데이터·AI 스킬

Set up Prisma ORM in an application, connect its database, or troubleshoot the connection of an existing Prisma 6, 7, or 8 app. Defaults new applications to Prisma ORM 8 and loads the package-owned prisma-8 skill; keeps existing Prisma 6/7 apps on their version with provider references for PostgreSQL, MySQL, SQLite, SQL Server, CockroachDB, MongoDB, and Prisma Postgres.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Integrate MDMA into an application and build features with it — wire up parsing, the runtime store, React rendering, LLM streaming, custom components, prompts, and CI validation. Use this skill when the user asks to add MDMA to an app, build a chat that streams MDMA, author or maintain a custom prompt, validate MDMA documents, register a custom component, or expose MDMA to an agent via MCP. Generates focused, correct wiring that uses the right packages for the job instead of reinventing them.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Following what organisms do — behavior, metamorphosis, host-plant relationships, social dynamics, and the long-form ethograms that reveal how species actually live. Covers the vocabulary of ethology, the structure of a life cycle, the classic categories of species interaction, the discipline of recording behavior without premature interpretation, and the gap between a single observation and a statistically useful record. Use when the task is to understand or record what a species does rather than what it is.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Birding by sight and sound — gestalt, song and call vocabulary, behavioral and habitat clues, and the discipline of producing eBird-grade records. Covers the vocabulary of bird field marks, the primary categories of vocalization, the habits of habitat-filtering, and the protocol for submitting records to a citizen-science database without degrading data quality. Use when the task is bird-specific observation or record-keeping.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Catalog of informal fallacies with definitions, canonical examples, and detection heuristics. Covers relevance fallacies (ad hominem, straw man, red herring, appeal to authority, appeal to emotion), presumption fallacies (false dichotomy, complex question, begging the question), ambiguity fallacies (equivocation, amphiboly, accent), causal fallacies (post hoc, slippery slope, correlation-causation), and statistical fallacies (hasty generalization, cherry-picking). Use when evaluating arguments for rhetorical or informal reasoning errors.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with the non-metallic engineering materials — polymers, ceramics, or composites — and you need to reason about structure, processing, or properties. Covers thermoplastics versus thermosets, chain structure, glass transition, and viscoelasticity in polymers; ionic and covalent bonding, sintering, brittleness, and Weibull statistics in ceramics; and fiber-reinforced laminates, matrix and reinforcement roles, the rule of mixtures, and anisotropy in composites. Reach for it to choose a plastic, understand why a ceramic fails, or predict the stiffness of a laminate.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Map design, spatial analysis, and Geographic Information Systems. Covers map projections and their distortion trade-offs, coordinate systems, thematic mapping techniques (choropleth, proportional symbol, dot density, isoline), remote sensing and satellite imagery, GIS data models (vector and raster), spatial analysis operations (overlay, buffer, interpolation, network analysis), and cartographic design principles. Use when creating maps, analyzing spatial data, selecting projections, interpreting satellite imagery, or reasoning about spatial relationships in any domain.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Grammar and syntactic structures across human languages -- word order typology (SVO, SOV, VSO, VOS, OVS, OSV), morphological systems (isolating, agglutinative, fusional, polysynthetic), agreement patterns (gender, number, case, person), phrase structure, clause embedding, and cross-linguistic universals. Covers constituent analysis, dependency vs. constituency grammars, grammatical relations (subject, object, oblique), ergativity vs. accusativity, tense-aspect-mood systems, and how grammar encodes meaning differently across language families. Use when analyzing sentence structure, comparing grammar systems, teaching grammatical concepts, or understanding why a learner makes transfer errors from their L1.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Grammar of graphics, chart type selection, color theory, interactive visualization, dashboards, and the principles of honest, effective data display. Covers Tufte's data-ink ratio, Bertin's visual variables, perceptual principles, accessibility, small multiples, annotation, and the full workflow from exploratory plots to publication-quality graphics. Use when creating charts, designing dashboards, critiquing visualizations, or choosing how to display data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Public speaking and oral presentation skills for effective communication. Covers speech structure (introduction, body, conclusion), delivery techniques (projection, pace, pause, gesture), audience analysis, impromptu and extemporaneous methods, managing anxiety, visual aids, and persuasive versus informative speaking. Use when preparing speeches, practicing delivery, analyzing presentations, or building confidence in oral communication.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Evaluating the quality, provenance, and relevance of evidence that supports or undermines a claim. Covers source credibility, sampling quality, study design, levels of evidence (anecdote to meta-analysis), base rate integration, distinguishing primary from secondary sources, and calibrating belief to evidence strength. Use when the question is not whether an argument is valid but whether its premises are actually supported by the available data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Algorithms and data structures from first principles through advanced analysis. Covers sorting (bubble, insertion, selection, merge, quick, heap, radix), searching (linear, binary, BFS, DFS, Dijkstra, A*), fundamental data structures (arrays, linked lists, stacks, queues, hash tables, trees, heaps, graphs, tries), complexity analysis (Big-O, Big-Omega, Big-Theta, amortized), recurrence relations, and algorithm design paradigms (divide-and-conquer, greedy, dynamic programming, backtracking). Use when analyzing, selecting, implementing, or comparing algorithms and data structures.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Data cleaning, transformation, reshaping, joins, missing data handling, and tidy data principles. Covers the full pipeline from raw ingestion to analysis-ready datasets -- type coercion, deduplication, outlier detection, normalization, melting/pivoting, regex extraction, and reproducible transformation chains. Use when preparing, cleaning, or transforming data for analysis.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Bias detection and mitigation, fairness metrics, privacy frameworks, consent models, transparency requirements, and accountability structures for data science practice. Covers algorithmic bias sources, disparate impact testing, differential privacy, GDPR principles, model cards, datasheets for datasets, responsible AI frameworks, and the organizational governance needed to make ethics actionable. Use when auditing models for bias, designing privacy-preserving systems, establishing governance processes, or evaluating the social impact of data-driven decisions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

