structured-analytic-skills

Plugin structured-analytic-skills from marketplace structured-analytic-skills in radarist/structured-analytic-skills. Commands read from the repo's manifest — 1 month ago.

Skills (70)

• skill-name-here

  Third person, one or two sentences: what the skill does, then when to reach for it, with two to four quoted trigger phrases a user would actually type — \"score this on TRL\", \"is this claim safe to ship?\". Route the near misses explicitly: not for {adjacent situation} (use `sibling-skill`). No wo

• abstain-or-escalate

  Decides what to do with a claim that verification could not confirm — drop it, refuse it in plain words, escalate it as a named open question, or report the disagreement between conflicting sources — instead of shipping a hedged guess. Use when verification has already failed: \"there is no source f

• amstar2-review-appraisal

  Appraises a systematic review or meta-analysis with AMSTAR 2 (AMSTAR-2; Shea et al., BMJ 2017): answers the 16 checklist items from the review's report, flags flaws in the seven critical domains and derives the overall confidence rating — High, Moderate, Low or Critically low — never a summed score.

• analysis-of-competing-hypotheses

  Ranks rival explanations of a question by which one the evidence contradicts least (Heuer's Analysis of Competing Hypotheses — ACH — CIA), then names the single piece of evidence the ranking hinges on. Use when a question has two or more plausible explanations and confirmation bias would be costly —

• analyze-patent-claims

  Dissects one patent's claim set the way an examiner reads it — independent versus dependent claims, the transitional phrase that fixes the scope (comprising = open, consisting of = closed), the elements of claim 1, the classification codes, and prior-art signals — and returns a structured record of

• analyze-release-notes

  Turns a release note or changelog into a structured record — version and prior version, the SemVer bump, breaking changes and deprecations quoted verbatim, bug-fix count, CVE/GHSA advisories — and rates how much the release should worry a consumer. Use when a version delta is on the table: \"what ch

• apply-hype-cycle

  Places one discontinuous technology on the five phases of Gartner's Hype Cycle — Innovation Trigger, Peak of Inflated Expectations, Trough of Disillusionment, Slope of Enlightenment, Plateau of Productivity — by counting sourced indicators, then reports the phase, a time-to-plateau range and the sta

• assess-research-momentum

  Reads a scholarly result set for one research area — publication S-curve phase, citation velocity and acceleration, author and institution concentration — and reports a research-front or maturing verdict with the observation that would flip it. Use when asked \"is research on X heating up?\", \"is t

• assess-study-bias

  Grades a randomised trial with Cochrane RoB 2 — the five domains of randomization process, deviations from intended interventions, missing outcome data, measurement of the outcome, and selection of the reported result — and emits per-domain and overall judgements of Low risk / Some concerns / High r

• backcasting

  Works backwards from a desired end state to the present, producing a dated milestone chain, evidenced measure packages, a barrier and lock-in register and a near-term action agenda (Robinson's normative backcasting, Energy Policy, 1982). Use when the goal is a future that current trends will not del

• bayesian-update

  Revises a stated probability in light of one new piece of evidence using the odds form of Bayes' rule — prior odds × Bayes factor = posterior odds — and reports the posterior in both relative and absolute terms with a sensitivity sweep over the prior and the likelihood ratio. Use when a belief has t

• benchmark-model-claims

  Audits a claim about model or system performance against six integrity domains — test-set contamination, baseline pinning, seed and run variance, evaluator independence, metric selection, and whether the test set is large enough for the reported gap — and emits a 0–5 reliability score with named ris

• brier-score-calibration

  Scores a set of resolved probabilistic forecasts with the Brier score, decomposes it into reliability, resolution and uncertainty, compares it against the base-rate reference with a Brier Skill Score, and reports a per-bin calibration table showing where the forecaster is over- or underconfident. Us

