments\n- mediation or ceasefire signals\n- red lines and ultimata\n\n### D. Regional and global spillover\n- shipping and chokepoints\n- oil and gas markets\n- refugee / humanitarian indicators\n- proxy fronts\n- neighboring states’ alert status\n- UN / IAEA / international organization warnings\n\n### E. Forward indicators\n- what would signal escalation\n- what would signal negotiated de-escalation\n- what would signal a shift in probable end-state\n\n---\n\n## Source Hierarchy\n\nBuild the answer from the top of this hierarchy downward.\n\n## Tier 1: Core authoritative backbone\nUse these first to build the main factual structure.\n\n### Reuters\nUse for:\n- fast and relatively restrained reporting\n- official statements\n- battlefield + diplomacy + market linkage\n- shipping, oil, energy, sanctions, legislative context\n\n### AP\nUse for:\n- live war updates\n- casualties and immediate developments\n- domestic political reaction\n- field-level narrative updates\n\n### Official primary sources\nUse to confirm what an actor said, not automatically whether the claim is true:\n- White House\n- U.S. Department of Defense / State Department\n- Israeli PM office / defense ministry / IDF\n- Iranian foreign ministry / military / official state outlets\n- UN, IAEA, UNHCR, ICRC, etc.\n\n### Hard-data and system indicators\nUse where available:\n- shipping traffic data\n- oil price reactions\n- public market data\n- satellite imagery reporting\n- port advisories\n- aviation / maritime notices\n\n---\n\n## Tier 2: Strong supporting sources\nUse to add depth, background, or insider context.\n\n### Financial Times / BBC / Wall Street Journal / New York Times\nUse for:\n- deeper diplomatic context\n- insider sourcing\n- strategic framing\n- policy debates\n\nRule:\n- anonymous sourcing should ideally be checked against another reliable source\n\n### Al Jazeera and major regional outlets\nUse for:\n- regional framing\n- Arab-world reactions\n- local political atmosphere\n\nRule:\n- do not rely on these alone for decisive battlefield claims\n\n---\n\n## Tier 3: Cautious-use sources\n### Social media, Telegram, X, viral video\nUse only for:\n- early leads\n- geolocation clues\n- timeline hints\n\nNever treat them as settled fact until checked.\n\nIf using them, verify:\n- date\n- location\n- whether footage is old\n- whether credible journalists or organizations have corroborated it\n\n### Analysts / think tanks / military commentators\nUse for:\n- force structure\n- campaign logic\n- weapons context\n- scenario analysis\n\nDo not let commentary substitute for hard confirmation.\n\n---\n\n## Mandatory Verification Labels\n\nFor every major claim, implicitly or explicitly classify it as one of these:\n\n- Confirmed  \n  at least two reliable sources or one reliable source plus strong corroborating data\n\n- Single-party claim  \n  one side says it; independent confirmation is missing\n\n- High-confidence inference  \n  not formally confirmed, but several indicators point the same way\n\n- Unverified / preliminary  \n  not safe to treat as established\n\nExamples:\n- “State X says it destroyed underground missile infrastructure” → single-party claim unless independently supported\n- “Tanker traffic through a chokepoint collapsed” → confirmed if supported by Reuters plus traffic data\n- “Leadership is considering a ceasefire” → high-confidence inference or unverified unless solidly corroborated\n\n---\n\n## Standard Workflow\n\n## Step 1: Establish the situation frame\nBefore details, answer:\n1. What phase is the conflict in?\n2. What are the most important events in the last 48 hours?\n3. Is the conflict escalating, stabilizing, or fragmenting?\n4. Are there any real negotiation signals?\n5. What spillover risks are already visible?\n\nBuild this first with Reuters + AP + official primary sources.\n\n---\n\n## Step 2: Build a dated timeline\nList at least 5–10 major events with:\n- exact date\n- what happened\n- why it matters\n- source confidence level\n\nFormat:\n- 2026-03-05 — Israel signals a “second phase” focused on underground missile facilities.  \n  Why it matters: target set shifts from visible assets to survivable strategic capacity.  \n  Status: reported by Reuters.\n\n---\n\n## Step 3: Disaggregate actor goals\nAlways separate what each actor wants.\n\n### U.S. usually cares about\n- degrading opponent military capability\n- protecting forces and allies\n- maintaining deterrence credibility\n- avoiding politically costly quagmire\n- limiting oil-price and market damage\n- preserving coalition support\n\n### Israel usually cares about\n- maximizing long-term reduction of hostile capability\n- degrading missile, nuclear, proxy, and command networks\n- converting battlefield opportunity into strategic depth\n\n### Iran or similar regional state actors often care about\n- regime survival\n- preserving retaliatory capacity\n- raising cost on adversaries\n- using missiles, drones, proxies, and chokepoints asymmetrically\n- turning a military disadvantage into a political/economic endurance contest\n\nDo not merge these into one “allied side” goal.\n\n---\n\n## Step 4: Identify constraints\nPrediction quality depends on knowing not just intent, but limits.\n\nCheck:\n- munitions stockpiles\n- air superiority status\n- survivability of underground assets\n- shipping chokepoint control\n- domestic political support\n- legislative constraints\n- coalition cohesion\n- proxy readiness\n- economic pressure\n- humanitarian blowback\n\n---\n\n## Step 5: Forecast by time horizon\nNever give one undifferentiated prediction blob.\n\n### Horizon A: next 24 hours\nLook for:\n- immediate retaliatory patterns\n- strike tempo\n- naval incidents\n- emergency diplomacy\n- casualty shocks that change behavior fast\n\n### Horizon B: next 3–7 days\nLook for:\n- campaign phase shifts\n- strikes on harder strategic targets\n- proxy front activation\n- widening to nearby states\n- backchannel mediation\n\n### Horizon C: next 2–6 weeks\nLook for:\n- sustained limited war\n- negotiated freeze\n- regionalization\n- internal instability\n- strategic exhaustion\n\n---\n\n## Forecast Template\n\nFor each forecast, use this structure:\n\n### Conclusion\nExample:\n- “Over the next 3–7 days, the U.S. and Israel are likely to intensify strikes on hardened and underground missile infrastructure.”\n\n### Why this is plausible\nList the supporting signals:\n- public rhetoric remains escalatory\n- evidence of air-access advantage\n- campaign messaging indicates a second phase\n- strategic logic favors reducing residual retaliatory capability\n\n### Constraints\nList what could slow or limit this:\n- munitions expenditure\n- oil price pressure\n- domestic political pushback\n- escalation risk to shipping or bases\n- allied caution\n\n### Confirming signals to watch\n- more reporting on bunker-busting or underground target sets\n- repeated strikes on command-and-control nodes\n- expanded evacuation notices\n- intensified maritime protection operations\n\n### Disconfirming signals\n- public move toward talks\n- partial restoration of commercial shipping under de-escalation arrangements\n- legislative effort constraining operations\n- credible third-party mediation producing reciprocal restraint\n\n---\n\n## End-State Forecasting\n\nDo not write one cinematic ending.\nUse scenario trees.\n\n### Scenario 1: Limited-war advantage followed by ceasefire or frozen conflict\nTypical signs:\n- one side achieves clear conventional military superiority\n- the other side is badly degraded but not collapsed\n- international pressure builds\n- both sides redefine victory politically\n\n### Scenario 2: Protracted regionalized conflict\nTypical signs:\n- multiple proxy fronts remain active\n- shipping and energy disruption persist\n- strikes continue episodically\n- no side can impose a decisive settlement\n\n### Scenario 3: Internal regime or command-structure fracture\nTypical signs:\n- decapitation or severe leadership disruption\n- fragmented control\n- growing elite splits\n- security apparatus inconsistency\n- rising uncertainty over strategic asset control\n\nFor each scenario:\n- assign rough probability\n- state why\n- state what would move probability up or down\n\n---\n\n## Variables That Most Often Change the Outlook\n\n### Military variables\n- who owns the airspace\n- survivability of underground