2,329 件 ・ 関連度順
概要と使いどころ
Provides TypeScript-specific code review patterns covering strict mode, ESM, type safety, branded types, discriminated unions, async patterns, runtime safety, and common anti-patterns. Activates on detection of tsconfig.json, *.ts, or *.tsx files during code review — loaded automatically by dh:code-reviewer.
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。
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
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。
Advises on setting up LLM-based text classification as a validated measurement design. Covers codebook construction, learning-regime and model choice, prompt construction, validation against human coding with kappa and F1, hybrid human-LLM review, downstream measurement error, and reporting, plus a short resumable batch pattern with a rule-based baseline for repeated free text against a closed codebook. Use when the user wants to classify, code, or label text at scale. Category discovery goes to topic-modeling.
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。
Runs a multi-model orchestration workflow led by the session's Fable or Claude Opus model. Sends menial tool-calling work to Haiku subagents, judgment work to Opus subagents at an effort matched to each task, and high-stakes or fresh-perspective questions to a GPT-6 Astra Codex peer. Detects the lead from session context; `--lead fable` or `--lead opus` overrides. Use to orchestrate, delegate, fan out, get a decorrelated Codex opinion, run a blind Opus-Codex cross-check, or act as tech lead.
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。
Cross-verify Claude-generated plans and code using OpenAI Codex and Google Gemini CLI. Provides code review, plan validation, and comparative analysis. Use when needing second opinions on Claude's code or plans, validating technical decisions, or seeking consensus from multiple AI models.
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 Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
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。
Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered sources. Skip one file, one function, a single needle, or a one-page PDF conversion. Triggers: long context, context rot, large codebase, many files, all files, big document, multi-document, PDF, aggregate, summarize everything, codebase-wide, multi-hop, recursive, sub-agents, map-reduce.
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。
Apply modern web development best practices for security, compatibility, and code quality. Use when the task involves `apply best practices`, `security audit`, `modernize code`, `code quality review`, or `check for vulnerabilities`.
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。
ALIGN-video for Claude Code with independent Codex adversarial review. Create or revise a video through agent-authored code, rendering, editing and fresh-context audiovisual review, without image, video or music generation models. Use for reference-led animation, procedural films, motion design, explainers, construction replays, and continuing an existing coded-video project. Carries the work from reference study and animatic through a finished, reproducible film; supports explicitly requested self-review when appropriate.
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。
ALIGN-video for Codex. Create or revise a video through agent-authored code, rendering, editing and fresh-context audiovisual review, without image, video or music generation models. Use for reference-led animation, procedural films, motion design, explainers, construction replays, and continuing an existing coded-video project. Carries the work from reference study and animatic through a finished, reproducible film; supports explicitly requested self-review when appropriate.
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。
Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp. Includes Qwen 3.5 serve scripts (9B dense + F16, 35B MoE) with asymmetric KV cache and thinking mode. Secondary to Ollama; use when needing direct model control or LoRA hot-loading. Triggers on 'llama.cpp', 'GGUF', 'LoRA adapter', 'benchmark inference', 'llama-server'.
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。
機能検討・プロダクト機能設計の壁打ちスキル。Mode A「壁打ち開始：〇〇機能」で1機能を深掘り、Mode B「アプリの機能を考えたい」でアプリ全体の機能セットを設計。ペルソナ・競合分析・トンマナを統合して議論。
Convert SVG files to high-quality PNG images with precise control over dimensions, background color, and CSS rendering (including mix-blend-mode, filters, gradients). Use this skill when the user wants to: (1) convert SVG to PNG, (2) generate app icons or splash screens from SVG source, (3) batch-generate multiple PNG sizes from a single SVG, (4) render SVG with advanced CSS features like mix-blend-mode or filters to PNG. Triggers: "SVG to PNG", "SVG変換", "PNG変換", "アイコン生成", "スプラッシュ生成", "app icon from SVG", "favicon generation", "splash screen generation".
Fit hidden Markov models using the Baum-Welch (EM) algorithm with model selection, Viterbi decoding for state sequences, and forward-backward probabilities. Use when observations are generated by unobservable latent states, you need to segment a time series into latent regimes (market regimes, speech phonemes, biological sequences), compute sequence probabilities, decode the most likely hidden state path, or compare models with different numbers of hidden states.