• causal-layered-analysis

  Deconstructs an issue through the four levels of Causal Layered Analysis — litany, systemic causes, worldview/discourse, myth/metaphor (Inayatullah, Futures, 1998) — then reconstructs a vertically coherent alternative future, producing a four-layer table, deconstruction notes and a reframed narrativ

• cheapest-experiment

  Turns a recommendation into its cheapest decisive test — the smallest bounded pilot, its cost and duration, a pass/fail rule fixed before the run, and what each outcome would change — in the spirit of Ries's Lean Startup build-measure-learn loop and MVP. Use when a brief ends in recommendations or a

• chemistry-claim-check

  Checks molecular claims stated in prose — compound name against formula, degree of unsaturation, recomputed molecular weight, and the assessable part of the Lipinski rule of five — and returns a PASS/FAIL verdict per item with the arithmetic shown. Use when a paper, patent, or product page pairs a c

• cite-ieee

  Converts a report's sources into IEEE numbered-bracket citations — inline `[1]`, `[1], [4]`, `[2]–[5]` markers numbered by first appearance, plus an end-of-document References list formatted per source type — and checks that the numbering and the list agree. Use when a document carries three or more

• claim-provenance

  Tags every fact-claim in a document inline as either `[validated, {source}]` or `[assumption, retire-by {milestone}]`, so a reader can see at a glance which sentences rest on evidence and which rest on reasoning, and what would convert each assumption into knowledge. Use when a brief mixes cited fac

• critique-report

  Runs a structured self-critique of a finished draft before it is published — ten review points (does it answer the question, is the evidence sourced, is confidence honest, are limitations and counter-evidence stated, are the numbers defensible, is the next action actionable) plus three conditional o

• cross-impact-analysis

  Builds an N x N cross-impact matrix over a set of events or variables, rating each ordered pair's direct influence, then computes direct-stage MICMAC influence/dependence rankings that separate strategic levers from indicators and flags asymmetric pairs for re-rating (Gordon & Hayward, Futures, 1968

• cynefin-classification

  Classifies a decision situation into one of Cynefin's five contexts — Clear, Complicated, Complex, Chaotic or Disorder — and names the matching decision mode, so recommendations are framed as playbooks, expert analysis, safe-to-fail probes or stabilising action. Use before advising action under unce

• decision-matrix-mcda

  Ranks several options against weighted criteria with a decision matrix / multi-criteria decision analysis (Heuer & Pherson's Decision Matrix; Saaty's AHP pairwise comparisons for the weights, with a consistency check) and reports how robust the winner is to weight and score changes. Use when a choic

• decompose-research-question

  Breaks a question too large, vague or multi-part to answer directly into a MECE issue tree of atomic sub-questions — each mapped to the skill or research step that answers it, ordered by dependency, with a named method for recombining the answers. Use when a request would otherwise sprawl — \"help m

• delphi-method

  Aggregates independent expert judgments into a consensus estimate — or an honest map of where experts split — with the RAND Delphi method: anonymous panel, iterated rounds, controlled feedback of the group median and interquartile range, and a stability stopping rule. Use when data alone cannot answ

• detect-funding-round

  Parses a capital-raise announcement into a structured FundingEvent record — company, round stage, amount and currency, dates, lead and participating investors, valuation, use of proceeds, confidence. Use when a news item, press release or search result reports financing: \"raised $47 million\", \"cl

• detect-ma-event

  Parses a news article, filing or press release about a change of control into a structured M&A event record — acquirer, target, deal type, consideration, deal value, premium, dates, regulatory jurisdictions, termination fee — and flags deal-structure risks. Use when text says \"agreed to acquire\",

• estimate-market-size

  Sizes a market by triangulating two independent estimates — a top-down cut from a larger market and a bottom-up build from buyer counts and revenue per buyer — and reports the TAM/SAM/SOM layer, a range, and whether the two estimates agree within an order of magnitude. Use when asked \"how big is th

