「sel」の検索結果

Use when designing, reviewing, implementing, or validating UI/UX and frontend experiences for web, mobile, responsive apps, design systems, Figma-to-code handoff, frontend stack/library selection, personas, UX mapping, information architecture, UI patterns, accessibility, interaction design, UX research, usability testing, theme/token application, or XR/spatial interfaces.

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, implementing, reviewing, debugging, testing, profiling, or porting concurrent, parallel, distributed, high-performance, network dataplane, kernel-bypass, or real-time software, including locks, semaphores, monitors, MPI, CSP rendezvous, DPDK, VPP, eBPF, XDP, AF_XDP, SR-IOV, RSS, RoCEv2/RDMA, RMS/EDF, priority inversion, and environment selection from silicon to edge.

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。

ローカルの変更差分（git diff）を3つのサブエージェントで並列レビューし、結果を統合して修正を適用する。PR作成前やタスク完了前のローカル品質チェックに使用する。ai-code-reviewと同一の6観点・重大度基準を適用する。

Domain knowledge for using PrintKK print-on-demand API tools effectively. PrintKK is a print-on-demand platform that lets sellers create custom products, manage designs, upload images, and fulfill orders via API. Use this skill whenever the user wants to interact with PrintKK — browsing products, creating designs, placing orders, managing images, or building integrations with the PrintKK API. Also trigger when the user mentions "PrintKK", "print on demand", "POD fulfillment", custom product design workflows, or wants to automate their PrintKK store operations.

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。

Compare your data to a partner's data in the marketplace. Given a dataset you already own with person/edge data, this skill walks you through picking a partner data source to match against, choosing which identifier types to match on, optionally selecting which enrichment attributes to attach, and then submits the report — returning overlap, match counts, and demographic coverage. Use when: "how does my data compare to your marketplace", "compare my data to [partner]", "how much overlap do I have with [supplier]", "run a match report", "match my customers against 3P data", "see what enrichment is available for my dataset", or any open-ended question about marketplace overlap. (narrative-identity)

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。

Verify a tested web agent's real behavior from its recorded Pi or Codex session and selected screenshots before scoring. The judge prompt provides absolute artifact paths; use targeted queries to compare actual outputs, errors, and the final answer with the recorded behavior, then return only the verdict JSON. Only for ego-bench judging—never to drive a browser or rerun the agent.

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。

Export Codex rollout/session JSONL as a self-contained HTML report that can be opened offline. Use when a user provides a complete session file path or Codex session ID, or asks to export a Codex session to HTML, generate a session report, or convert a rollout to HTML. Supports exact full-ID lookup in the CODEX_HOME sessions and archived_sessions directories.

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 self-contained HTML/CSS benchmark and comparison charts in an ego-inspired Browser-Native Editorial style. Use for blue-white product metrics, model benchmarks, A/B comparisons, efficiency reports, difficulty breakdowns, and compact technical data panels.

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。

Get literature into a research run when the plugin fetches nothing — fetch the source yourself with web_fetch / web_search or take a file the person already has, READ it with the pdf_* tools or ocr, then ingest record and text together with rs_cite, bind locators, and cite with [@key]. Use when a run needs sources, when a library export has to come in, when a citation key is unknown, or when a claim cannot be checked against a source.

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。

Hand a research run over as a file — read `rs_open action=capabilities` for the formats this build writes, choose between `md`, `docx`, a self-contained `html`, the `ris`/`bib`/`enw` library exports and `tex`, pick `draft=watermark` while working or `draft=clean` to hand it over, and read `build/build.json` for what was built from which bytes. Use when a document is finished enough to leave the run, when a citation style or an export has to be chosen, or when a build refuses.

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。

Work the prototyping lab itself — where runs live, what a run is, how to promote a run into the checked example library, and how to add a new runtime (Processing in Rust, Cinder) in one module. Use when asked to add a language or framework to the lab, to turn a prototype into a reusable example, to find or tidy what is in the lab, or when the lab's folder or catalog needs explaining.

