Research Skills

Evaluate scientific claims and evidence quality using evidence grading frameworks (GRADE, Cochrane Risk of Bias), 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.

Run AI web searches with real-time, citation-grounded answers using Perplexity Sonar models (sonar, sonar-pro, sonar-pro-search agentic search, sonar-reasoning, sonar-reasoning-pro) via LiteLLM and a single OpenRouter API key. Use when searching for current information or recent scientific literature, getting answers grounded in cited web sources, verifying a claim against current evidence, or reaching information beyond the model's training cutoff. Requires an OpenRouter API key. This is the direct single-backend Perplexity tool: for automatic routing between Perplexity and other backends use alterlab-research-lookup, and for structured per-paper experimental-data extraction (sample sizes, effect sizes, quality scores) use alterlab-bgpt-search. Part of the AlterLab Academic Skills suite.

Look up current research and scholarly papers by auto-routing each query to the best backend — the Parallel Web Systems Chat API (general research) or Perplexity sonar-pro-search (academic paper searches) — and save every result with citations to sources/. Use when finding papers, gathering research data, verifying scientific claims, or assembling citation lists and unsure which search backend fits. For plain general web search or extracting content from a known URL prefer alterlab-parallel-web instead (requires PARALLEL_API_KEY and OPENROUTER_API_KEY). Part of the AlterLab Academic Skills suite.

Estimates causal effects from observational and quasi-experimental data — difference-in-differences, instrumental variables, regression discontinuity, panel fixed effects, propensity-score / doubly-robust methods, and heterogeneous treatment effects (CATE) — using the verified Python stack: statsmodels and linearmodels (PanelOLS, IV2SLS), pyfixest (feols, event studies, Sun-Abraham, did2s), DoWhy (identify -> estimate -> refute), EconML (LinearDML, CausalForestDML, DRLearner), and rdrobust for RD. It names the identifying assumption before estimating and runs a refutation/robustness check after. Use when the request mentions difference-in-differences, instrumental variables, regression discontinuity, fixed effects / panel causal estimation, propensity scores, or treatment-effect estimation from non-randomized data. For choosing the design first prefer alterlab-ssci-design-gate; for plain regression or descriptive stats prefer alterlab-statistical-analysis. Part of the AlterLab Academic Skills suite.

Comprehensive survey and instrument design assistant supporting questionnaire construction, Likert scale design, question types (open/closed/matrix), response bias mitigation, sampling strategies (probability/non-probability), pilot testing, instrument validation (Cronbach's alpha, factor analysis), online survey tools (Qualtrics, REDCap, Google Forms), interview protocol development, focus group facilitation, mixed-mode surveys, and cultural adaptation of instruments. Use when designing a survey or questionnaire, building Likert scales, planning a sampling strategy, pilot testing, validating an instrument (Cronbach's alpha, factor analysis), developing an interview protocol, improving response rates, or working in Qualtrics or REDCap. For analyzing interview/focus-group data use alterlab-qualitative-methods; for qual+quant integration alterlab-mixed-methods; for test selection/power analysis alterlab-statistical-analysis; for IRB/consent alterlab-research-ethics. Part of the AlterLab Academic Skills suite.

Builds agent-based models of social systems with Mesa 3 — the current AgentSet API (model.agents.shuffle_do('step'), auto-assigned unique_id, mandatory super().__init__(seed=...)), cell spaces (mesa.discrete_space OrthogonalMooreGrid / classic mesa.space grids), the DataCollector, batch_run parameter sweeps, and SolaraViz — for emergence, segregation, diffusion, opinion dynamics, and cooperation models. It uses the Mesa 3.x API (the old mesa.time schedulers like RandomActivation are removed) and treats the model as a generative theory to be validated, not just run. Use when the request mentions an agent-based model, Mesa, simulating interacting agents, or emergent macro behavior from micro rules. For discrete-event (queueing/process) simulation prefer alterlab-simpy; for reinforcement learning prefer alterlab-stable-baselines3. Part of the AlterLab Academic Skills suite.

