Menu
SkillsMP has collected 39 skills from grammy-jiang/intelligence-analysis-agent. Open a skill to review its source and details.
Showing 39 of 39 collected skills.
Produce the calibrated numeric probability — a draft Judgment — for a question under uncertainty: outside view / base rate first, Fermi-decompose, fold in the bias/deception review findings, adjust with case specifics, then state an explicit number with…
Runs an open-source (OSINT) investigation to collect and verify evidence for an analytic question — search, fetch through the egress guard, hash/EXIF for archival, archive each item into the evidence-ledger as an UNTRUSTED ingested proposal, then verify…
Grade an evidence item before it drives a judgment: rate source reliability (A–F) and information credibility (1–6) on two independent axes, weight by diagnosticity, seek corroboration, check for deception, and record the absence of expected evidence. Invoke…
Run the structured analytic-tradecraft workflow on an intelligence or analytic question — frame it, enumerate ALL competing hypotheses, weigh evidence in an ACH matrix ranked by disconfirmation, get independent bias / method / calibration critique from…
Review how far the adversary is judged to trust a channel — the belief on which every deception rests; use when reviewing this facet of a deception or counter-deception case.
Review the material fed to the adversary and how the deception is built; use when reviewing this facet of a deception or counter-deception case.
Review the reasoning about whether you are the one being deceived — the mirror discipline that keeps a running deceiver honest; use when reviewing this facet of a deception or counter-deception case.
Review the organisation, policy, and approval machinery around a deception system; use when reviewing this facet of a deception or counter-deception case.
Review the structure of a controlled network for the security that keeps one blown agent from collapsing the rest; use when reviewing this facet of a deception or counter-deception case.
Review the physical and technical construction of a plant — staged sabotage, planted documents, funding, and channel choice; use when reviewing this facet of a deception or counter-deception case.
Review the long-horizon stewardship of a deception capability: when to build it, hold it, spend it, and wind it down; use when reviewing this facet of a deception or counter-deception case.
Review how a captured or walk-in agent is turned and then run day to day; use when reviewing this facet of a deception or counter-deception case.
Audits the training, team, and review process behind an analytic judgment — devil's advocacy, pre-publication review, postmortems — invoke to review that process, not the judgment itself.
Audits an analytic product's assumption explicitness, question framing, and fact/opinion/uncertainty write-up; invoke before a judgment or forecast is finalized.
Audit whether an estimate anchored to its reference-class base rate (the outside view) before case detail moved it; use when a forecast leans on inside-view specifics or ignores regression to the mean.
Audit whether a probability's move from prior to posterior was sized to the evidence's true diagnosticity; use when a belief was, or should have been, revised after new evidence.
Audits whether a probability judgment is numeric, granular, effort-triaged, self-checked, and coherent; invoke when reviewing an analytic estimate, probability, or forecast.
Review a single stated probability or confidence judgment, and its reasoning, for the failure modes that make numbers miscalibrated; use when checking one forecast's number.
Surface the cognitive traps that corrupt a forecast's reasoning (as distinct from its data or math); use when a defensible-looking forecast may rest on biased judgment.
Audits an analytic judgment or forecast for fast, intuitive System 1 biases — motivated skepticism, asymmetric scrutiny, the affect heuristic — before it is finalized.
Audits whether an analytic judgment weighed a full hypothesis set by diagnostic evidence rather than fit; invoke before finalizing a hypothesis-driven judgment or forecast.
Audits deterrence/spiral reasoning about adversary intentions, arms, and signals for security-dilemma blindness and self-confirming logic; invoke on a threat, concession, or arming decision.
Audits whether a fast, confident judgment in an analytic product was checked by deliberate reasoning, or instead rests on a substituted question, cognitive ease, or an illusory pattern.
Make a forecast or track record scoreable and score it without a story or excuse standing in for the arithmetic; use when evaluating forecast accuracy or a proper score.
Review whether a forecaster or team is cultivated and judged to build calibration, and whether multiple forecasts are aggregated well; use when assessing forecaster development or combining forecasts.
Guard a forecast review against failures in how forecasts are judged, rewarded, and defended (not the math); use when accountability, incentives, or communication of a forecast is in scope.
Audits a forecaster's reasoning, track record, and process design for hedgehog overconfidence and formula-vs-intuition failures; invoke when reviewing forecasting judgment or credibility claims.
Audits a judgment's use of historical analogy, its outcome-driven lessons, and hindsight's erasure of prior uncertainty; invoke when precedent or a resolved outcome shapes the case.
Audits an analytic judgment's anchors, base-rate use, and adjoining reasoning slips before the estimate drives a decision.
Audits an analytic judgment's use of theory, generalizations, and prediction limits — data- vs. concept-driven method and the mosaic fallacy — before the judgment is finalized.
Invoke to audit whether a judgment rests on an untested mind-set, filters out discrepant evidence, or skips a structured technique like Alternative Futures before the estimate is finalized.
Audits an analyst's own schemata, analogies, and historical lessons for premature closure and stale premises before a judgment is finalized.
Audits an analytic judgment for motivated reasoning and belief perseverance; invoke when a belief or policy resists discrepant evidence instead of updating.
Audits how an analytic product reads another actor's intent, image, or signals for attribution and perception bias; invoke before that reading drives a judgment or response.
Audits whether an analytic product tested — not merely assumed — how an adversary reads our signals, firmness, or resolve; invoke whenever a judgment characterizes how the adversary perceives us.
Audits a stated probability or forecast for coherence, aggregation, and calibration; invoke also to advise on or compare aggregation approaches before one is finalized.
Audits framing, reference points, and decision weights in an analytic product's stated preferences and value or well-being claims; invoke when framing itself may be driving the stated judgment.
Check whether a forecast's precision, form, and confidence match what is knowable at its horizon and its subject's tail behaviour; use when reviewing scenario, range, or tail-risk framing.
Reviews an analytic product's use of structured techniques (Red Team, Alternative Futures, brainstorming, Outside-In, Indicators); invoke when choosing or sequencing one too.