1,210 件 ・ 関連度順
概要と使いどころ
Use tmux from the command line to run, drive, and monitor terminal programs as a coding agent (detached sessions, send-keys input injection, capture-pane output polling, formats, completion detection, and control mode). Use when a task needs long-running or interactive processes (builds, tests, servers, REPLs, watch modes, TUI apps) kept alive across turns or inspected live; skip when plain `cmd > log 2>&1 &` is 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。
Detect AI-generated writing patterns in developer text — docs, docstrings, commit messages, PR descriptions, and code comments. Use when reviewing any text artifact for authenticity and clarity, or when the user mentions ai writing, ai-generated or robotic writing, text that sounds like AI or ChatGPT, or writing quality. Builds on the docs-style core writing principles.
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。
Tutorial patterns for documentation - learning-oriented guides that teach through guided doing. Use when writing a tutorial, learning guide, getting-started or onboarding guide, beginner/introductory guide, or any learn-by-doing hands-on guide. Builds on the docs-style core writing principles.
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。
How-To guide patterns for documentation - task-oriented guides for users with specific goals. Use when writing a how-to/howto guide, task guide, procedural guide, step-by-step guide, or how-to documentation. Builds on the docs-style core writing principles.
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。
Explanation documentation patterns for understanding-oriented content - conceptual guides that explain why things work the way they do. Use when writing an explanation doc, conceptual guide, understanding/background doc, design rationale, or architecture explanation, or when asked how/why something works. Builds on the docs-style core writing principles.
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。
Provision and drive a `pu` box — an Incus container used as a clean Linux host for CI, builds, and evidence capture. Use when you need to run something on a fresh remote box instead of the user's machine: `nix run` a build, run CI against a real host, capture screenshots/video off-machine, or reproduce on a pristine environment. Covers create/connect/scp/destroy, running remote commands, copying artifacts back, and the no-egress failure mode. Triggers on "pu box", "spin up a box", "run this on a box", "ephemeral host", "pu create/connect/destroy".
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。
Never invoke implicitly; use only when explicitly asked for Play Store assets. Builds or updates RIPDPI's marketing screenshots and feature graphic (Next.js generator in play-store-screenshots/).
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。
Financial goal planner. Takes any goal (house down payment, college fund, wedding, sabbatical, business launch, car, vacation) and builds the required savings amount, monthly contribution, timeline, investment vehicle recommendation, milestone checkpoints, and adjustment scenarios. Supports multiple simultaneous goals with prioritization logic. Produces FINANCE-GOALS.md.
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。
Add a new chain to an existing warp route owned by a customer. Reads a Linear ticket, adds the new chain to the deploy.yaml, builds a customer-specific strategy file for existing chains, runs warp apply, and outputs transaction files for the customer to sign via their multisig.
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。
Generic update orchestrator for an already-deployed warp route. Reads a Linear ticket describing any combination of warp-fee changes / ISM changes / hook changes / owner-address changes / additional-collateral-chain additions, edits the registry deploy.yaml accordingly, builds a per-chain strategy file from the artifact-context owner classifications, runs `hyperlane warp apply`, fork-simulates the resulting receipts via `/warp-route-check`, and hands off to `/warp-update-propose` to land the proposals. Chain extension (adding a brand-new chain with new on-chain contracts) is a separate skill — see `/warp-update-extend`.
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。
Trigger Docker image builds for Hyperlane agent, monorepo, or node service images. Use when the user wants to build new Docker images for a branch, commit, or tag.
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。
Guide a researcher step by step into an unfamiliar research field, or decode a paper, abstract, figure caption, or referee comment they cannot parse. Builds understanding in rungs (motivation, vocabulary, core framework, methods, frontier), anchored to what the user already knows, with a checkpoint before each advance. Use when the user says they are new to a field, asks what a research area or method is, says an explanation was too technical, asks to be walked through something step by step, asks for a reading path, or supplies dense research text. Trigger even when the user only names an unfamiliar field or pastes an abstract without asking to be taught. Do not trigger for a one-line summary, a short overview request, or a direct factual answer; do not use it for translation, editing, search, debugging, or specialist questions inside the user's own field. Also trigger in other languages, including Chinese such as 入门, 一步一步讲, 看不懂, 这篇论文讲什么, 帮我理解这个领域.
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。
Provides Docker and containerization best practices including multi-stage builds, security hardening, and compose patterns. Use when writing Dockerfiles, optimizing images, setting up containers, or when user mentions 'Docker', 'container', 'Dockerfile', 'docker-compose', 'image'.
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 dispatching a multi-agent team, run a spectral diagnostic on the proposed communication graph and emit a (ρ, Δ, κ) coordination signature plus a pass/fail verdict against per-task-class thresholds. Builds the row-stochastic operator P from the team graph, computes the successor representation M = (I − γP)⁻¹, and ranks the topology for robustness (κ, condition number), consensus (Δ, spectral gap), and drift (ρ, spectral radius). Per Parks & Alharthi (arxiv 2605.11453), rank order on (κ, Δ, ρ) predicts coordination quality pre-execution with rank correlations of 1.0 / 0.5 / −1.0. Triggers: "dispatch the team", "team topology check", "before running the agents", "is this team configuration OK", "team pre-flight".