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 a generative recipe DSL so agents emit small validated JSON documents and ONE audited interpreter renders them all — data, not code. Covers the N-artifacts threshold for choosing a DSL over bespoke code, designing roles as style slots so a single recipe renders unchanged in every output style, the validator gate (compile + bounds + real render in all styles, plus a --fast mode for corpus-wide sweeps), hand-authored seed recipes, and the emergent conventions that keep a corpus of hundreds consistent without per-item steering. Use when many similar artifacts (icons, status badges, diagram nodes, test fixtures) must be generated by agents, when per-item bespoke code is multiplying unreviewable code paths, or when a whole corpus must be re-rendered cheaply into new styles.
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。
Four-stage alchemical code transmutation — nigredo (decomposition), albedo (purification), citrinitas (illumination), rubedo (synthesis) — with meditate and heal checkpoints between stages. Transforms tangled or legacy code into optimized, well-structured output through systematic material analysis. Use when transforming legacy code into modern equivalents, refactoring deeply tangled modules where incremental fixes keep failing, converting a codebase between paradigms, or when simpler refactoring approaches have stalled and a full-cycle transformation is needed.
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。
Fix Playwright automation failures against code-server (VS Code in browser). Use when: (1) trust dialog blocks all clicks — "monaco-dialog-modal-block intercepts pointer events", (2) button:has-text() finds wrong buttons behind modal dialog, (3) keyboard shortcuts don't work — Meta vs Control inconsistency, (4) VS Code extension activity bar icon not found by aria-label, (5) panels show placeholder text despite extension being "Connected". Covers trust dialog dismissal, keyboard shortcut hybrid mode, extension panel selectors, and database connection verification for Grafema extension.
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。
TypeScript and JavaScript performance and code-quality rules, usable in any framework. Use when writing, reviewing, or refactoring hot paths, data-structure choices, async flows, or bundle-size-sensitive code. Triggers include "optimize this function", "too slow", "reduce allocations", "bundle size", "lazy load", "speed up imports", or general code review of utilities and services.
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 feature or code change made by Claude is complete and the developer wants to confirm they actually understood it before shipping. Triggers on "handoff", "quiz me", "comprehension check", "did I understand this", "verify I read the code", "test my understanding", or after finishing a feature when the developer wants to take ownership of AI-written code. Also triggers on requests for an interactive or clickable quiz ("interactive mode", "let me answer with the mouse", "mode interactif", "je réponds à la souris"). Quizzes the developer on WHERE the logic lives (file/function) and WHY decisions were made (trade-offs, behavior, debugging), with the number of questions scaled to the size of the change. Multiple-choice questions are clickable by default (asked through `AskUserQuestion`) and fall back to typed answers. Points to file:line on wrong answers, allows one retry, then reveals the answer, and ends with a score plus the weak areas to re-read. Conducts the quiz in the developer's language.
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。
White-box source code security review structured around OWASP ASVS 5.0 (427 verification requirements across 16 chapters). Reads and understands application source code to build a security-aware knowledge base that enriches all downstream skills. Covers: tech stack identification, route/endpoint mapping, authentication and authorization architecture, dangerous function patterns, source-to-sink data flow tracing, IaC review, dependency analysis, ASVS compliance mapping, and LLM integration security (prompt injection, tool abuse, output handling, RAG poisoning, MCP server patterns). When LLM/AI framework usage is detected, automatically reviews OWASP LLM Top 10 patterns from source code and chains into /ai-redteam with white-box context for live endpoint testing. Chains into /pentester, /threat-modeling, /web-exploit, /api-security, /cloud-security, /analyze-cve, /credential-audit, and /ai-redteam — providing white-box context that transforms black-box testing into targeted, informed assessment.
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。
Put one question to several models at once — you, OpenAI Codex, and a cheap third via OpenCode — and show all the answers side by side. No judging, no consensus: three opinions, the user picks. Use for "ask everyone", "what do the other models think", "second opinion", "multi ask", or any open question where one model's answer is not enough.
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。
Use when a task needs the judgment of a computer programmer implementing to a given specification — translating a design/pseudocode/systems-analyst spec into working code in a specified language, flagging spec ambiguity before writing code, maintaining or modernizing an existing codebase against its original contract, or writing unit tests that prove the implementation matches the spec (not designing the system the spec describes).
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。
Distill large models into smaller ones — teacher-student training, data generation, loss design, and quality validation. Use when you need big-model behavior at small-model cost.
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。