테스트·보안 스킬

Audits fielded survey-response data for registered elements, data quality, bot and AI-automation screening, and sample integrity, and produces an appendix-ready quality report. Use at soft launch before full field, after fielding before outcomes are analyzed, or when asked what a study did about bots and AI respondents.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OCRs scanned or image-only corpora with vision-language models in four phases. Triage inventories the scans, identifies script and language, and shortlists models by script, hardware, and data constraints. Evaluate selects a system by measured CER or WER against ground truth, using born-digital twins, a second reader, and decision rules set in advance. Run builds the production pipeline. Clean removes model artifacts, audits what every cleaning rule deletes, corrects with rule-based and LLM passes, and records provenance. Use when choosing an OCR model for a corpus, measuring OCR accuracy, transcribing scans at scale, or correcting raw OCR. Born-digital documents with text layers go to doc-to-markdown; runs on Leiden's ALICE cluster add vlm-ocr-alice.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Writes or reviews a pre-analysis plan before data collection — registry choice (OSF, AEA RCT Registry, AsPredicted, registered reports), PAP structure, models and decision rules locked in advance, analysis code run on simulated data, contingencies for attrition, failed manipulations, and exclusions, deviation records, and timeline. Operationalizes the pre-data-collection side of DA-RT. Use when the user asks to draft or audit a pre-registration or PAP, choose a registry, decide what to lock versus leave exploratory, or handle a later deviation. Hypotheses and estimands come from hypothesis-building, post-hoc reporting from methods-reporting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Designs publication tables for social-science manuscripts. Covers whether a result belongs in a table at all, column order, row grouping and panels, decimal precision, standard-error and confidence-interval conventions, self-contained titles and notes, and code-generated output. Use when building or revising a regression, balance, descriptive, or robustness table, or when working with modelsummary, stargazer, gt, esttab, or booktabs. Finished tables go to figure-table-audit for end-stage QA.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Scaffolds or audits a social-science replication package and evaluates the manuscript and archived research objects against FAIR principles. Scaffold mode writes the folder structure, README, master.R, figure-table crosswalk, codebook, LICENSE placeholder, and .gitignore; audit mode grades the package against a pre-release checklist and audits data, code, materials, identifiers, licenses, access restrictions, and availability statements. Use when setting up or repairing a package, checking one before submission, auditing FAIR compliance, or drafting availability statements. Adapted from Yusaku Horiuchi’s replication-package-guide.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Operates or audits a live Qualtrics survey through the v3 APIs without disrupting fielding. Covers publish gating, quotas, flow routing, embedded data, panel-vendor redirects, read-back verification, and a read-only pre-fielding audit. Use when publishing or patching a fielding instrument, when a quota counts without blocking, when configuring panel-vendor redirects or flow gates, or when auditing a survey before launch for consent gates, force-response completeness, quotas and redirects, anti-bot instrumentation, and language-arm symmetry.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Drafts or audits a scientific paper’s introduction and framing — the real-world "why", an evidence audit, the funnel from theory to a falsifiable if-then with a named estimand, bridges across experiments, and a contribution list matched to the design. Use when the user asks to write, restructure, or critique an introduction, motivate or frame a paper, repair a gap-in-the-literature opening, sharpen or calibrate a contribution claim, or connect experiments into one argument. Sentence-level flow and wording are out of scope.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Designs and diagnoses list experiments (the item count technique), covering whether indirect measurement is warranted, control-list construction against floor and ceiling effects, design variants, estimators and assumption tests in the list package, and power planning for the precision penalty. Use when the user measures a sensitive attitude or behavior and asks about list experiments, item count, unmatched count, or veiled questioning, or has an implausible prevalence estimate. Deciding whether sensitivity bias exists at all goes to survey-design.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audits a methods section against a 45-item reporting checklist synthesized from the APSA Experimental Section rubric, JARS-Quant, CONSORT, and DA-RT, covering pre-registration, recruitment, randomization and treatments, sample flow and attrition, sample-size justification, three-tier results labeling, conjoint reporting, validity, and open-science infrastructure. Use when checking whether a methods section reports enough, preparing a submission or replication archive, asking what CONSORT, JARS, or DA-RT require, or documenting a deviation from a pre-analysis plan. Writing that plan before data collection goes to pre-registration-writing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Drafts a referee report for a journal editor. Produces a recommendation, claim-and-design summary, three to six decision-driving concerns, additional concerns, and a revision plan through five parallel adversarial finders, Breaker, Butcher, Shredder, Void, Situator, a Blue Team error filter, Chief Reviewer synthesis, Tone Guard legal pass, and optional confidential editor note. Use when the user has been asked to referee a manuscript. Self-audits go to paper-review-lite or presubmit, and author responses go to referee-response.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Turns a theory into falsifiable, pre-registerable hypotheses, covering the DGP and DAG, identification, SATE versus PATE, counterfactual and directional framing, named estimands, justified SESOIs, the choice among NHST, equivalence, interval, and minimum-effect tests, scope conditions, and primary, secondary, and exploratory tiers. Use when the user asks to turn a research question or theory into hypotheses, whether a prediction is falsifiable, what the estimand is, or how to predict a null. Framing goes to narrative-building, the plan to pre-registration-writing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runs end-stage QA on a finished figure and table set. Checks callouts, numbering, and cross-references, whether numbers in the text match the exhibits, self-contained captions and statistical notes, accessibility and production quality, and links to the SI and replication package. Values that could only be read off an image are marked for author verification rather than estimated. Use when preparing a submission. Design guidance during drafting belongs to figures and tables.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Designs publication figures for social-science manuscripts. Covers chart choice, axes and scales, color and accessibility, legend order, captions that carry the title, and script-based reproducibility. Use when making, revising, or critiquing a figure for a paper, such as a coefficient plot, small multiples, a distribution, a trend, a map, or a network. Finished figure sets go to figure-table-audit for end-stage QA.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

