1,706 件 ・ 関連度順
概要と使いどころ
This skill provides expert-level guidance for implementing VS Code WebView features. Use when creating WebView panels, implementing secure CSP policies, handling Extension-WebView communication, managing WebView state persistence, optimizing WebView performance, or debugging WebView rendering issues. Covers security best practices, message protocols, and VS Code-specific WebView patterns.
日本語の概要は準備中です。原文の説明を表示しています。
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
日本語の概要は準備中です。原文の説明を表示しています。
Build throwaway code to validate an uncertain approach before committing to a plan. Two branches — Logic (terminal state machine) or UI (multiple designs on one route with URL-param switcher). No persistence, no tests, single-command start. Use between analyze and plan when the approach itself is uncertain.
日本語の概要は準備中です。原文の説明を表示しています。
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
日本語の概要は準備中です。原文の説明を表示しています。
Generate design or architecture documents from existing implementation. Works backwards from code/prototypes to create missing planning docs.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of an Environmental Health Specialist (Registered Sanitarian) — classifying a food-establishment temperature violation as critical vs. priority-foundation, determining pool closure and hyperchlorination protocol after a fecal/vomit incident, evaluating a septic percolation test against site-limiting conditions, deciding whether a complaint pattern meets the threshold for an outbreak investigation, or issuing an imminent-health-hazard closure.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of an Electrical and Electronic Engineering Technologist/Technician — bench-testing a prototype board against a power or timing spec, isolating a resistive fault in a power path with node-to-node voltage-drop measurements, checking whether an oscilloscope's own bandwidth is limiting a rise-time measurement before trusting it, running a power-supply load-regulation sweep, or evaluating ESD-event provenance and IPC-A-610 acceptance on a returned unit.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of an EMT (Basic Life Support tier) — deciding whether a chest-pain patient gets aspirin under protocol, dosing an epinephrine auto-injector for anaphylaxis and knowing when to repeat it, applying spinal-motion-restriction criteria instead of routine backboarding, recognizing the moment a call exceeds BLS scope and requesting ALS intercept, or working a patient refusal (AMA) to a legally defensible conclusion.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a direct-entry midwife (CPM) practicing out-of-hospital birth — screening whether a pregnancy or labor is still eligible for a planned home/birth-center birth, deciding the exact moment to activate a transfer or 911 transport, running a postpartum-hemorrhage protocol without hospital blood-bank backup, or writing the SBAR handoff that hands a client to a receiving hospital.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a Criminal Justice and Law Enforcement Teacher, Postsecondary — grading or defending a crime-trend assignment that must distinguish rate from raw count, mapping a CJ curriculum against ACJS certification standards or a state POST lesson-plan hour requirement, screening a student research protocol involving parolees, probationers, or incarcerated subjects for IRB Subpart C, or setting the liability and confidentiality terms for a ride-along or corrections practicum placement.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a Cytogenetic Technologist — choosing a culture/harvest protocol and band resolution for a specimen, applying ISCN clonality criteria to a metaphase count, deciding between karyotype, FISH, and chromosomal microarray for a clinical question, or writing and QCing an ISCN-formatted cytogenetics report.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a Diagnostic Medical Sonographer — deciding whether a duplex, compression, or graded-compression ultrasound study is diagnostic versus technically limited, choosing when to interrupt a scanning protocol to escalate a real-time critical finding, setting scan technique and ALARA (TI/MI) parameters for a given exam type, or drafting the technical worksheet and preliminary findings a physician will interpret and sign.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a Clinical Nurse Specialist — diagnosing why a unit-level outcome metric (CLABSI, falls, pressure injury) is off benchmark, designing and scaling a practice-change pilot, appraising whether a new clinical guideline actually fits the local population, writing a quarterly outcomes report to nursing leadership, or coaching staff nurses through a new protocol without formal authority over them. US hospital/health-system default; state nurse practice acts vary. A reasoning aid, not clinical or legal advice.