1,375 件 ・ 関連度順
概要と使いどころ
Use when the user asks to "log this subscriber's opt-in", record unsubscribes/complaints, or query lawful basis; curates pseudonymous consent facts through the append-only consent stream and applies suppression/erasure tombstones immediately. Not for SEND scoring — use email-quality-auditor; not for building segments — use list-segment-builder. 订阅同意台账/实时退订抑制/合法性依据登记
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 asks to register/query a social channel, record channel state, cadence, governance, voice adaptation, UGC permission, or advocacy facts; curates them through the append-only channels event stream and derived views. Not for ECHO scoring — use social-quality-auditor; not for channel selection — use channel-portfolio-planner. 渠道台账/账号档案/UGC授权记录
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。
Deep, iterative internet research for current facts, source triangulation, contradiction checks, due diligence, competitive analysis, claim verification, "latest" lookups, and cited reports. Use when the user asks to browse, search, research the web, verify claims, compare sources, gather primary sources, investigate companies, people, products, technical topics, news, events, markets, or create AKBP-ready durable research evidence.
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。
Configures GitHub Actions CI/CD workflows for Flutter projects. Use when creating or editing `.github/workflows/` YAML files for Flutter, integrating subosito/flutter-action, automating `flutter test`, `flutter analyze`, or `dart format` on push or pull_request events, running build_runner in CI, building Android AAB or iOS IPA artifacts, managing keystore or signing secrets in GitHub Secrets, or combining GitHub Actions with Fastlane or Codemagic for the deployment stage.
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。
Prepares mobile releases across Flutter, native Android, native iOS, React Native and Kotlin Multiplatform, including separate Android/iOS artifacts from a shared KMP revision. Covers versions, signing, symbols, store readiness, rollout, release notes and CI/CD. Use for release audits, store submission, build pipelines or rollout planning.
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。
Automate CircleCI tasks via Rube MCP (Composio): trigger pipelines, monitor workflows/jobs, retrieve artifacts and test metadata. Always search tools first for current schemas.
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。
Azure Container Registry SDK for Python. Use for managing container images, artifacts, and repositories.
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 for Nauthilus Lua plugins, Lua callback tests, policy compiler and registry work, Lua environment and subject sources, Lua actions, hooks, backend scripts, policy facts, obligation targets, `server/lualib`, `server/lua-plugins.d`, `server/policy`, and JSON fixtures under `testdata/lua`.
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 for Nauthilus configuration loading, config schema and defaults, Viper-backed config formats, config dump behavior, vim syntax generation, template validation, prompt guideline sync, documentation under README/IDP/server docs, config converters, and generated documentation or syntax artifacts.
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 running the dev Grafana stack and/or the Playwright e2e suite against a *packaged* plugin zip (a release/RC artifact like `hydrolix-hydrolix-datasource-<ver>.zip`) rather than the working-tree `dist/`. Unpacks the package into a timestamped `dist_<timestamp>/dist` sandbox alongside copies of the compose artifacts, so the run is reproducible and the folder stays available to experiment with afterwards. Delegates stack bring-up to `stack-run` (frozen mode: read-only mount + `DEV=false` so the mage-watcher can't rebuild the packaged Go binary), verifies signature/version, runs the suite, and treats cleanup as optional — the sandbox is deleted only with the user's approval. Apply whenever the task is "test this plugin package / zip" or "run e2e against the built artifact".
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 starting, stopping, or inspecting the dev stack for this Hydrolix Grafana datasource plugin — Grafana (with the plugin bind-mounted), ClickHouse, Keycloak (OAuth), and the on-demand playwright runner. Covers `docker compose up` semantics, the `dist/` prerequisite, serving plugin artifacts from an alternate folder (any path, live or frozen, via an ephemeral compose override), switching Grafana versions, hot-reload behaviour, delve attach, log streaming, OAuth/anonymous auth, and ClickHouse fixture access. Apply whenever a task needs the plugin running locally, needs to reset the stack, or needs to debug why Grafana won't come up.
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。
Derive slices from specs, order by dependencies, write acceptance criteria with citations, and finalize phase/progress artifacts
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。
Per-screen design spec generator for AI design tools (Stitch / Figma AI / Claude artifacts). Consumes per-feature PRDs from kta-prd-pipeline. Emits tool-agnostic markdown specs. Triggers — design spec, AI design prompt, screen mockup brief, Figma AI input, Stitch prompt, design system tokens, post-PRD design phase, generate design specs, design brief, mockup spec. DOES NOT generate Compose code, Kotlin code, or @Preview stubs.
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 Kotlin Compose design tokens from one of three supported sources — Google Stitch (MCP), Figma (MCP or JSON), or Claude Design (kta-design-spec output, Claude HTML/markdown artifacts). Three-layer architecture (Primitive/Semantic/Component) with code generation. Use when user asks to "generate design tokens", "create theme from Figma/Stitch/Claude design", "build Compose tokens from design spec", or "convert design source to tokens". Refuses any other input source and asks user for correct seed data.
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。
Per-screen design spec generator for AI design tools (Stitch / Figma AI / Codex artifacts). Consumes per-feature PRDs from kta-prd-pipeline. Emits tool-agnostic markdown specs. Triggers — design spec, AI design prompt, screen mockup brief, Figma AI input, Stitch prompt, design system tokens, post-PRD design phase, generate design specs, design brief, mockup spec. DOES NOT generate Compose code, Kotlin code, or @Preview stubs.
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 Kotlin Compose design tokens from one of three supported sources — Google Stitch (MCP), Figma (MCP or JSON), or Codex Design (kta-design-spec output, Codex HTML/markdown artifacts). Three-layer architecture (Primitive/Semantic/Component) with code generation. Use when user asks to "generate design tokens", "create theme from Figma/Stitch/Codex design", "build Compose tokens from design spec", or "convert design source to tokens". Refuses any other input source and asks user for correct seed data.
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 and run the owner's self-branding system in a structured way across LinkedIn, Substack, dev.to, X, profile rewrites, recurring series, and comment strategy. Use when the owner asks for positioning, a branding plan, profile updates, content drafts, a publishing sequence, comment ideas, or help maintaining a consistent public voice. Optimize for operator credibility: specific experience, defensible numbers, concrete artifacts, and category ownership.
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 working with Dbt Cloud — dbt Cloud management — monitor projects, environments, job runs, model status, and data freshness. Use when reviewing job run health, debugging failed models, inspecting run artifacts, or auditing project configuration.
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 working with Azure Devops — azure DevOps comprehensive management. Covers pipelines, boards, repositories, artifacts, test plans, work item tracking, and release management. Use when checking pipeline status, managing work items, investigating build failures, or auditing Azure DevOps project configurations.
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 working with Bentoml — bentoML model serving and packaging management. Covers service management, model packaging, deployment status, API testing, Bento building, and runner configuration. Use when packaging ML models for serving, deploying BentoML services, debugging inference issues, or managing model artifacts.
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 one-off HTML artifacts (landing, deck, prototype).
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。
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
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。
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow, 연구부터 논문까지, 연구 주제 설정부터 논문 완성까지, 논문 전체 워크플로.
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。
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
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。