scdenney/open-science-skills

qualtrics-ops

Operate a live Qualtrics survey via the v3 APIs without breaking fielding. Publish gating, quotas, flow routing, embedded data, panel-vendor redirects, and read-back verification.

doc-to-markdown

Read or convert any document a research workflow hands you — PDF, Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, or CSV. Use whenever a document has to be read, opened, quoted, summarized, searched, extracted, or added to a source library. Decides whether…

qualtrics-ops

Operate a live Qualtrics survey via the v3 APIs without breaking fielding. Publish gating, quotas, flow routing, embedded data, panel-vendor redirects, and read-back verification.

survey-data-audit

Audit fielded survey response data for registered elements, data quality, bot and AI-automation screening, and sample integrity. Emits an appendix-ready quality report.

survey-flow-audit

Pre-fielding audit of a live survey over the platform API, with an optional browser walk. Consent-before-anything gates, publish state, force-response completeness, quotas, vendor redirects, anti-bot instrumentation, language-arm symmetry.

doc-to-markdown

Read or convert any document a research workflow hands you — PDF, Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, or CSV. Fires whenever a document has to be read, opened, quoted, summarized, searched, extracted, or added to a source library, including…

research-repo

Scaffold or audit an entire research project repository organized around its source library. Use whenever the user is starting, structuring, organizing, or reviewing a whole project — "set up a research repo", "how should I structure/organize this project",…

survey-data-audit

Audit fielded survey response data for registered elements, data quality, bot and AI-automation screening, and sample integrity. Emits an appendix-ready quality report.

survey-flow-audit

Pre-fielding audit of a live survey over the platform API, with an optional browser walk. Consent-before-anything gates, publish state, force-response completeness, quotas, vendor redirects, anti-bot instrumentation, language-arm symmetry.

advisor

Consult Fable 5 as an independent second reviewer, always at max reasoning effort. The calling session is the main model — Opus 5 or Sonnet 5 — and Fable holds the advisor seat. Use before committing to an interpretation or a substantial piece of…

fable-orchestrate

Run a multi-model orchestration workflow led by Fable 5, the strongest model on the team. Use when the session is already running on Fable 5 — its sibling opus-orchestrate is the one to use when the session is on Opus 5. The Fable lead does the hard reasoning…

opus-orchestrate

Run a multi-model orchestration workflow with Claude Opus 5 as the lead, at medium reasoning effort by default. Use when the session is already running on Opus 5 — its sibling fable-orchestrate is the one to use when the session is on Fable 5. The lead is…

spawn

Spawn full peer Codex or Claude sessions in their own panes and git worktrees — real sessions, not subagents — briefed by the lead and merged back. Not for bounded consults a subagent covers. Use when work must outlive or run beside this session, needs its…

spawn

Spawn full Claude Code peer sessions in their own terminal panes and git worktrees — real sessions, not subagents — each on a directed task with a contract brief, monitored and merged back by the spawning lead. Detects the environment and takes the strongest…

model-committee

Run one consequential, contestable decision through a deliberative committee of GPT-5.6 and Claude Opus 5, chaired by opus (default), fable, or sol. Not for factual lookups, brainstorming, routine implementation, independent-coder reliability, or final…

research-repo

Scaffold or audit an entire research project repository organized around its source library. Use when starting, structuring, organizing, or reviewing a research repo. Build sources/{og,md,unprocessed}, references.bib, a PDF-to-Markdown converter, a repo-local…

text-classification

Design and validate LLM-based text classification. Use for codebooks, prompts, validation samples, agreement statistics, and reporting model-coded data.

vlm-ocr-pipeline

Design VLM-based OCR pipelines. Use for model selection, prompting, architecture, multilingual documents, structured output, and evaluation planning.

list-experiment

Design and diagnose list experiments (item count technique).

fact-check

Fact-check manuscript claims against cited sources in a per-source Markdown knowledge base. Use to audit claim support, overclaiming, direction, scope, and misattribution after source intake is complete.

46-orchestrate

Orchestrate complex work as the Codex lead, with a gpt-5.6-sol lead at xhigh effort owning decomposition, integration, and verification while delegating bounded work to cheaper GPT-5.6 tiers and a cross-vendor Claude peer. Not for routine single-context work.…

advisor

Consult an independent, read-only GPT-5.6 advisor before committing to a substantive interpretation, approach, or final result. Not for routine work, implementation, or file edits. Always gpt-5.6-sol at xhigh effort, the flagship tier at its strongest routine…

conjoint-design

Design conjoint experiments covering attributes, power, and AMCE/AMIE estimation. Use for conjoint design choices, attribute tables, estimands, and power planning.

conjoint-diagnostics

Diagnose conjoint design integrity, estimation choices, and validity.

cross-national-design

Design cross-national survey experiments covering power, equivalence, and localization. Use for multi-country sampling, measurement comparability, and instrument adaptation.

diverge-codex

Delegate creative divergence to a fresh Codex subagent before implementation. Use when the user explicitly asks Codex to delegate brainstorming, obtain an independent Codex context, or keep implementation separate from approach generation. Generate 3–5…

diverge

Before implementing, generate 3-5 conceptually distinct approaches labeled by creativity dimension (Novel, Surprising, Diverse, Conventional), then hold for selection. Brainstorm-then-select to resist defaulting to the most obvious solution.

hypothesis-building

Build falsifiable causal hypotheses. Use for DAGs, FPCI, equivalence testing, mechanism specification, and deriving testable predictions from theory.

journal-review

Draft a senior peer-review report on a social-science manuscript.

llm-calibration-logprobs

Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.

methods-reporting

Check methods reporting against CONSORT, JARS, DA-RT standards.

model-council-voting

LLM council/panel voting — multi-model coders, consensus rules, inter-rater agreement (kappa, alpha), correlated-error diagnostics.

narrative-building

Draft or audit scientific introductions. Use for argument logic, framing, contribution structure, and coherence across multiple studies or experiments.

paper-review-lite-codex

Run a cross-model adversarial pre-submission audit from Codex. Use when a user explicitly requests the heavier paper-review-lite-codex workflow, independent Codex and Claude review passes, or cross-model verification of a manuscript. Apply the…

paper-review-lite

Run a pre-submission manuscript audit covering argument, numerics, references, writing, figures, methods, preregistration, and replication readiness.

paper-tex

Typeset a working paper or journal submission in house-style LaTeX from Markdown, Word, TeX, ODT, RTF, or HTML. Use to convert drafts, build PDFs, or prepare journal-specific spacing, limits, anonymization, disclosures, and citations.

post-ocr-cleanup

Clean post-OCR research text. Use for correction, quality assurance, multilingual handling, uncertainty preservation, and provenance-aware cleanup.

research-wayfinder

Plan a research project as a durable decision map, resolving one design decision per session until the destination is a defensible, pre-registerable design. Not for executing analyses or writing the paper. Use at the start of a project, when a design has more…

vlm-ocr-evaluation

Compare OCR systems before a bulk run: candidate set, stratified ground truth, CER/WER, normalization, per-language and per-stratum accuracy.

model-committee

Runs a deliberative two-model committee — GPT-5.6 Sol and Claude Opus 5 as members, under a selectable chair. Chair defaults to Claude Opus 5; `/model-committee-fable` chairs with Fable 5, and `/model-committee-sol` chairs with GPT-5.6 Sol via Codex, which…