• estimative-language

  Rewrites and lints the likelihood and confidence wording of an assessment against one declared standard — the ODNI ICD 203 estimative-probability terms, the UK PHIA Probability Yardstick, or the IPCC AR5 likelihood scale — converting numbers to calibrated terms, keeping confidence in its own sentenc

• evidence-appraisal

  Rates how much certainty a body of evidence deserves, outcome by outcome, on the GRADE scale (Grading of Recommendations Assessment, Development and Evaluation — high, moderate, low, very low), naming the reason behind every downgrade or upgrade and writing the summary-of-findings row and a calibrat

• evolution-stage

  Tags a named technology, capability or vendor category with its Wardley evolution stage — Genesis, Custom built, Product (+rental) or Commodity (+utility) — anchored in observable evidence, and states the way of working that stage implies. Use when asked \"is this a product or still bespoke?\", \"bu

• expected-value-decision-tree

  Lays out a staged bet as a decision tree, rolls it back to expected values and prices the information a pilot or test would buy — expected value of perfect information (EVPI), expected value of sample information (EVSI) and a one-way sensitivity (tornado) with switching probabilities (Raiffa 1968).

• experimental-design

  Produces a preregisterable design card for a causal test before any data are collected — a falsifiable hypothesis with a minimum detectable effect, the randomization unit and mechanism, a power-based sample size per arm, a fixed stop rule and analysis plan, and an audit of the validity threats that

• five-forces-analysis

  Assesses the structural profitability of an industry with Porter's Five Forces — entry threat, supplier power, buyer power, substitutes and rivalry — rating each on evidence, naming the one or two forces that actually control profits, and reporting how they are trending. Use when the question is whe

• foresight

  Produces one dated, falsifiable prediction about a single technology, trend or market shift — the milestone with a date and a confidence, its accelerants and blockers with lead times, weak signals to watch now, kill-signals that would retract it, and a review date. Use for timing questions — \"when

• futures-wheel

  Maps the consequences of one defined change ring by ring — primary, secondary and tertiary impacts, each chained to a named parent with its mechanism — and returns an assessed consequence map with convergence points, a desirable/undesirable valence check and an implication-to-action table (Jerome C.

• grounded-answer

  Produces a factual answer in which every claim has been independently checked against a source and cited, using Chain-of-Verification (CoVe — Dhuliawala et al., 2023) — the answer ships only with claims that survived verification, plus a list of what could not be verified. Use when a factual answer

• grounded-fact-check

  Audits the load-bearing specifics of a finished draft before it is published — the qubit counts, market figures, benchmark scores, dates and precedence claims a reader would act on — verifying each against live sources with a neutral query and returning a ledger of confirmed, corrected, unverifiable

• high-impact-low-probability

  Takes one event judged unlikely but devastating, postulates it has happened, and reasons backwards to the pathways that could produce it — returning the impact, 2–4 distinct pathways with their triggers, observable early-warning indicators, and a proportionate hedge (High-Impact/Low-Probability and

• horizon-scanning

  Runs a horizon scan — a systematic early-warning sweep of sources outside an organisation's usual reading for weak signals and emerging issues — and delivers a prioritised horizon-scanning report with impact/likelihood ratings, verified sources and next steps (UK Government Office for Science Future

• indicators-validation

  Builds and validates a signpost list — indicators of change — for rival scenarios or hypotheses (Heuer & Pherson's Indicators and Indicators Validator), rating every indicator against every scenario, dropping those that would appear under all of them, and returning the diagnostic set with a monitori

• jtbd-framing

  Frames a technology, vendor or product comparison around the customer's Job to be Done (JTBD) — a solution-free job statement, Ulwick's desired-outcome metrics, the competing solutions a customer could hire (including non-consumption) and the struggling moment that triggers the search. Use when a br

• key-assumptions-check

  Surfaces every premise a conclusion rests on — especially the unstated ones — then challenges each and sorts it into the Key Assumptions Check categories (basically solid, correct with caveats, unsupported or questionable), turning load-bearing unsupported premises into named key uncertainties with

