「how」の検索結果

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。

Diagnose and fix slow pyfixest regression GRIDS (many feols/fepois calls run sequentially) that stay slow despite demeaner_backend="cupy64" and an idle GPU. Use when: (1) a script looping dozens of pf.feols models on a 100k+ row panel takes ~1 min/model, (2) process inspection shows ~1-1.5 cores busy and nvidia-smi shows ~0% GPU utilization with a resident cupy context, (3) planning any worker prompt that will run a model grid (robustness variants x FE structures x domains). Root cause: per-model CPU-side single-threaded fixed costs (formulaic model-matrix build, interaction construction, singleton detection, cluster vcov) dominate wall time; GPU demeaning is a small slice. Fix: shard the model grid across OS processes and/or use pyfixest multiple-estimation syntax; mandate this IN THE WORKER PROMPT.

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。

Fast sprint status check. Reads the current sprint plan, scans story files for status, and produces a concise progress snapshot with burndown assessment and emerging risks. Run at any time during a sprint for quick situational awareness. Use when user asks 'how is the sprint going', 'sprint update', 'show sprint progress'.

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。

Audit, classify, validate, and scaffold documentation using the Diataxis framework (Tutorials, How-to guides, Reference, Explanation). Use when user mentions "diataxis", "documentation framework", "quadrant", "doc audit", "doc coverage", "collapsed document", "tutorial vs how-to", "quadrant purity", "documentation types", or wants to classify docs by type.

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。

Construct a compelling job offer. Use when the user says "write an offer letter", "help me make an offer", "how should I structure this offer", "what should we include in the offer", "how do I explain the equity", "the candidate is negotiating", or wants to convert a candidate from interested to accepted - even if they don't explicitly say "offer letter". Also use when a recruiter needs to explain comp philosophy or total compensation to a candidate.

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 a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

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。

Design and write QA test artifacts - test cases, test plans, acceptance criteria, API test specs, and PR testability reviews. Use this skill whenever a QA engineer or SDET needs to translate requirements, user stories, or feature specs into structured test documentation. Trigger on phrases like "write test cases", "create a test plan", "define acceptance criteria", "review this PR for testability", "write API test specs", "test coverage for this feature", "what should we test", "how do we test this", or any request to structure what and how to test before execution begins. Also trigger when a developer asks "is this testable?" or a PM asks "what are the edge cases?".

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 QA quality dashboards, calculate defect metrics, analyze escape rates, and produce quality trend reports. Use this skill whenever a QA lead or manager needs to measure and communicate quality outcomes. Trigger on phrases like "quality metrics", "defect density", "escape rate", "bug trends", "quality dashboard", "sprint quality report", "test coverage metrics", "QA KPIs", "how is quality trending", "defect leakage", "production bugs this quarter", "mean time to detect", "quality scorecard", or any request to quantify, visualize, or report on the quality of a product or testing process. Also trigger when a manager asks "how is QA performing?" or an engineering lead asks "what does our defect data tell us?".

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。

Create QA test strategy documents, coverage matrices, and risk-based test prioritization plans. Use this skill whenever a QA lead or manager needs to plan what to test, why, and at what depth. Trigger on phrases like "write a test strategy", "test strategy document", "what should we test", "prioritize testing", "risk-based testing", "test coverage plan", "QA approach for this project", "coverage matrix", "test scope", "how should we approach testing this quarter", "where are our coverage gaps", or any request to define the strategic plan for testing - not the execution of it. Also trigger at project kickoff when a QA lead asks "how do we approach quality on this?"

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。

Conduct a competitive analysis. Use when the user says "competitive analysis", "how do competitors handle X", "market landscape", "blue ocean", "strategy canvas", "what does [competitor] do", "compare us to X", "positioning analysis", "value curve", or wants to understand how a product or feature compares to alternatives - even if they don't explicitly say "competitive analysis".

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。

Write an operational runbook. Use when the user says "write a runbook", "on-call documentation", "how to operate this service", "alert runbook", "troubleshooting guide for ops", "what to do when this alert fires", "operational procedures", or needs to document how to run, troubleshoot, or respond to a service - even if they don't explicitly say "runbook".

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。

Deliver feedback using Kim Scott's Radical Candor framework - care personally while challenging directly. Use when a leader needs to give difficult feedback, says "I need to tell someone something hard", "how do I give feedback without hurting them", "I've been avoiding a conversation", "my direct report isn't performing", "someone on my team has a blind spot", "I keep sugarcoating things", or "how do I be honest without being a jerk". Also trigger when someone describes being too nice (ruinous empathy) or too harsh (obnoxious aggression), or when they describe avoiding a conversation they know they need to have.

