1,893 件 ・ 関連度順
概要と使いどころ
Install and initialize OneCLI Agent Vault. Migrates existing .env credentials to the vault. Use after /update-nanoclaw brings in OneCLI as a breaking change, or for first-time OneCLI setup.
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。
Check the local environment for Spec Kit by running `specify check` (and `specify version`). USE FOR: verifying required tools are installed, diagnosing a broken spec-kit setup, reporting CLI version/feature capabilities. DO NOT USE FOR: installing or upgrading the CLI itself (use the speckit-self skill).
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。
Upgrades Python pip/poetry/pipenv dependencies with breaking change handling
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。
Generates sustainability-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Google Cloud Well-Architected Framework (WAF). Use this skill to evaluate a workload, identify environmental impact requirements, and provide actionable recommendations to build, deploy, and manage the workload sustainably in Google Cloud.
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。
Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.
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。
Plan, create, and configure production-ready Google Kubernetes Engine (GKE) clusters using the golden path Autopilot configuration. Covers Day-0 checklist, Autopilot vs Standard, networking (private clusters, VPC-native, Gateway API), security (Workload Identity, Secret Manager, RBAC hardening), observability, scaling, cost optimization, and AI/ML inference. WHEN: create GKE cluster, provision GKE environment, design GKE networking, secure GKE, optimize GKE cost, GKE autoscaling, GKE inference, GKE upgrade, GKE observability, GKE multi-tenancy, GKE batch, GKE HPC, GKE compute class.
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 morphir-scala work needs environment diagnostics or build/network/sandbox unblocking; reference repository management; branch lifecycle refresh after squash-merging a target branch into main; Morphir IR spec/schema sync or export; or task-tracking configuration and beads mode resolution.
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。
Scan projects for credential leaks, secrets in code, insecure patterns, LLM API key exposure, PII leakage to external AI services, and .env/.gitignore misconfigurations. Especially useful for data and API integrations, regardless of implementation 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。
Unified verification engine for Python data science projects. Covers environment checks, type checking, linting, tests, security scans, code review with DS anti-patterns, and notebook checks. Commands (/verify, /quality-gate) invoke different subsets of this skill.
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。
Team conventions for Python development — credentials, API clients, LLM response parsing, testing patterns, and data pipeline structure. Covers dotenv loading, retry logic, secret validation, and pipeline anti-patterns.
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。
Inspired by the ClawIntelligentMemory project, this skill ensures Kim Assistant's environment stays clean and its memory stays dense.
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。
Securely inject secrets from 1Password into agent workflows. Uses service accounts with op run/.env.tpl as the primary pattern, op read as fallback. Includes hardened security rules, input validation, and troubleshooting for auth/permission failures. Use when accessing API keys, credentials, or any 1Password secret.
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, implement, or review dygo HTTP APIs and public App SDK contracts. Use for Record APIs, metadata and boot endpoints, query behavior, response envelopes, compatibility, and public Go 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。
Query and filter Datadog logs from the shell using the Composio CLI. Run scoped log searches, pivot across services/environments, and export structured JSON for incident investigation and diagnostics.
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。
Safe deployment workflow for Drupal 10/11 sites: pre-flight checks, backup, the correct update sequence (composer install, database updates, config import, cache rebuild), verification, and rollback plan. Use when deploying to any environment, releasing to production, or when the user asks to "push changes live", "update the server", or run a release. Also use for multisite releases where each site needs its own database update pass.
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 authoring or debugging GitLab CI/CD pipelines (.gitlab-ci.yml) — e.g. "add a CI pipeline for this Drupal project", "run phpcs/phpstan/phpunit in GitLab CI", "deploy with drush from a pipeline", "why is my job not running", "cache composer dependencies", or anything involving stages, rules, artifacts, environments, or GitLab runners.
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 operational Drupal 11 workflows in DDEV environments, including safe updates, backup-first procedures, and troubleshooting commands.
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。
Delegate implementation to Codex, grok, or cursor-agent, then review the diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex, the grok 后端, or cursor-agent to write code, mentions handing off / delegating implementation to one of those backends, asks to work through a plan or spec unit-by-unit with an implementation backend doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer runs in the real environment behind backend-specific git and publication boundaries, must not be pointed at a full test suite by default, and its self-report is a claim rather than evidence. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the engineering-mode skill when it is installed.
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 when: (1) the user mentions "manim", "scene", "video", "EN/KO render", "GEODE_HERO_LANG", "1080p60", or (2) editing files under `scripts/visualizations/` ending in `.py`, or (3) the user asks to render, re-render, or extend any of the four validated scenes (`geode_hero.py`, `autoresearch_filewalk.py`, `autoresearch_compare.py`, `critical_floor.py`). GEODE Manim Scene authoring standard. Locks the patterns the four validated scenes already share — Anthropic-style palette, Helvetica Neue + Pretendard font pairing with weight=NORMAL, EN/KO multilingual lang via `GEODE_HERO_LANG` env, `_dashed_arrow_with_head` stage-coupled tinting, `verify_hero_layout.py` ratchet — so the next scene does not re-discover the kerning / padding / transition regressions catalogued in [[viz-frame-audit]].