A/B testing, randomization, sample size calculation, confounding control, and causal inference for data science. Covers the full experimental lifecycle from hypothesis formulation through power analysis, randomization strategies, blocking, factorial designs, sequential testing, and the potential outcomes framework for causal claims. Use when designing experiments, planning A/B tests, calculating sample sizes, or reasoning about causation from data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Supervised and unsupervised learning, bias-variance tradeoff, cross-validation, decision trees, ensemble methods, neural network fundamentals, and the practitioner's workflow from problem framing through deployment. Covers classification, regression, clustering, dimensionality reduction, regularization, hyperparameter tuning, and evaluation metrics. Use when building predictive models, selecting algorithms, or understanding the machine learning pipeline.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Regression analysis, ANOVA, generalized linear models, Bayesian methods, and model selection. Covers the full modeling workflow from problem formulation through diagnostics -- linear regression, logistic regression, Poisson regression, mixed-effects models, prior specification, posterior inference, AIC/BIC comparison, cross-validation for model selection, and assumption checking. Use when fitting models, testing hypotheses, or selecting among competing statistical explanations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Spectroscopy, chromatography, titration, elemental analysis, X-ray crystallography, and mass spectrometry for chemical identification and quantitation. Covers UV-Vis and IR spectroscopy, NMR fundamentals, gas and liquid chromatography, gravimetric and volumetric analysis, diffraction methods, separation techniques, and quantitative error analysis. Use when identifying unknown substances, determining purity, measuring concentrations, or interpreting analytical data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Understanding and managing what digital services collect, store, share, and infer about you. Covers password security and entropy, multi-factor authentication, privacy settings, data minimization, the difference between first-party and third-party tracking, cookies and fingerprinting, privacy laws (GDPR, CCPA), and how to respond to data breaches. Use when helping a learner make informed decisions about what to share, with whom, and under what terms.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Interrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, Deacon heartbeat supervision. Fights LLM passivity bias.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when you have captured session evidence — session-retro / session- observatory-live traces in .planning/patterns/, tool logs, correction records — and want to induce a reusable skill from it. Segments the traces into candidate skill units (an LLM judgment, not a deterministic parse) and decomposes each candidate into a four-part structured spec: workflow structure, execution semantics, and runtime attachments (verification, safety, rollback, state). It emits a spec object, NOT a finished SKILL.md, and hands that spec to skill-forge. It sits between skill-integration (upstream frequency detector) and skill-forge (downstream author). Backed by Agent-Trace-to-Skill Induction (arxiv 2606.06893v1). Triggers on inducing a skill from captured traces, turning a repeated pattern into a skill spec, and preparing evidence for skill-forge.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consolidation promoting session traces to MEMORY.md, or embedding externally-ingested content. Scores each candidate record against a fixed panel of sentinel queries and quarantines any record that would become the nearest neighbor of too many unrelated queries — a hub — whether from adversarial poisoning or accidental over-generality. This is the memory-record-side sibling of skill-injection-guardian (file-side) and the write-side complement of memory-use-warrant (read-side). Quarantine, never silently drop; a human reviews. Backed by the admission-time hubness gate (arxiv 2606.19692v1). Triggers on inserting into vector memory, consolidating memory, and embedding stranger content.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Classify the information-need of a query and dispatch it to the appropriate retrieval or reasoning strategy. Use before read-side memory access, before multi-strategy retrieval, or any time you'd otherwise default to "one retriever for everything". Returns a strategy label, a token budget, and a retrieval depth so downstream handlers can be specialised. Backed by Pre-Route (arxiv 2605.10235v2) and MemFlow (arxiv 2605.03312v1), which together show LLMs possess latent routing ability elicitable via a structured prompt — and that externalising the routing decision improves small-model performance by ~2x. Triggers: "route this", "what strategy", "before retrieving", "intent classification", or any query whose ideal handling depends on what KIND of question it is.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when parallel agents in a convoy or across git worktrees hit a write conflict on shared state — a git tree, a config, or a shared document — and you must decide whether the conflict is semantically real. Classifies each conflicting hunk as independent (keep both), redundant (pick one), or a genuine clash (escalate), instead of blind locks, abort-and-retry, or escalate-everything. Sits ABOVE refinery-merge and NEVER blind auto-merges: it wraps an LLM judgment, defaults to escalate on any uncertainty, and unconditionally escalates any hunk touching .planning/, config, credentials, or safety-critical paths. Backed by CoAgent (arxiv 2606.15376v1). Triggers on write conflicts between parallel agents on shared repo state.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.