效率提升技能

Executes plans.json tasks — solo, parallel, or breezing team mode. Use when implementing tasks or running the work loop.

中文简介正在准备中。当前显示原文说明。

Plans and tracks tasks in .claude/harness/plans.json. Use when creating plans, adding tasks, updating markers, checking progress, or brainstorming an idea into tasks.

中文简介正在准备中。当前显示原文说明。

Initializes and configures Harness in a project — CI, memory, duo workflow, Codex. Use when setting up a new project or adding Harness configuration.

中文简介正在准备中。当前显示原文说明。

Use when scoring finished content against quality dimensions, evaluating whether a piece meets publishable standards, or determining which workflow phase needs rework based on quality gaps.

中文简介正在准备中。当前显示原文说明。

Issue または ExecPlan を、人の確認を待たずに「準備 → 実装 → 範囲の照合 → 検証 → 自己レビュー → push → PR」まで役割を分けて進めるスキル。`/run-issue <番号>`・`/run-plan <ExecPlan のパス>`・`/finish-task` を提供する。ユーザーが「/run-issue」「/run-plan」「Issue を自走で直して」「ExecPlan を最後まで進めて」「0 節の Issue を順に片付けて」と依頼したときに使う。ExecPlan を作るだけなら exec-plan、次のタスクを選ぶだけなら roadmap-manager を使う。

中文简介正在准备中。当前显示原文说明。

Issue または ExecPlan を、人の確認を待たずに「準備 → 実装 → 範囲の照合 → 検証 → 自己レビュー → push → PR」まで進めるスキル。`/run-issue <番号>`・`/run-plan <ExecPlan のパス>`・`/finish-task` を提供する。ユーザーが「/run-issue」「/run-plan」「Issue を自走で直して」「ExecPlan を最後まで進めて」「0 節の Issue を順に片付けて」と依頼したときに使う。ExecPlan を作るだけなら exec-plan、次のタスクを選ぶだけなら roadmap-manager を使う。

中文简介正在准备中。当前显示原文说明。

Hand a sub-task to another agent, a specialist model, or a background job.

中文简介正在准备中。当前显示原文说明。

Track multi-step work with todo, plan mode, kanban and missions.

中文简介正在准备中。当前显示原文说明。

Take a change from branch to merged pull request, CI included.

中文简介正在准备中。当前显示原文说明。

Evolution CMS JP Editionの開発タスクを実行するためのワークフロー、コマンド(/work, /start-session等)、およびコーディング規約ガイド。開発作業を開始する際に使用します。

中文简介正在准备中。当前显示原文说明。

ロードマップ（`.agent/roadmap.md`）を運用するスキル。タスクの追加・変更・削除、次タスクの選定（`/next-task`）、完了同期（`/roadmap-sync`）を扱い、着手時に改修規模で ExecPlan の要否を判断する。選んだタスクの実装から PR までは exec-plan-runner に渡す。「次のタスク」「/next-task」「ロードマップに追加」「ロードマップを同期」と依頼されたときに使う。

中文简介正在准备中。当前显示原文说明。

ExecPlan（実行計画）の作成・検証・更新を支援するスキル。複雑なタスク（新機能開発、リファクタリング、バグ修正）の設計フェーズで使用します。`/create-plan`でプラン作成を開始。

中文简介正在准备中。当前显示原文说明。

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

中文简介正在准备中。当前显示原文说明。

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

中文简介正在准备中。当前显示原文说明。

Manage SVG icons as framework components using Denji CLI. Use when the user needs to add, remove, list, or manage SVG icons in React, Preact, Solid, Qwik, Vue, or Svelte projects. Triggers include requests to "add an icon", "set up icons", "manage SVG icons", "remove an icon", "list icons", or any task involving Iconify icons as framework components.

中文简介正在准备中。当前显示原文说明。

Work with the @upstash/workflow TypeScript/JavaScript SDK for durable, long-running workflows in serverless functions, multi-step processes that survive timeouts, retries, and restarts (built on QStash). Use when defining a workflow endpoint with serve(), running steps with context.run, sleeping for minutes to days without holding a function open, calling external APIs with context.call, waiting for an external event or webhook, invoking other workflows, configuring retries, failure callbacks, and a DLQ, controlling concurrency, rate, and parallelism, triggering, cancelling, or inspecting runs with the Workflow client, building AI agents and orchestrators, human-in-the-loop approvals, realtime updates, local development with the QStash dev server, adding middleware, or migrating workflows safely. Also use when the user asks for durable execution, step functions, saga or orchestration patterns, background jobs with checkpoints, or long-running tasks on Vercel, Next.js, Cloudflare Workers, or other serverless platforms.

中文简介正在准备中。当前显示原文说明。

Full Stock Analysis Orchestrator — launches 5 parallel subagents via delegate_task for comprehensive multi-dimensional stock analysis with composite Trade Score (0-100). Triggered by "trade analyze <TICKER>" or "analyze <TICKER> stock".

中文简介正在准备中。当前显示原文说明。

Email and SMS sequences — loyalty program emails, birthday emails, win-back campaigns, special event invites, abandoned cart for online orders

中文简介正在准备中。当前显示原文说明。

Handles git workflow: creating branches, atomic commits with conventional prefixes, PR creation with structured summaries, keeping PR descriptions updated on follow-up pushes, and post-merge cleanup. Use when the user asks to commit, create or update a PR, push changes, address PR feedback, or says a PR was merged.

中文简介正在准备中。当前显示原文说明。

End-to-end automated model quantization and accuracy tuning workflow. Use when user asks for automated model quantization and accuracy tuning, e.g. "自动量化", "量化调优", "一键量化", "精度调优", etc. 当用户给出多卡（≥2 卡）卡号时，量化阶段通过 EP 并行适配（msmodelslim-ep-parallel-adaptation）保证多卡 EP 并行，调优主流程仍在本 Skill。

中文简介正在准备中。当前显示原文说明。

Aggregate DiT inference outputs into per-dimension VBench metrics via AISBench. Run after the quant-tuning-evaluate DiT workflow produces a directory of mp4s and the user supplies a VBench-1.0-mini JSON + pre-populated cache dir. Single mode (Standard).

中文简介正在准备中。当前显示原文说明。

Compile, profile, diagnose, optimize, and compare Ascend NPU operators across CANN versions and A2/A3/A5 for Ascend C, CATLASS, Triton-Ascend, TileLang-Ascend, PyPTO, and SHMEM/MC2. Use when an operator already has a runnable implementation and the user asks for msOpProf collection, bottleneck analysis, source-level tuning, or a reproducible before/after performance report. Do not use as the primary workflow for operator creation, migration, or unresolved correctness failures.

中文简介正在准备中。当前显示原文说明。

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

中文简介正在准备中。当前显示原文说明。

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

中文简介正在准备中。当前显示原文说明。