Fits and reports mixed-effects / multilevel / hierarchical models for clustered, nested, longitudinal, and repeated-measures data — random intercepts and slopes, variance components and the ICC, cross-level interactions, and GLMMs (logistic/Poisson) — using statsmodels MixedLM and bambi (Bayesian on PyMC) in Python, or the field-standard R lme4 / glmmTMB / brms via Rscript. It enforces the reporting items reviews find under-reported: full fixed + random specification, centering, variance components + ICC, estimation method, assumption checks, model comparisons, and effect sizes. Use when data are grouped/nested (students in schools, repeated measures, panel/longitudinal) and the question concerns within- vs between-cluster variation. For general single-level regression prefer alterlab-statsmodels; for panel fixed effects used for causal identification prefer alterlab-causal-inference. Part of the AlterLab Academic Skills suite.

Runs quantitative meta-analysis — computes effect sizes (Hedges' g / standardized mean difference, log odds/risk ratios) with their variances, pools them under fixed-effect and random-effects models, quantifies heterogeneity (I-squared, tau-squared, Cochran's Q), draws forest and funnel plots, and tests publication bias (Egger's regression, trim-and-fill) — using statsmodels.stats.meta_analysis in Python or the field-standard R metafor via Rscript. It enforces PRISMA reporting and the random- vs fixed-effect decision. Use when pooling effect sizes across studies, running a systematic review's quantitative synthesis, or assessing heterogeneity and publication bias. For finding and screening the literature prefer alterlab-deep-research; for a single study's statistics prefer alterlab-statistical-analysis. Part of the AlterLab Academic Skills suite.

Handles missing data with principled methods — forces an explicit MCAR / MAR / MNAR mechanism statement, then applies multiple imputation by chained equations (MICE) with Rubin's-rules pooling of estimates and standard errors, or full-information maximum likelihood (FIML) where a likelihood/SEM model applies. Uses statsmodels MICE / MICEData in Python or the field-standard R mice via Rscript, and warns that single (mean/regression) imputation and scikit-learn's IterativeImputer return one completed dataset without Rubin's-rules pooling, so they understate standard errors if used as multiple imputation. Use when a dataset has missing values, when choosing an imputation strategy, or when reporting how missingness was handled. For general modeling on complete data prefer alterlab-statistical-analysis; for latent-variable models with FIML prefer alterlab-sem-psychometrics. Part of the AlterLab Academic Skills suite.

Runs Qualitative Comparative Analysis — crisp-set (csQCA), multi-value (mvQCA), and fuzzy-set (fsQCA) — for small-to-medium-N configurational research: calibrating raw data into set membership, building and refining a truth table, and Boolean minimization into conservative / parsimonious / intermediate solutions with consistency and coverage. Because there is no maintained Python QCA library, it shells out to R's QCA package (calibrate, truthTable, minimize) via Rscript and documents that dependency honestly rather than faking a Python API. Use when the request mentions QCA, fsQCA, csQCA, configurational or set-theoretic analysis, necessary/sufficient conditions, truth tables, or calibration of conditions. For net-effect estimation of a single treatment prefer alterlab-causal-inference; for interpretive analysis prefer alterlab-qualitative-methods. Part of the AlterLab Academic Skills suite.

Fits and evaluates measurement models — confirmatory factor analysis, full structural equation models, exploratory factor analysis, item response theory, and multi-group measurement invariance — using the verified Python stack: semopy (model syntax =~ / ~ / ~~, Model.fit, inspect(std_est=True), calc_stats for CFI/TLI/RMSEA), factor_analyzer (EFA, KMO, Bartlett, ConfirmatoryFactorAnalyzer), and pingouin/girth, computing McDonald's omega from standardized loadings and judging fit against Hu & Bentler cutoffs. Use when the request mentions confirmatory factor analysis, structural equation modeling, a latent variable or construct model, factor loadings, IRT, or measurement invariance across groups. For deciding whether a scale is trustworthy at all prefer alterlab-ssci-measurement-gate; for plain regression prefer alterlab-statistical-analysis. Part of the AlterLab Academic Skills suite.

Analyzes 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.

Routes 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.

Audits 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.

Gates 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.

Applies social-network-analysis method discipline to relational data — degree/betweenness/closeness/eigenvector centrality and PageRank, community detection (Louvain and greedy-modularity native in networkx, Leiden via igraph), and inferential network models (ERGM) — choosing the measure that matches the substantive question and the right dependence assumptions, then routing computation to the existing networkx (and igraph/R) tooling. Use when the request mentions social network analysis, centrality, key players/brokerage, community or cluster detection in a network, ERGM, or modeling ties between nodes. For general graph algorithms and plotting prefer alterlab-networkx; for graph neural networks prefer alterlab-torch-geometric. Part of the AlterLab Academic Skills suite.