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 the user starts a non-trivial coding/building task in Claude Code (e.g. "帮我做个 X", "help me build Y", "add feature Z", "搭一个 Z"). Layers an AI-native pedagogical coat over normal coding work — surfaces implicit assumptions in user intent, annotates non-trivial design decisions inline with brief concept-scaffolding for terms the user may not know, and replaces "should I run it?" handoffs with rigorous AI self-verification plus a clean list of what only the user can verify. Skip for pure Q&A, single-line edits, read-only investigation, or refactoring along an existing pattern.

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。

하나의 긴 메서드를 grouping(Reorder/Chunk)·comment로 정돈해 책임을 드러낸 뒤 Arlo Belshee 6단계 네이밍(완전정직 이름 → Extract Method → Intent Revealing → Domain Abstraction)을 하나의 연속 흐름으로 관통하는 self-contained 워크플로우. "이 긴 메서드 이름이 하는 일을 안 드러낸다", "메서드 이름부터 정직하게 만들어서 쪼개줘", "이름 주도로 이 메서드 리팩토링" 요청 시 사용. 단, 여러 파일에 흩어진 개별 이름 스멜의 배치 교체는 /naming-process, 클래스 분리·도메인 이동 같은 대규모 구조 변경은 /system-wide-refactoring이 적합. /intent-revealing-names로 호출.

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。

Refactor code to remove dead code, useless comments, unused variables, and unused imports. Use when asked to declutter a class, clean up noisy code, remove cruft, or run `/refactor:declutter`.

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。

Brutally honest AGENTS.md/CLAUDE.md review backed by real A/B test evidence. Not just opinions — actual proof that your rules are dead weight. Roasts instruction files for bloat, slop, and redundancy, then proves it by running evals. Use when user says "roast my agents.md", "roast my CLAUDE.md", "prove my rules are useless", "eval roast", or wants entertaining evidence-based feedback on their AI config files. Also triggers on "audit my instructions" or "are my rules helping".

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 rich, self-contained HTML explanation of a code change — diff, branch, commit range, MR/PR — with background, intuition, a code walkthrough, diagrams, and a glossary, then quiz the reader interactively in chat. Use when the user asks to explain a change, understand a PR/MR, walk through a diff, onboard onto a branch, or says "explain this PR", "what does this branch do", "teach me this change", or "/explain-diff".

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。

Implement functional Clawix UI wiring while respecting visual mutation boundaries, pattern contracts, protected surfaces, and debt baselines.

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。

Load when the user asks for CTO advice on feature strategy, architecture direction, build-vs-buy, infrastructure, market positioning, roadmap, self-hosting, cost, or organizational tradeoffs; not for reviewing an existing implementation-plan workstream.

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。

Load when evaluating an Islamic software feature, provider policy, AI behavior, moderation, monetization, privacy, defaults, ranking, self-hosting, or deployment model for provider responsibility and Islamic value-sensitive design; not for generic fiqh rulings or ordinary technical implementation.

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。

Load when asked to create, update, re-baseline, or continue a repository-grounded implementation/technical/refactor plan and its `dev/active/<task>` plan/context/tasks files; not for a product PRD, informal advice, or reviewing an already-written plan.

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。

Load for pre-PR self-review or pull-request review that must verify the matched intent, allowed scope, required tests/docs, forbidden actions, architecture gates, and merge readiness; not for a general code-quality diff review alone.

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。

Load when editing Blazor `.razor.css`, scoped selectors, `::deep`, BEM class names, RTL/logical CSS properties, or styling nested MudBlazor components; not for global design tokens or non-Blazor CSS.

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 verification strategy: diagnose observability, select oracle families, map to loop tiers, surface blind spots. Use after ln-plan when frontier items or scoped slices need oracle design — especially for LLM, visual, or compositional work — or when verification coverage has drifted.

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。

Econometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest", "generalized random forest", "GRF", "double machine learning", "DML", "debiased machine learning", "LASSO for variable selection", "post-LASSO", "heterogeneous treatment effects", "CATE", "conditional average treatment effect", "BLP analysis", "CLAN analysis", "causal tree", "honest estimation", "因果森林", "双重机器学习", "异质性处理效应", "条件平均处理效应", "LASSO变量选择", "机器学习因果推断", "去偏机器学习"

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。