facilities\n- remaining missile inventory\n- maritime interdiction capability\n- resilience of command networks\n\n### Political variables\n- leadership rhetoric shifts\n- legislative constraints\n- coalition discipline\n- tolerance for casualties and economic pain\n\n### Economic variables\n- oil price trajectory\n- insurance and shipping disruption\n- domestic consumer price impact\n- sanctions tightening or leakage\n\n### Diplomatic variables\n- whether mediators are active\n- whether allies begin pressing for de-escalation\n- whether international watchdogs issue sharper warnings\n- whether a face-saving negotiation channel appears\n\n---\n\n## Output Structure\n\nUse this order:\n\n# 1. One-sentence bottom line\nExample:\n- “The conflict has moved into a deeper, more dangerous phase, and the near-term outlook favors continued escalation before any serious public ceasefire opening.”\n\n# 2. Confirmed facts\nGroup into:\n- recent battlefield developments\n- political signaling\n- regional/economic spillover\n\n# 3. Assessment\nExplain:\n- what phase the conflict is in\n- which side currently has initiative\n- what each side is trying to achieve\n- what the key constraints are\n\n# 4. Forecast\nSplit by:\n- next 24 hours\n- next 3–7 days\n- next 2–6 weeks\n\nWithin each, separate:\n- high probability\n- medium probability\n- low probability / high impact\n\n# 5. End-state scenarios\nAt least three:\n- most likely\n- plausible alternative\n- lower-probability but high-risk\n\n# 6. Watchlist\nGive 3–7 indicators that would change the assessment fastest.\n\n---\n\n## Common Failure Modes\n\n### Failure 1: repeating propaganda as fact\nFix:\n- attribute clearly\n- verify independently\n- downgrade confidence where needed\n\n### Failure 2: focusing only on kinetic events\nFix:\n- always include oil, shipping, politics, diplomacy, and humanitarian spillover\n\n### Failure 3: prediction without time horizon\nFix:\n- always separate near-term, short-term, and multi-week outlook\n\n### Failure 4: overconfidence\nFix:\n- use probability bands\n- include disconfirming evidence\n- show what would change your mind\n\n### Failure 5: actor-blending\nFix:\n- separate U.S., Israel, Iran, proxies, Gulf states, and other actors where relevant\n\n---\n\n## Final Discipline Checklist\n\nBefore delivering, verify:\n\n- [ ] Facts and forecasts are clearly separated\n- [ ] Dates are concrete\n- [ ] Reuters / AP / primary sources form the backbone\n- [ ] Major claims are cross-checked\n- [ ] Single-party claims are labeled as such\n- [ ] Military, political, economic, and diplomatic dimensions are covered\n- [ ] Forecasts are time-boxed\n- [ ] End-state analysis uses scenarios, not one rigid ending\n- [ ] There is a watchlist of indicators that could change the view\n- [ ] Language is disciplined, not theatrical\n\n---\n\n## One-line operating principle\nBe slower than propaganda, but more accurate than hype.\n","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":530,"installsAllTime":19,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1772941456780,"updatedAt":1778491773474},"latestVersion":{"version":"1.0.0","createdAt":1772941456780,"changelog":"**Initial release of the conflict information collection and forecast handbook.**\n\n- Provides a systematic process for collecting, verifying, and forecasting US-Iran-related conflict developments.\n- Enforces clear separation between confirmed facts and predictions, with specific labels and verification standards.\n- Outlines information collection priorities (battlefield, capabilities, political, spillover, future signals).\n- Specifies a tiered source reliability hierarchy, with Reuters, AP, and official channels as primary.\n- Establishes step-by-step workflow and output templates, including timeline, scenario trees, and probability-based forecast windows.\n- Includes detailed validation checklists and common error prevention guidelines.","license":null},"metadata":{"setup":[],"os":null,"systems":null},"owner":{"handle":"wlkqyang-star","userId":"s177je4na5d6mkn26g9g2adff583q1eq","displayName":"wlkqyang-star","image":"https://avatars.githubusercontent.com/u/228461771?v=4"},"moderation":null}