Coordinates a social-science study through the stage-gated methods pipeline — question then design-gate then measurement-gate then sampling-gate then the right analysis module then inference-gate then reporting — holding a single YAML Design Passport that each gate reads and appends, and enforcing gate order with PASS / WARN / BLOCK semantics (design-gate and inference-gate are fail-closed). It is thin: it routes and holds the artifact, it does not run analysis itself. Use when a researcher describes a whole social-science study end to end, asks to run the methods pipeline or a full methodology review, or wants the design-to-inference workflow coordinated rather than a single step. For a single stage trigger that gate directly (alterlab-ssci-design-gate, -measurement-gate, -sampling-gate, -inference-gate); for multi-agent execution mechanics see alterlab-workflow-orchestration. Part of the AlterLab Academic Skills suite.

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.

Analyzes complex-sample survey data with design-based inference — declares a survey design (weights, strata, PSUs/clusters, FPC) before estimating means, totals, proportions, ratios, and quantiles, computes design-adjusted standard errors via Taylor linearization or replicate weights (BRR, Jackknife, Bootstrap), calibrates with post-stratification / raking / GREG, and fits design-adjusted GLMs (linear, logistic, Poisson). Uses samplics (stable Python), the emerging svy successor, or the field-standard R survey + srvyr via Rscript. Use when analyzing GSS/ANES/ESS/DHS/Eurobarometer or any weighted/stratified/clustered survey, when a dataset ships survey weights, or when someone quotes unweighted percentages from a complex survey. For questionnaire and sampling-plan DESIGN prefer alterlab-survey-design; for the sampling-adequacy gate prefer alterlab-ssci-sampling-gate; for causal identification prefer alterlab-causal-inference. Part of the AlterLab Academic Skills suite.

Computes the annual Turkish academic-incentive (akademik teşvik) score for Devlet (state) university öğretim elemanı (academic staff) from a classified activity list, applying the verified Akademik Teşvik Ödeneği Yönetmeliği (2018/11834) Faaliyet Hesaplama Tablosu headline puanları (Proje 20, Araştırma 15, Yayın 30, Patent 30, Atıf 30, Tebliğ 20, Ödül 20) with the k (author-count), p (Q1 1/Q2 0.8/Q3 0.5/Q4 0.25), and r (project-role) coefficients via türü puanı = Σ(faaliyet oranları) × headline (MADDE 8/2), then enforcing the per-type headline ceilings, the 100 cap (MADDE 8/3), and the net-30 payment gate (MADDE 10/3) in a deterministic scripts/tesvik_score.py. Use when the user wants to calculate akademik teşvik puanı, check the en az 30 (net-30) threshold, apply TABLO 4 ceilings, or estimate teşvik eligibility; keeps its coefficients separate from doçentlik scoring. For doçentlik point eligibility prefer alterlab-docentlik-eligibility. Part of the AlterLab Academic Skills suite.

Gates 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.

Runs a PARTIAL pre-screen of a Turkish associate-professorship (doçentlik) publication list against the ÜAK (Üniversitelerarası Kurul) Sağlık Bilimleri TABLO 10 criteria, applying the author-share rule (full; 0.8 + 0.5; lead-author half-the-rest split) and pass-fail checking the four computable minimums (≥100 total, ≥90 post-doctorate, ≥40 SCIE/SSCI article points, ≥3 lead-author Q1–Q4 articles). It deliberately does NOT emit an ELIGIBLE verdict — it lists the unmodelled mandatory minimums (TR Dizin/national article, citation, congress, teaching, per-category caps) for the user to verify. Use when the user wants to estimate doçentlik eligibility, calculate ÜAK points, or audit lead-author (başlıca yazar) requirements; resolve a journal's live TR Dizin status with alterlab-trdizin first, and compute the akademik teşvik (academic-incentive) score with alterlab-akademik-tesvik. Always verify the full live TABLO 10 — criteria change each term and differ per field. Part of the AlterLab Academic Skills suite.

