matthewdigiuseppe

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Updates MStack — git pull plus setup for clone installs, or points marketplace installs at /plugin marketplace update. User-invoked only.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Reads the paper folder's .mstack/ memory and pipeline outputs and reports where the project stands — stage, artifacts present or missing, stale verdicts, and the single recommended next MStack skill. Use when the user asks where they left off, what's next, or for a status check — and at the start of a session on an…

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Computes target N and minimum detectable effect in R, defaulting to DeclareDesign simulation with a sensitivity curve. Use after a design is chosen and before fielding or preregistration, or whenever the user asks about sample size, statistical power, or MDE.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Drafts a complete OSF/AsPredicted preregistration — hypotheses, sample, exclusions with thresholds, measures, the exact primary specification, robustness, deviations policy — and refuses to mark it ready until every field is specific. Use before fielding or before touching a fresh sample, or when the user mentions…

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Builds the response-to-reviewers document — every comment quoted verbatim, answered, and mapped to a located manuscript change, plus an editor summary and change log. Use when the user has a revise-and-resubmit decision letter or referee reports to answer.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Writes a mock R1 referee report (methodologist, theorist, area-expert, or editor persona) calibrated to the target journal — summary, major and minor comments, and an honest recommendation. Use when a draft is near submission-ready or the user asks how reviewers will react.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Interrogates a candidate research idea with six forcing questions — contribution, audience, identification, falsifiability, feasibility, scoop risk — and issues a green/yellow/red verdict. Use when the user pitches a new paper idea, asks whether a project is worth pursuing, or wants to pressure-test a research…

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Staff-statistician audit of the full analysis — sample-size consistency across tables, spec-vs-prereg match, clustering, multiple comparisons, forking-paths exposure, end-to-end reproducibility. Use after /mstack:analyze and before drafting results, or whenever the user asks to check the analysis or the numbers look…

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Structured paper retrospective — timeline reconstruction plus five questions on where time went, unforced errors, surprises, wins, and the one systematizable lesson. Use after acceptance, rejection, or a major R&R round, or when the user wants to debrief a finished project.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Stress-tests the headline result across alternative samples, operationalizations, fixed effects, clustering, and functional forms, rendering a robustness table and specification curve with a stable/sensitive/fragile verdict. Use after the primary table is locked, or when the user asks for robustness checks or worries…

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Adversarial scope check — is this a paper, a footnote, or three papers? Four challenges force the contribution into one sentence and one table. Use when a project is sprawling, sections keep multiplying, the user cannot name the headline result, or they ask whether to split a paper.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Prepares the actual submission bundle — anonymization sweep for double-blind review (self-citations, acknowledgments, metadata), word-count and formatting checks against the target journal's limits, title-page separation, and a final checklist. Use when the user is about to submit or asks to anonymize or format the…

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Designs a Qualtrics survey instrument — blocks, question table, randomization, embedded data — with layered AI-agent/bot defenses and a probe manifest baked in. Use whenever the user is designing or programming a survey, survey experiment, or panel study, even if they do not mention bot protection.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Builds the causal mechanism (X causes Y because Z), an ASCII DAG with signed edges, scope conditions, and out-of-sample predictions. Use after the lit map, when the user asks to formalize a theory or mechanism, sketch a DAG, or derive predictions — and before hypotheses are operationalized.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Generates 8-12 title candidates across forms (declarative, question, colon, anomaly, mechanism), scores them on hook x precision x searchability, and pairs the winner with the abstract framing. Use late in writing when the user asks for title ideas or a better title.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Clears the /mstack:freeze write lock; careful mode, if on, stays on.

matthewdigiuseppe/MStack

Skill Claude CodeCodex

Publication-quality ggplot figures — one claim per figure, claim-stating titles, colorblind-safe palette, PDF+PNG+underlying CSV — via a bundled theme. Use when the user asks for figures, plots, coefficient or marginal-effects charts, or slide-ready graphics from results.