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, validate, and use DACP bundles as structured execution context. Detects .bundle/ companion directories, validates integrity (manifest schema, fidelity, provenance), loads typed data, and builds ExecutionContext for receiving agents. Scripts are NEVER auto-executed. Use when processing incoming DACP bundles, interpreting .bundle/ directories alongside .msg files, validating bundle integrity, or building execution context from bundle payloads.
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。
Launches and supervises long-running commands — solves, workflows, downloads, builds — detached with a log, PID and exit sentinel, then tells stuck from slow and kills verifiably. Use before running anything that may exceed a minute, for nohup or background launches, and when a run hangs, shows no output, or timed out.
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。
Grooms a GitHub milestone for parallel execution — batch-grooms ungroomed items, assesses scope gaps, analyzes cross-item dependencies via Impact Radius overlap, builds conflict groups, assigns items to execution waves, and persists the dispatch plan via dispatch_create_plan MCP tool. Calls dispatch_wave_start per wave to register state. Use when preparing a milestone for /work-milestone execution. Pass the milestone number as the first argument. Requires milestone items assigned via /group-items-to-milestone.
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。
Builds comprehensive Claude Code skills using parallel research agents — categorization, parallel documentation gathering, anti-hallucination checkpoints, and final validation. Use when building a skill from official docs, when "research for skill" or "create comprehensive skill" is requested, or when extensive multi-source documentation gathering is needed before skill creation.
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 an award-winning "3D scroll" website of ANY kind from ONE prompt — product launch, portfolio, agency, contractor/home-services, restaurant, real estate, personal brand, event, app, etc. Generates a high-end cinematic hero visual + clips (360° orbit, fly-through, reveal, explode, parallax) fitting the site's subject with the Higgsfield MCP, slices them into a scroll-scrubbed canvas frame sequence with ffmpeg, builds a branded multi-section site (Lenis smooth scroll + scroll reveals), and launches it on localhost. Use when the user asks for a "3D scroll" site, scroll-driven hero/reveal, a cinematic landing page, a buckssauce/Apple/Awwwards-style scroll site, or "build me a website like X" — for a product OR a service, person, place, or brand. Trigger words: 3D scroll, scroll animation, cinematic hero, fly-through, turntable, scroll site, landing page, portfolio site, agency site, Higgsfield site.
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。
Opt-in recreation of the Bun + TypeScript framework used to build Vapi's landing-page voice agents from a ROUGH_DRAFT.md spec, including a scenario registry, language stacks, prompt composer, assistant builder, and idempotent bootstrap script. Use only when the user explicitly invokes vapi-bootstrap-framework or specifically asks to reproduce or experiment with the landing-page-agent architecture. Do not use for ordinary Vapi assistant builds; use create-assistant, create-tool, create-squad, and vapi-prompt-builder instead. Targets Bun + TypeScript + @vapi-ai/server-sdk.
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。
OCRs scanned or image-only corpora with vision-language models in three phases. Evaluate selects a system by measured CER or WER against stratified human ground truth. Run builds the production pipeline. Clean corrects raw OCR with LLM and rule-based passes, quality diagnostics, and span-level provenance. Use when choosing an OCR model for a corpus, measuring OCR accuracy, transcribing scans at scale, or correcting raw OCR. Born-digital documents with text layers go to doc-to-markdown.
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。
Organizes an author’s response to peer review. Extracts every referee and editor point, tags severity and type, orders the revision by dependency, flags defensible pushbacks as questions, and builds a numbered comment → response → location letter whose substantive answers the author writes. Use when the user has referee reports, a revise-and-resubmit decision, or an editor’s letter and wants to plan the revision, draft the response letter, or check that every point was addressed. The reviewer-side twin is journal-review.
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。
Typesets a working paper or journal submission in house-style LaTeX from Markdown, Word (.docx), TeX, ODT, RTF, or HTML. Converts with pandoc, wraps the body in an EB Garamond template, builds the PDF with latexmk, and sets journal-specific spacing, page limits, anonymization, disclosures, and citation style. Use to format or convert a paper to LaTeX, make a working paper, or prepare a submission to a named journal.
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。
Builds or audits a literature review, producing an evidence map, the closest prior work, source clusters, a gap verdict, and a synthesis plan for the introduction. Use when the user asks whether a contribution is novel, who has studied a question, what the literature establishes, or how to organize a review, or wants a reading list, Zotero export, or pile of papers turned into one. For systematic reviews or meta-analyses it produces the protocol scaffold and routes registration (PROSPERO or OSF) and screening to dedicated tools.
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。