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。
GitHub workflow automation with the gh CLI — pull requests, issues, releases, the REST/GraphQL API, and safe message escaping. Auth via GH_TOKEN (set in global settings, attached to the sandbox env).
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。
GitLab workflow automation with the glab CLI — merge requests, issues, CI, releases, and safe message escaping. Auth via GITLAB_TOKEN (set in global settings, attached to the sandbox env).
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。
host / 辅助段优化模块（L3）：把**非 DiT、非解码段**的固定开销落成可复验的优化—— ① 交付与搬运（mp4/图片编码、worker→API 通路、落盘、异步化）； ② 装载与预热（权重加载、编译与图下发预热、镜像/容器预热）。 当用户说“mp4 编码/传输/落盘慢”“交付这段占了不少时间”“模型加载慢”“首启编译太久” “固定开销占比高”“每个请求都要重新编码/重新写盘”时使用。 **入口条件**：占比已达门限（瓶颈标签 `非DiT-host段`；标签枚举、门限与测点口径的单一真源在 model-auto-optimization/references/bottleneck-labels.md，本技能只消费不定义）。 near-miss（看似相关但不属本技能）： - **并发 / 吞吐 / 批处理调度 / 队列深度与限流** → **不属本技能**（会改变所有性能口径与 SLO 语义， 未来独立立项；本技能只在**不改变请求并发模型**的前提下压固定开销）； - VAE/TAE 解码段（计算或通信）→ `vae-opt`；DiT 计算 → `dit-perf-opt`； 多卡并行 / 通信掩盖 → `dit-parallel-opt`； - **装库 / 下载权重 / 构建镜像 / 创建容器** → `env-install`（本技能只优化装载与预热**过程本身**）； - 编译与图下发的**机制本体**（pattern / Inductor / NPUGraph / 图 pool / 缓存条目）→ `pattern-dev` / `aclgraph-dev`（本技能不另做一套缓存）； - 产物一致性与精度判据 → `accuracy-gate`；收益口径 → `perf-gate`； - 瓶颈未定位 / 没有占比锚点 → `model-auto-optimization`。
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。
三方框架特性落地（原 framework-feature-enablement ＋ framework-extension-dev 合并）： 一个入口信号「框架侧特性没落地」，内部分两分支——**分支 A 框架已有 → 使能与验证** （计数契约 + 三层证据 + 使能异常回修）；**分支 B 框架缺失 → 补齐开发** （注入点 + 代码组织/注册机制 + 合入姿势：平台注册优先 / 上游 PR / fork 钉版 / monkey 备选）。 分支 A 触发词：量化/稀疏/缓存开关没生效、融合算子没命中、使能异常或精度不符、 "起 vllm 服务""模型在框架里跑不通""把 mindiesd 接到其他框架"。 分支 B 触发词：框架没 comm-stream 掩盖、框架没缓存消费者、框架不支持某 collective/mask、 feature_* NotImplemented、要给框架补一条结构性能力。 near-miss：纯安装/权重 → env-install；纯采集/分析 → profiling-collect / profiling-analyze； 纯选档（该不该开量化、开哪一档）→ dit-perf-opt； mindiesd 仓内 pattern / 算子 / 图下发开发 → dev-workflow + pattern-dev / operator-dev / aclgraph-dev。 由 model-auto-optimization 的 S1（融合接入）/S4（有损使能）/S5（训练感知）与 §0 缺口补齐策略路由， 亦由 dev-workflow 的框架接入/验证场景指引加载。
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。
多模态模型自动优化流程总入口（编排层）：把一个三方框架托管的扩散模型从环境准备到无损/有损 优化自动跑完。任务判定后按 S0 环境准备、S1 kernel 融合优化（原 S1/S2 合并）、S3 并行通信、 S4 有损优化、S5 训练感知（预留，少步蒸馏 + SLA/QAT）、闭环复验路由到能力技能（env-install / framework-integration / profiling-collect / profiling-analyze / performance-optimization / dit-parallel-opt / dummy-run 等），检查各阶段产物与验收并回填经验槽位。 当用户需要对具体模型做框架接入、无损/有损加速、并行调优或确认收益时使用本入口；即使用户只提 模型名加"优化/加速/跑通/采profile"而未说框架或阶段，也应由本入口判定路由。仓库代码开发类任务 请走 dev-workflow。流程执行/验收按 workflows/optimization-flow.md，run-state + stage_gate 门禁。
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。