菜单
这个仓库中的 skills
SkillsMP 已收集 radarist/structured-analytic-skills 中的 70 个 Skill。打开任一 Skill 可查看来源和详情。
radarist/structured-analytic-skills已展示 30 / 70 个已收集 Skill。
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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 /…
原文语言：英语
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.…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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,…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语
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…
原文语言：英语