Drives TÜBİTAK Açık Bilim Politikası (Open Science Policy) compliance and deposition into Aperta — TÜBİTAK ULAKBİM's national open archive at aperta.ulakbim.gov.tr — encoding the binding mandates (green-road deposit of the accepted manuscript on acceptance; open access within 6 months for fen/mühendislik (STEM) and 12 months for sosyal/beşeri (SSH); İlke-6 documentation when data must stay closed for KVKK/privacy reasons) and scaffolding a TÜBİTAK Veri Yönetim Planı / VYP (data management plan) at grant-application time. Use when depositing to Aperta, complying with the TÜBİTAK açık bilim policy, preparing a TÜBİTAK data management plan (VYP), reporting open-access compliance in a final report, or documenting a justified data embargo. For Zenodo/Dryad/OSF and international DMPs prefer alterlab-open-science; for the KVKK lawful-basis/anonymisation plan prefer alterlab-kvkk-dmp. Part of the AlterLab Academic Skills suite.

Harvests article metadata, abstracts, and full-text PDFs from DergiPark (TÜBİTAK ULAKBİM's national journal-hosting platform, ~2,537 journals) via its verified platform-wide OAI-PMH endpoint (https://dergipark.org.tr/api/public/oai/; verbs Identify/ListSets/ListRecords/GetRecord; prefixes oai_dc/oai_mods/oai_marc/oai_etdms; setSpec=journal-slug), parses Highwire citation_* and DC.* meta tags on /pub/{slug}/article/{id} pages, pulls PDFs from the citation_pdf_url path, and emits BibTeX/RIS locally. Use when the user wants to harvest a Turkish journal, fetch DergiPark articles, list a journal archive, get BibTeX/RIS for a DergiPark paper, or read a journal aim-and-scope (öz/kapsam). For TR Dizin indexing status use alterlab-trdizin; for YÖK theses use alterlab-yok-tez; for academic profiles use alterlab-yok-akademik. Part of the AlterLab Academic Skills suite.

Produces KVKK-compliant (Law 6698, as amended by Law 7499 — published in the Official Gazette 12 Mar 2024, KVKK provisions effective 1 Jun 2024) data management plans for Turkish research, encoding the açık rıza (explicit consent) default basis, the Art. 28(1)(b) anonymization exemption as the primary compliance lever, the Art. 6 special-category regime for health/genetic/biometric data, Art. 7 deletion/destruction/anonymization at purpose-end, the Art. 13 thirty-day data-subject response window, Art. 9 cross-border adequacy-decision rules for cloud/overseas data, and Art. 16 VERBIS pre-processing registration, with a KVKK-vs-GDPR crosswalk. Use when the user needs a KVKK data management plan, to anonymize a research dataset under Turkish law, a VERBIS check, or to fix EU DMP boilerplate for Turkey; for pure GDPR/HIPAA use alterlab-research-ethics. Part of the AlterLab Academic Skills suite.

Formats manuscripts for Turkish journals: TR Dizin submission rules (TR Dizin mandates a set abstract word limit, two referees from different institutions, Latin script for non-Latin-alphabet articles, and only suggests a second-language abstract; bilingual oz/abstract ~200-250 words and 3-5 keywords are common journal house conventions to confirm against the journal's yazim kurallari) and the Turkish adaptation of APA-7 (ve ark./vd. for multi-author cites, ampersand only in the reference list, s. for page, Cev. for translator, t.y. for no date, aktaran for as-cited-in, Turkish capitalization). Use when writing for a Turkish/Turkce journal, preparing a TR Dizin submission, needing Turkce APA 7 in-text or reference formatting, or formatting a bilingual oz. For English-language citation styles prefer alterlab-citation-mgmt or alterlab-venue-templates; for live TR Dizin index status use alterlab-trdizin. Part of the AlterLab Academic Skills suite.

Scaffolds Turkish human-subjects etik kurul (ethics committee) applications and routes a study to the correct committee using the TR Dizin/ULAKBIM 2020 trigger rule: survey, interview, focus-group, observation, or experiment data collection requires a university Girisimsel Olmayan Etik Kurulu (non-interventional committee); drug, device, cosmetic, stem-cell, or BA-BE clinical studies also require a TITCK-approved Klinik Arastirmalar Etik Kurulu plus a separate TITCK permit. Generates bilingual (TR/EN) Etik Kurul Basvuru Formu, basvuru dilekcesi (cover petition), and Bilgilendirilmis Gonullu Olur Formu (informed consent), and lints a consent draft against the TITCK 2023 minimum-content checklist. Use when the user needs a Turkish etik kurul basvurusu, an onam/olur (consent) formu, asks which ethics committee a study requires, or needs TITCK approval guidance. For non-Turkey IRB/Belmont/GDPR use alterlab-research-ethics; for KVKK data plans use alterlab-kvkk-dmp. Part of the AlterLab Academic Skills suite.