• meta-analysis

  Pools the effect sizes of several comparable studies into one estimate — inverse-variance fixed-effect and DerSimonian–Laird random-effects — and reports how much the studies disagree (Cochran's Q, I², tau²) and whether small studies skew the pool (Egger's test), with a forest table. Use when a user

• morphological-analysis

  Maps the solution space of a design, architecture, or business-model problem with General Morphological Analysis (Zwicky box, 1969; Ritchey's Cross-Consistency Assessment) — parameters × discrete values, every cross-parameter value pair judged consistent or excluded for a stated reason, then the cou

• oss-project-health

  Reads one open-source repository's maintenance vitality — contributor concentration (the CHAOSS Contributor Absence Factor, i.e. bus factor), commit and release cadence, issue responsiveness, unpatched security advisories — and returns a healthy / at-risk / abandoned verdict naming the single bigges

• position-competitor

  Maps three or more competitors onto a two-axis competitive landscape — axis choice tested for orthogonality, each placement justified by evidence, quadrants read, whitespace argued — and reports whether an empty region is an opportunity or simply unviable. Use when asked \"where does X sit versus Y

• premortem-analysis

  Runs Gary Klein's premortem — declare that the plan has already failed, then work backwards to surface the failure modes, pre-emptive mitigations and a kill threshold before the plan is locked in. Use before a strategy, roadmap, launch or investment decision is committed — \"premortem this plan\", \

• pyramid-principle

  Restructures an analytical document top-down using Minto's Pyramid Principle — a single governing thought at the apex, a MECE set of supporting arguments beneath it, evidence beneath those — and checks the vertical and horizontal logic of the result. Use when a document must persuade and currently r

• quality-of-information-check

  Audits the whole evidence base behind an assessment's key judgments — the Quality of Information Check from the CIA Tradecraft Primer (2009), operationalising ICD 206. Maps sources to judgments, exposes single-source, thin and re-reported findings, and writes a source summary statement that tempers

• quantitative-sanity-check

  Recomputes the arithmetic that a document's own numbers imply — CAGR and compounding, price × volume unit economics, percentage vs percentage-point change, share-of-whole, survivorship and base-rate framing, Fermi order-of-magnitude — and flags every claim whose figures do not reproduce each other.

• rate-source-admiralty

  Grades one source on the NATO Admiralty Code — a letter for source reliability (A–F) and a digit for information credibility (1–6), such as B2 — and returns the code with a one-sentence rationale. Use when a source behind a claim, citation or record needs a defensible trust grade rather than a gut f

• read-patent-landscape

  Reads a cluster of patent families for competitive and white-space signal — assignee concentration (HHI, CR4), filing velocity by priority year, CPC/IPC density and the sparse classes next to the dense ones — and reports who owns the area, whether filing is accelerating and where the gaps sit. Use w

• red-team-claim

  Attacks a headline claim the way a hostile reviewer would, along seven named vectors — definition, baseline, selection, counter-example, mechanism, base rate, incentive — then returns a survival score, a verdict of ship, hedge, rewrite or retract, and the hedged wording to publish. Use before a conc

• reference-class-forecasting

  Sanity-checks an inside-view estimate (schedule, cost, adoption, revenue) against the outside view — the outcome distribution of a reference class of similar past cases (Kahneman & Tversky; Flyvbjerg's reference class forecasting) — and computes the base rate, the estimate's percentile in the class

• scenario-planning

  Builds a small set of divergent, equally plausible futures on the two most consequential uncertainties — the Shell/GBN 2×2 scenario method — and stress-tests a strategy against every one of them, ending with robust moves and signposts to watch. Use when the horizon is 3–10 years and a single forecas

• score-technology-readiness

  Scores how mature a specific technology is on the NASA Technology Readiness Level scale (TRL 1–9, read through a software/AI evidence checklist) and reports the highest level the evidence defends, the gap to any vendor claim, and the single piece of evidence needed to advance one level. Use when ask