End-stage QA for a finished figure and table set (callouts, numbering, cross-references, text-to-exhibit consistency, captions and notes, accessibility, SI and replication linkage). Use when preparing a submission.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit fielded survey response data for registered elements, data quality, bot and AI-automation screening, and sample integrity, and emit an appendix-ready quality report. Use at soft launch or after fielding, before outcomes are analyzed.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Interactive browser automation via playwright-cli. Use when you need to navigate a site, click elements, fill forms, take snapshots, or triage a live app.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when validate-chunk reports test failures specifically, when the user says "tests are failing", "figure out what's wrong with the tests", "fix the failing tests", or when test assertions don't match expected output after chunk implementation. Triages whether the test or the implementation is wrong and fixes the correct one.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Write thorough tests following TDD and BDD principles

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use the project MCP infrastructure to inspect the running app from a coding agent. Covers the Playwright MCP servers for headless-browser automation against the dev UI - navigate, snapshot, evaluate JS, capture console + network, and debug runtime state without leaving the conversation. TRIGGER when: the user asks you to "open the app", "click around", "check the browser", "use playwright", "drive the UI", "screenshot the page", "inspect runtime state in the browser", "check the console", "verify a fix in the running app", or log in as a named user; the user offers "do you want to connect to mcp"; a bug needs in-browser reproduction and the dev stack is running; you need to read live YDoc / Redux / window state to confirm a hypothesis. SKIP when: the user is asking about MCP / Playwright in general (not the project's setup); the task is pure backend, code-only, or covered by reading tests/logs; the dev stack is not running and the user hasn't asked you to start it.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Execute the full end-to-end permission matrix against the live Uniffy app through the two Playwright MCP browsers: every sharing, access, denial, viewing, revocation, and request-access case on every content domain (notes, files, projects, tasks, calendar, chat, agents, automations, rooms), proven as the affected user. Covers the PostgreSQL-authoritative access behaviors: instant revocation in search and mentions, per-surface search authorization (spotlight, domain searches, filters, pagination), restricted chips, access requests, COMMENTER and role floors, expiry-aware grants, live org-default inheritance, group membership churn, delete and tag and bookmark revocation, attachment byte gating, and live no-reload pruning. Use when asked to run the permission matrix, matrix-test the permission system, do a full e2e sweep of sharing and access control, or validate a permissions PR end to end. Use `uniffy-e2e-flows` for a lighter single-domain permission loop and `uniffy-playwright` for one-off browser inspection. Skip for unit or integration tests, backend-only work, or when the dev stack is not running and the user has not asked to start it.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create or refine GitHub issues in `uniffy-io/uniffy` using the project's title, template, dependency, project, and image-attachment conventions. Use when asked to create, open, file, draft, report, rename, or track a bug, feature, security issue, or performance issue in this repository, including requests that begin with `[BUG]`, `[FEATURE]`, `[SECURITY]`, or `[PERFORMANCE]`. Skip for pull requests, commit messages, implementation plans that do not need a tracking issue, other repositories, or general GitHub CLI questions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run disciplined end-to-end flows against the live Uniffy app through the project's Playwright MCP infrastructure. Covers authentication, content creation across domains, and the full permission and sharing model, including verification as a second user. Use when asked to test auth, login, permissions, sharing, access control, creation or CRUD, smoke-test the app, exercise each domain, or run a create-and-share flow. Use `uniffy-playwright` instead for a one-off browser inspection or single-bug reproduction. Skip for unit or integration tests, backend-only work, or when the dev stack is not running and the user has not asked to start it.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run a disciplined review of the pending changes (uncommitted work plus the branch delta against main) across four dimensions: security, correctness, performance, and repo consistency. Fans out exploration subagents per dimension, then the main agent acts as judge: every finding is re-verified against the actual code before it is reported, and the result is saved to `.agents/local/reviews/` and replied verbatim. Use when asked to review the changes, review before a PR, check my work, audit this branch, or run a pre-merge review. Use `security-review` instead for a security-only pass, and `simplify` for quality-only cleanup with no bug hunting. Skip for reviewing a single function in conversation or code outside this repo.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create a comprehensive Uniffy feature plan in `.agents/local/plans/` through deep codebase analysis, applicable rules, verified patterns, risks, tests, and executable validation steps. Use when the user asks to plan a feature or prepare implementation work without writing product code.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.