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。

Write a product positioning document. Use when the user says "write a positioning doc", "positioning statement", "how should we position this product", "positioning for [product]", "we need to differentiate from competitors", "product positioning and messaging", "positioning workshop", "help me define our position in the market", or wants to establish how a product should be perceived relative to competitors. For customer-facing message wording, see messaging-framework. For the competitive research behind it, see competitor-analyst. For storing it in the knowledge base, see brand-context.

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。

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

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。

Structure a consulting findings presentation using the Pyramid Principle storyline. Use when a consultant says "help me structure my presentation", "I have findings and need to present them", "how do I structure the deck", "build me the storyline", "help me tell the story of the findings", "I have data but no narrative", "client presentation is next week", "how do I present recommendations to the steering committee", or "the deck needs a through-line". Also trigger when someone has completed analysis and needs to communicate findings and recommendations to senior client stakeholders in a structured, persuasive format.

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。

Write an ETL operational runbook. Use when the user says "ETL runbook", "pipeline runbook", "data job runbook", "how to operate this ETL", "on-call guide for data pipelines", "what to do when the data job fails", "pipeline troubleshooting guide", "data ops runbook", or needs to document how to operate, monitor, and recover a data pipeline or ETL job - even if they don't explicitly say "runbook".

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。

Document a machine learning model in a structured, transparent format for stakeholders, reviewers, and future maintainers. Use when the user says "document this model", "write a model card", "model documentation", "how should I document my ML model", "bias and fairness report", "model transparency", "what does this model do", "model handoff", "production model documentation", or needs to communicate what a model does, how it was built, where it works, and where it fails.

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。

Explore and debate solutions before writing code. Use when the user poses a design question, asks "how should I approach X", wants to think through options before committing, or says anything like "let's brainstorm", "what's the best way to...", "I'm not sure how to tackle this", or "should I use X or Y". Always runs before /ck:plan for novel or ambiguous features. No code is written — only: explore → clarify → spec → 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。

Explore and debate solutions before writing code. Use when the user poses a design question, asks "how should I approach X", wants to think through options before committing, or says anything like "let's brainstorm", "what's the best way to...", "I'm not sure how to tackle this", or "should I use X or Y". Always runs before /ck:plan for novel or ambiguous features. No code is written — only: explore → clarify → spec → 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 designing or reviewing Salesforce sandbox topology, refresh cadence, masking, and environment purpose. Triggers: 'Developer sandbox', 'Developer Pro', 'Partial Copy', 'Full sandbox', 'sandbox refresh', 'data masking', 'test environment', 'Gov Cloud sandbox'. NOT for how many environments a program needs and how they map to branches - use devops/environment-strategy. NOT for re-seeding reference data after a refresh - use data/sandbox-refresh-data-strategies. Also covers: SandboxPostCopy Apex class, SandboxInfo and SandboxProcess Tooling API, SandboxSettings metadata, sandbox topology table, refresh calendar.

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 this skill when setting up, configuring, or managing Salesforce Lightning Knowledge — enabling the feature, designing record types on Knowledge__kav, configuring Data Categories for organization and visibility control, setting up publishing workflows, and layering approval processes. Trigger keywords: Lightning Knowledge setup, Knowledge article record types, Data Category visibility, Knowledge publishing workflow, Knowledge__kav configuration. NOT for converting Classic Article Types to Lightning — use admin/knowledge-classic-to-lightning. NOT for bulk-loading articles from an external help center — use data/knowledge-article-import. NOT for sizing the taxonomy itself (how many groups, how deep) — use architect/knowledge-taxonomy-design.

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 Lightning record page, home page, or app page is slow to load or render — covers Experienced Page Time (EPT) analysis, component count reduction, progressive disclosure via tabs and conditional rendering, Lightning Experience Insights diagnostics, and DOM/XHR minimization strategies. Triggers: 'Lightning page is slow', 'EPT is high', 'record page takes too long to load', 'too many components on page', 'Lightning Experience Insights shows slow page', 'how to optimize Lightning page performance'. NOT for Visualforce page performance (separate concern). NOT for Apex or SOQL query optimization (use apex/apex-cpu-and-heap-optimization or data/soql-query-optimization). NOT for report or dashboard performance (use admin/report-performance-tuning).

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。

Firmware development for the Raspberry Pi Pico (original, RP2040 — dual Cortex-M0+ @ 133 MHz, 264 KB SRAM, 2 MB QSPI flash) — its 26 exposed GPIO, 4-channel 12-bit ADC, 16-channel PWM, 2× UART/I2C/SPI, PIO state machines, USB 1.1 CDC, VSYS/VBUS/SMPS power wiring, and the PlatformIO + arduino-pico (earlephilhower) setup around them. Use when working on this board, any Pico H or Pico clone, or a bare RP2040: project setup, platformio.ini, the earlephilhower-vs-Mbed core choice, pin mapping, USB CDC serial, analogRead/analogWrite behaviour, Wire/SPI defaults, battery power, EEPROM emulation, BOOTSEL/UF2 flashing, or debugging why something on the board does not work.

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。