alterlab-ssci-reflexivity-gate
From the author
Gates trustworthiness before qualitative or interpretivist claims are written — the qualitative analog of the measurement gate. Checks that researcher positionality and role are stated, that the four Lincoln & Guba trustworthiness criteria are addressed (credibility via triangulation / member-checking / prolonged engagement, transferability via thick description, dependability via an audit trail, confirmability via reflexive bracketing), and that reflexivity is evidenced rather than asserted. Fail-closed: interpretivist generalizing or causal language is refused without the corresponding warrant. Use when a study is qualitative / ethnographic / interpretivist, when reviewing trustworthiness or reflexivity, or before writing up thematic or grounded-theory findings. For quantitative measurement validity prefer alterlab-ssci-measurement-gate; for running the coding prefer alterlab-qualitative-analysis; for the final claim audit prefer alterlab-ssci-inference-gate. Part of the AlterLab Academic Skills suite.
Install
npx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-ssci-reflexivity-gate -a claude-code
Installs to .claude/skills/alterlab-ssci-reflexivity-gate/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 77
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- alterlab-ssci-inference-gateAlterLab-IEU/AlterLab-Academic-SkillsAudits final inferential claims against the design, sample, and uncertainty before they are written or published — refuses causal language unless the design's identifying assumption is defended (else downgrades to associational), corrects p-value and confidence-interval misreadings (a p-value is not the probability the null is true, non-significance is not proof of no effect, a 95% CI is not a 95% probability the parameter is inside it), demands effect sizes with intervals rather than significance stars, flags uncorrected multiple comparisons and optional stopping / HARKing, and scopes generalization to the sampling frame. Use when writing or checking a results or discussion section, interpreting a p-value or confidence interval, or deciding whether a finding supports a causal or population claim. For choosing the statistical test prefer alterlab-test-selection-guard; to execute the analysis prefer alterlab-statistical-analysis. Part of the AlterLab Academic Skills suite.Testing★ 78
- alterlab-ssci-measurement-gateAlterLab-IEU/AlterLab-Academic-SkillsGates measurement quality before a scale or instrument is trusted — checks that each construct is defined and operationalized, that reliability is evidenced with McDonald omega (not Cronbach alpha alone, which assumes tau-equivalence and is only a lower bound), that reliability is not confused with validity (content, criterion, convergent/discriminant construct validity), and that measurement invariance is tested before comparing groups. Use when asking whether a scale or survey instrument is valid, reporting a Cronbach alpha, building or adopting a multi-item measure, or comparing a latent construct across groups. For designing the questionnaire items prefer alterlab-survey-design; for running the confirmatory factor analysis prefer alterlab-sem-psychometrics; to execute basic statistics prefer alterlab-statistical-analysis. Part of the AlterLab Academic Skills suite.Design★ 78
- alterlab-ssci-sampling-gateAlterLab-IEU/AlterLab-Academic-SkillsGates who is sampled, how, and how many before data collection — checks that the sampling FRAME matches the target population (coverage error), that the METHOD is named (probability vs non-probability: simple random, stratified, cluster, systematic, quota, convenience, snowball), that sample SIZE follows the inference paradigm (an a-priori power analysis for hypothesis tests, a precision/margin-of-error target for estimation, or saturation/information power for qualitative studies — never a rule of thumb or collect-until-significant), and that the generalization claim matches the sample (statistical generalization only from probability samples). Use when asking how many participants are needed, planning recruitment, running or checking a power analysis, or judging whether a sample supports a population claim. For questionnaire items prefer alterlab-survey-design; for choosing the statistical test prefer alterlab-test-selection-guard. Part of the AlterLab Academic Skills suite.Testing★ 78
- alterlab-qualitative-analysisAlterLab-IEU/AlterLab-Academic-SkillsAnalyzes qualitative data as a dispatched pipeline module — codebook development, thematic / framework / content analysis, and inter-coder reliability computed correctly (Krippendorff's alpha as primary via the krippendorff package or a bundled stdlib nominal calculator with bootstrap CIs; Cohen's / Fleiss' kappa via statsmodels) with 95% CIs and thresholds (alpha >= .80 reliable, .667-.80 tentative). It BRANCHES by design: coefficient-based ICR for codebook / content-analytic coding, versus consensus-and-reflexivity for reflexive thematic analysis where a statistic is not the right criterion. Supports human-vs-LLM double-coding with an alpha check against a human gold standard. Use when coding interviews or open-ended text, building a codebook, or reporting intercoder reliability. For topic modeling / embeddings / supervised text classification prefer alterlab-text-as-data; for the reflexivity gate prefer alterlab-ssci-reflexivity-gate. Part of the AlterLab Academic Skills suite.Design★ 78
- alterlab-ssci-design-gateAlterLab-IEU/AlterLab-Academic-SkillsRoutes a social-science study to its research design — true experiment, quasi-experiment (difference-in-differences, instrumental variables, regression discontinuity, interrupted time series, fixed effects), observational/correlational, qualitative, or mixed — by walking the random-selection and random-assignment decisions, then PINS the identifying assumption the causal claim will rest on (parallel trends, exclusion restriction, continuity at the cutoff, selection-on-observables, or qualitative saturation logic) before any analysis begins. Use when choosing a study design, asking what design to use, framing a causal question from observational data, or deciding experiment vs quasi-experiment vs observational. For executing the analysis prefer alterlab-statistical-analysis; for qualitative design depth prefer alterlab-qualitative-methods; for choosing the statistical test downstream prefer alterlab-test-selection-guard. Part of the AlterLab Academic Skills suite.Design★ 78
- alterlab-scientific-thinkingAlterLab-IEU/AlterLab-Academic-SkillsEvaluate scientific claims and evidence quality using evidence grading frameworks (GRADE, Cochrane risk-of-bias tools such as RoB 2 and ROBINS-I), assessing experimental design validity and identifying biases, confounders, statistical pitfalls, and logical fallacies. Use when judging evidence quality, grading certainty of evidence, spotting design or causal-inference flaws, identifying biases or confounders, naming statistical fallacies, or teaching critical analysis. For writing a formal submittable peer review use alterlab-peer-review; for a multi-reviewer mock panel verdict use alterlab-paper-reviewer; for IRB/consent/conflict-of-interest ethics use alterlab-research-ethics. Part of the AlterLab Academic Skills suite.Science★ 78
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in