• sift-source-check

  Runs the SIFT moves (Caulfield, 2019) — Stop, Investigate the source, Find better coverage, Trace claims to the original context — by lateral reading, leaving the page to see what the wider web says about an unfamiliar site or a viral claim, and returns a verdict of trusted, usable with caveat, unco

• smiles-sanity-check

  Checks a SMILES string token by token against the SMILES grammar — balanced brackets, atom symbols on the organic subset or a bracketed element, legal bond tokens, paired ring-closure digits, bond-order sums within normal valence — and returns a per-check VALID/INVALID verdict so copy-paste corrupti

• steelman-argument

  Reconstructs an opposing argument at its strongest, in its proponents' own terms and to the standard they would endorse, then names where even that version is exposed — so any rebuttal lands on the real position rather than a caricature. Use before refuting or dismissing a view: \"steelman this argu

• steep-pestle-analysis

  Sweeps the macro-environment around a decision with the STEEP / PESTLE category checklist (Aguilar's ETPS, 1967) — Social, Technological, Economic, Environmental, Political, plus Legal and Ethical — and delivers a rated driver inventory: every factor evidenced, scored for impact and uncertainty, sor

• systematic-review

  Runs a reproducible literature review to PRISMA 2020 — a pre-registered protocol, an exhaustive documented search, dual title/abstract screening with an agreement statistic, full-text eligibility with logged exclusion reasons, per-study grading and a synthesis — and delivers the PRISMA flow counts p

• test-significance

  Decides whether a reported gap between two groups is a real difference or sampling noise, and reports the p-value, the 95 % confidence interval on the difference and an effect size rather than a bare verdict. Use when a claim rests on a comparison — \"Model A scored 87% vs Model B's 85%\", \"the new

• three-horizons

  Tags every bet in a portfolio with a growth horizon — H1 defend-and-extend the core, H2 build emerging businesses, H3 create options for the future — and holds each to the evidence bar its horizon deserves, exposing a portfolio starved at one horizon. Use when several investments are proposed togeth

• trend-analysis

  Turns a trend claim into an evidence-checked trend statement, quantifies its rate, curvature and S-curve position from a time series, then projects it — naive extrapolation, logistic fit, or event-adjusted Trend Impact Analysis (Gordon) — with an assumption sheet, counter-trend scan and signposts. U

• triangulate-sources

  Establishes one claim by independent corroboration — gathering candidate sources, grading each, collapsing those that share an author, a first-hand root document, a publication event or an incentive structure, and reporting whether at least two genuinely independent sources agree. Use when one sourc

• value-intellectual-property

  Values an early-stage patent, software right, know-how bundle or other IP asset with an explicit valuation purpose, base date and evidence set; selects cost, market, income/DCF, probability-adjusted NPV or real-options framing; and returns a defensible range with sensitivities instead of a false-pre

• verify-citations

  Validates every scholarly identifier in a reference list — DOI, arXiv, ISBN, PMID, PMCID, ORCID, URL — against its canonical format and check digit, then reports PASS / REVIEW / FAIL per citation. Use when a draft's references need checking before it ships, or on requests like \"are these citations

• wardley-map-drafting

  Draws a Wardley map — anchor on the user need, chain the components that deliver it by visibility, plot each on the evolution axis from genesis to commodity, then read the map for build, buy and consume-as-utility calls. Use when a strategy argument needs a picture of the whole dependency chain — \"

• write-imrad-report

  Structures an empirical report in the IMRAD convention — Introduction, Methods, Results, Discussion — with an optional executive summary above and a numbered reference list below, so a reader can audit the methods and results before meeting the interpretation. Use when findings will face reviewers o

• write-sbar-brief

  Structures a one-page decision briefing as SBAR — Situation, Background, Assessment, Recommendation — with a hard length cap per section and a single named action, so a decision-maker gets the whole picture and the ask on one page. Use when someone asks for a short briefing rather than a report: \"g

Similar plugins