Searches TR Dizin (TÜBİTAK ULAKBİM national citation index) and verifies a journal's current national-index status through its confirmed unauthenticated REST/Elasticsearch API at https://search.trdizin.gov.tr/api/defaultSearch/{publication|journal|author|institution}/ (params q, order e.g. relevance-DESC, page), parsing hits.hits[]._source plus faceted aggregations, and derives indexing status from a journal record's isActive + journalYear coverage vs rejectYearList. Use when the user wants to search TR Dizin, check if a journal is TR Dizin indexed (TR Dizin'de var mı / taranıyor mu), find Turkish-indexed publications, verify national-index status before submitting, or audit doçentlik-eligible venues. For DergiPark hosting prefer alterlab-dergipark; for doçentlik points prefer alterlab-docentlik-eligibility; for teşvik scoring prefer alterlab-akademik-tesvik. Part of the AlterLab Academic Skills suite.

Scaffolds TÜBİTAK ARDEB national research proposals (1001 Bilimsel ve Teknolojik Araştırma Projeleri and 1002-A Hızlı Destek Modülü) against the official .doc form trees: 1. ÖZGÜN DEĞER (konunun önemi/özgün değer, araştırma sorusu/hipotezi, amaç ve hedefler), 2. YÖNTEM, 3. PROJE YÖNETİMİ (iş-zaman çizelgesi/iş paketleri + B-Planı, araştırma olanakları), 4. YAYGIN ETKİ, EK-1 Kaynaklar, EK-2 Bütçe ve Gerekçesi. Enforces the 600-word TR/EN özet (abstract) caps, program caps (1001 <=36 months/3,000,000 TRY for 2026-1; 1002-A <=12 months/150,000 TRY, rolling), and the four panel review dimensions; submission via PBS (ardeb-pbs.tubitak.gov.tr) with ARBİS prerequisite. Delegates generic grant craft to alterlab-research-grants. Use when the user wants to write a TÜBİTAK 1001 or 1002-A proposal, draft özgün değer or yaygın etki sections, scaffold a Turkish national grant, or map broader-impacts framing to TÜBİTAK terms. Part of the AlterLab Academic Skills suite.

Looks up a Turkish academic's official YOKSIS-backed profile, current affiliation, unvan (academic title), publications, research projects, and supervised theses on the YOK Akademik portal (akademik.yok.gov.tr/AkademikArama/), a server-rendered JSP app with no public JSON API, by scraping its verified endpoints (AkademisyenArama POST search, viewAuthor.jsp profile, AkademisyenProjeBilgileri, AkademisyenYonTezBilgileri) keyed by an opaque authorId, with Turkish-character (Iı Şş Ğğ Çç Öö Üü) normalization for name matching. Use when the request is to verify a Turkish academic's current institution, find a researcher on YOK Akademik, confirm affiliation for authorship or a recommendation letter, or list someone's supervised theses or projects. For admission statistics (kontenjan, taban puan) use alterlab-yokatlas; for the national thesis full-text archive use alterlab-yok-tez; for publication metadata enrichment use alterlab-openalex. Part of the AlterLab Academic Skills suite.

Searches YÖK Ulusal Tez Merkezi (tez.yok.gov.tr/UlusalTezMerkezi), Turkey's mandatory national graduate-thesis repository, for literature-review discovery and pre-proposal özgünlük (originality) checks. Drives the detailed search form (Tez Adı/Yazar/Danışman/Konu/Anahtar Kelime/Özet, tez türü, year range, language, İzinli/İzinsiz permission status) via the saidsurucu/yoktez-mcp tool, applies Turkish auto-stemming and ve/veya/içermesin boolean operators, runs paired Turkish+English queries, and emits Türkçe APA-7 thesis citations mapping Tez No to the published Yayın No. Use when the user wants to search Turkish theses, ara YÖK tez, check thesis novelty before approving a proposal, find dissertations by advisor (danışman) or university, dedupe a topic against existing tezler, or cite a YÖK thesis; respects the 2000-results-per-search cap and online-view-only access. For non-thesis Turkish journals use alterlab-dergipark or alterlab-trdizin. Part of the AlterLab Academic Skills suite.