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a Clinical Research Coordinator — managing patient recruitment/enrollment against a trial's screen-fail rate, handling a protocol deviation, tracking informed consent and regulatory documentation, or coordinating a multi-visit study schedule against patient retention risk.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a Commercial/Industrial Designer — designing the form, ergonomics, and manufacturability of a physical product, choosing between manufacturing processes at a given volume, selecting materials/finishes under a cost or durability constraint, or planning a prototyping sequence before tooling commitment.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a Biostatistician — designing a clinical trial's sample size and analysis plan, choosing a survival-analysis or censoring-aware method, preparing a DSMB safety readout, or judging whether a trial's efficacy claim survives ITT vs. per-protocol scrutiny.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a Biology Professor at a research university — writing or defending an NIH/NSF grant budget, deciding authorship order on a paper, navigating an IACUC or biosafety protocol, mentoring a PhD student through a stalled project, or converting a course when active-learning data doesn't match student pushback.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a livestock geneticist/animal breeder — selecting a sire against EPDs or genomic data, screening a proposed mating for inbreeding risk, deciding AI versus natural service, timing an estrus-synchronization protocol, or defending a breeding-goal tradeoff to a herd owner.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of an Animal Control Worker — responding to a dog-bite or animal-attack call, determining rabies-exposure quarantine protocol, evaluating a dangerous-dog classification referral, planning a cruelty/neglect investigation and removal, or selecting a capture/restraint method for a stray or wildlife-in-structure call.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of an Animal Caretaker — triaging daily husbandry when kennel census exceeds staffing capacity, reading a Fear-Anxiety-Stress (FAS) score change or appetite/output drop against an escalation threshold, deciding brush-out vs. shave-down on a matted coat, or setting isolation and vaccination-lead-time protocol for a new intake or boarding admission.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of an animal trainer — designing a behavior-modification plan for a specific problem behavior, choosing a reinforcement schedule and deciding when to raise criteria, structuring session length and frequency to avoid fatigue or frustration plateaus, or setting a handler/public safety protocol around a training animal.
日本語の概要は準備中です。原文の説明を表示しています。
Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wraps HTML fragments in a frame template, broadcasts live-reload over WebSocket, and captures browser-side click events to a JSONL file. Use when an agent needs to show HTML to the user in a browser and react to clicks — mockups, design exploration, gallery browsing, multi-select choices, prototype iteration. Triggered by "live preview", "browser companion", "preview server", "browser mockup", "show in browser", "arkhe-preview", or any skill that wants to write HTML fragments and have the user see them reload in real time.
日本語の概要は準備中です。原文の説明を表示しています。
Guideline for designing, implementing, and verifying secure TypeScript and JavaScript applications following OWASP Top 10 best practices. Use when the user wants to: (1) review TypeScript or JavaScript code for security vulnerabilities, (2) design a secure Node.js, Deno, or browser application architecture, (3) implement security features (authentication, authorization, cryptography, input validation), (4) audit npm/yarn/pnpm dependencies for known vulnerabilities, (5) create security checklists or verification plans, (6) fix security bugs or harden existing TypeScript or JavaScript code, (7) set up security testing and static analysis (ESLint security plugins, Semgrep, Snyk), or (8) handle any TypeScript/JavaScript security concern including injection prevention, prototype pollution, XSS protection, SSRF prevention, secrets management, and secure deployment.
日本語の概要は準備中です。原文の説明を表示しています。
Build native Linux packages (.deb / .rpm / .apk / .pkg.tar.zst) from a PKGBUILD or yap.json project using the yap-mcp Model Context Protocol server. Use this skill whenever the user asks to "build a package", "make a deb/rpm", "cross-compile for arm64/aarch64", "sign a release", generate SBOMs, install a built artifact, or diagnose why a yap build failed. The yap MCP server exposes async builds with buildID polling, validation, dependency-graph inspection, and artifact discovery.
日本語の概要は準備中です。原文の説明を表示しています。