Retrieves Türkiye higher-education program and admission statistics from YÖK Atlas (yokatlas.yok.gov.tr) — quotas (kontenjan), placements (yerleşen), minimum admission scores (taban puan), success ranks (başarı sırası), and per-title academic-staff counts — via the keyless yokatlas-py (>=0.6.0, MIT) wrapper over the JSON API at /api/tercih-kilavuz/ (search, universiteler, universite-programlar), with SearchFilters for puan türü (SAY/SÖZ/EA/DİL/TYT), university type (DEVLET/VAKIF), province, and success-rank ranges. Use when the request mentions YÖK Atlas, program statistics, kontenjan/quota data, taban puan/minimum admission score, başarı sırası/success rank, placement counts, or program staff counts for institutional research, program benchmarking, or student advising. For an academic's CV/profile/affiliation prefer alterlab-yok-akademik; for theses prefer alterlab-yok-tez. Legacy PHP endpoints are dead post-April-2026; only the JSON API is used. Part of the AlterLab Academic Skills suite.

Verify publication figures with a render-then-check QA pass — data-fidelity against every underlying row, axis/label floor-and-ceiling legibility, bounding-box collision detection for overlapping text/markers, and 300-dpi print-readiness. Use when proofing or auditing a finished figure for correctness and print quality, catching mislabeled or overlapping elements, or confirming a plot faithfully represents its data before submission. For CREATING the plot prefer alterlab-matplotlib (or alterlab-seaborn / alterlab-plotly); for multi-panel publication layout prefer alterlab-scientific-viz; for schematic diagrams prefer alterlab-scientific-schematics. Part of the AlterLab Academic Skills suite.

Creates professional infographics with Nano Banana Pro AI and smart iterative refinement, using Gemini 3 Pro for automated quality review and an optional Perplexity Sonar research phase for accurate, sourced data — supports 10 infographic types, 8 industry styles, and colorblind-safe palettes. Use when the request is for an infographic, data-story graphic, statistical poster, comparison chart, timeline, process/how-to visual, or list/social graphic that pairs a designed layout with figures. Use alterlab-scientific-schematics instead for technical flowcharts, CONSORT/PRISMA, pathways, or architecture diagrams; alterlab-generate-image for non-infographic illustrations. Part of the AlterLab Academic Skills suite.

Writes Markdown documents and text-based Mermaid diagrams (flowcharts, sequence, class, ER, gantt, state, and more) with full style guides, 24 diagram-type references, and 9 document templates. Use when authoring a scientific document, report, analysis, or README, or when a diagram should be expressed as version-controllable Mermaid/Markdown text rather than a rendered image. For AI-rendered publication schematics use scientific-schematics instead. Part of the AlterLab Academic Skills suite.

Orchestrates matplotlib, seaborn, and plotly with opinionated publication styles to produce journal-ready figures. Use when preparing journal-submission figures that need multi-panel layouts with bold panel labels, statistical significance annotations, error bars, colorblind-safe palettes (Okabe-Ito), or specific journal formatting (Nature, Science, Cell). Does NOT cover raw low-level plotting or fine-grained control of individual plot elements; for building custom plots from scratch or tuning every artist and rcParam prefer alterlab-matplotlib instead. Part of the AlterLab Academic Skills suite.

Prepares academic career documents and professional-development materials for faculty and researchers. Use when drafting academic CVs, research statements, teaching philosophies, diversity statements, faculty-position cover letters, tenure dossiers, promotion narratives, academic portfolios, or mentorship statements, and when planning conference-networking strategy, building academic web presence, setting up ORCID profiles, or understanding impact metrics. Part of the AlterLab Academic Skills suite.

Formulates structured, testable hypotheses from experimental observations using a scientific-method framework — derives predictions, proposes mechanisms, and designs experiments to test them, then renders a LaTeX report. Use when turning observations or data into falsifiable, mechanistic hypotheses, competing-explanation sets, testable predictions, or experimental designs. For a standalone systematic literature review or evidence synthesis (not a means to hypotheses) use alterlab-literature-review; to evaluate an existing manuscript use alterlab-peer-review. Part of the AlterLab Academic Skills suite.

Creates professional research posters in LaTeX using beamerposter, tikzposter, or baposter — handles layout design, color schemes, multi-column formats, figure integration, and poster-specific visual-communication best practices. Use when building a conference or academic poster in LaTeX. For PowerPoint/PPTX poster output prefer pptx-posters instead. Part of the AlterLab Academic Skills suite.

Manages citations for academic research — searches Google Scholar and PubMed for papers, extracts accurate metadata, validates citations, and generates properly formatted BibTeX entries. Use when finding papers, verifying citation information, converting DOIs to BibTeX, checking reference accuracy in scientific writing, or building a bibliography. Part of the AlterLab Academic Skills suite.

Conducts comprehensive, systematic literature reviews across multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar), with PRISMA flow tracking, study screening (title/abstract and full-text), evidence-table extraction, and risk-of-bias assessment, producing professionally formatted markdown documents and PDFs with verified citations in multiple styles (APA, Nature, Vancouver). Use when running a systematic literature review, meta-analysis, research synthesis, or broad literature search, building a PRISMA flow diagram, screening studies, extracting an evidence table, or assessing risk-of-bias across biomedical, scientific, and technical domains. Part of the AlterLab Academic Skills suite.

Converts academic papers into promotional and presentation formats — interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster) from LaTeX or PDF sources. Use when disseminating a paper, preparing for a conference, building an explorable academic homepage, generating a video abstract, or producing a print-ready poster from a paper. Part of the AlterLab Academic Skills suite.

Writes structured, checklist-based manuscript and grant peer reviews — assesses methodology, statistical validity, reporting-standards compliance (CONSORT/STROBE/PRISMA), and gives constructive feedback. Use when writing a formal reviewer report, responding to a journal/grant review invitation, or revising a manuscript against reviewer criteria. For evaluating claims/evidence quality prefer alterlab-scientific-thinking; for a multi-reviewer mock-panel verdict use alterlab-paper-reviewer; for quantitative rubric scoring use alterlab-scholar-eval. Part of the AlterLab Academic Skills suite.

Writes competitive research grant proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC — applies agency-specific formatting and review criteria, prepares budgets, and drafts broader-impacts, significance statements, and innovation narratives that comply with submission requirements. Use when drafting or revising a grant proposal, aligning a proposal to a funding agency's review criteria, or preparing grant budgets and compliance sections. For Turkey's TÜBİTAK 1001/1002-A national proposals use alterlab-tubitak-proposal; to write a reviewer's critique of someone else's proposal use alterlab-peer-review; for a journal manuscript use alterlab-scientific-writing. Part of the AlterLab Academic Skills suite.

Evaluates scholarly work with the ScholarEval framework, producing structured assessment across research-quality dimensions (problem formulation, methodology, analysis, and writing) with quantitative rubric scores and actionable feedback. Use when scoring or grading a paper, thesis, or research output against rubric-style criteria, or benchmarking publication readiness across revisions. For checklist-based narrative reviewer reports prefer alterlab-peer-review; for evidence/claim quality and argument soundness use alterlab-scientific-thinking. Part of the AlterLab Academic Skills suite.

Builds slide decks for research talks in PowerPoint and LaTeX Beamer, providing slide structure, design templates, timing guidance, and visual validation. Use when making conference presentations, seminar talks, research presentations, thesis-defense slides, or any scientific talk deck. Part of the AlterLab Academic Skills suite.

Writes scientific manuscripts in full flowing paragraphs (never bullet points) via a two-stage process — section outlines with key points using research-lookup, then conversion to prose — applying IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, and reporting guidelines (CONSORT/STROBE/PRISMA). Use when drafting or revising research papers, journal submissions, or any manuscript section (abstract, introduction, methods, results, discussion), or professional/technical reports. For a specific venue's LaTeX template and house style use alterlab-venue-templates; to build a BibTeX bibliography or verify reference metadata use alterlab-citation-mgmt. Part of the AlterLab Academic Skills suite.

Use when grading, reviewing, rewriting, or approving a Hermes Agent SOUL.md. Uses the SOUL.md field-guide research artifacts as the only normative source for what makes a good SOUL.md.