2.4K skills · sorted by relevance
Create or update hierarchical AGENTS.md files that explain a project's structure, commands, and conventions. Analyze directory complexity to choose useful locations, then keep local guidance concise and avoid repeating parent instructions.
Use this skill when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and running the `gpunetio_ib_write_lat` client + server pair under `doca/tools/gpunetio_ib_write_lat/`, checking GPU-NIC pairing, reading the half-iter / full-iter / CUDA-side usec columns, characterizing median / p99 / jitter for a real-time control loop, picking GPUNetIO vs GPI vs CPU-initiated `perftest`, or weighing the latency-vs-batching trade-off. Trigger even without 'GPUNetIO' or 'ib_write_lat': 'GPU kernel RDMA latency benchmark', 'how fast can a CUDA kernel post a WRITE', 'p99 RDMA latency on H100 + ConnectX', 'kernel-launched WR tail latency', or 'compare GPU-init vs CPU-init perftest'. Route elsewhere for bandwidth runs (doca-gpunetio-ib-write-bw), the GPI surface (doca-gpi), library debugging (doca-gpunetio), or DOCA install.
The English summary is being prepared. Showing the original description.
Use this skill when the user is doing hands-on DOCA RDMI (RDMA Initiator) programming — picking doca-rdmi vs doca-rdma for an accelerator-initiated one-sided RDMA flow, standing up a doca_rdmi_connection or doca_rdmi_poster, attaching a doca_dpa_completion or doca_verbs_cq before doca_ctx_start(), retrieving the DPA-side handle for a DPA kernel, auditing whether a doca_rdmi_* symbol is EXPERIMENTAL on this DOCA, or debugging DOCA_ERROR_* returns from RDMI calls. Trigger even when the user does not say "DOCA RDMI" or "initiator" — implicit phrasings include "my DPA kernel needs to post RDMA writes to a remote responder", "DPA kernel sees no completions", "function not found on doca_rdmi_* at link time", "DOCA_ERROR_BAD_STATE from completion attach", or "the DPA posted but the work request never arrived". Refuse and route elsewhere for two-sided or host-CPU RDMA, the DPA programming model, GPU-side RDMA initiation, or general RDMA/IB/RoCE concepts — those belong to other skills.
The English summary is being prepared. Showing the original description.
Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server benchmark — a CUDA kernel on the client posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE bandwidth on a GPU+IB-device pair. Trigger even when the user does not explicitly mention "doca-gpunetio-ib-write-bw" or "GPUNetIO" — typical implicit phrasings include "measure WRITE BW when the GPU posts the WRs", "BW swings between runs on the same flags", "is the NIC saturated or am I CPU-bound on the CUDA kernel", "meson compile fails for the GPUNetIO bw tool", "nvidia_peermem isn't picking up my GPU buffer", or "GPU-initiated WRITE throughput vs CPU-initiated perftest". Refuse and route elsewhere for general doca-gpunetio library work, DOCA install, the GPU-initiated WRITE latency analog, the CPU-initiated upstream perftest, or application-level end-to-end throughput — those belong to other skills.
The English summary is being prepared. Showing the original description.
Initialize uc-taskmanager for the current project. Creates works/ directory and configures Bash permissions in .claude/settings.local.json. Use when the user says "uctm init", "initialize uctm", "uctm 초기화", or "초기화".
The English summary is being prepared. Showing the original description.
Allocate a finite budget or headcount across competing initiatives by return and strategic fit. Use when asked to allocate budget, decide where to invest, build a funding/portfolio plan, or make trade-offs across initiatives under a cap. Produces a capital-allocation plan — initiatives scored by expected return × strategic fit per dollar, a funded/unfunded split against the cap, the cut line, and the reasoning.
The English summary is being prepared. Showing the original description.
First-time Archcore setup. Wires the host (MCP config, hooks, CLAUDE.md/AGENTS.md managed block), measures the authored context the repo already holds, then composes a first-day seed — stack rule, run guide, data-model, integrations, config, entry points, public surface, a linked architecture overview, and specs for the top hotspot modules — shown in ONE preview and created on a single confirm. Modes, named as the first word: init import converts the repo's authored context — CLAUDE.md, AGENTS.md, .cursor/rules and other agent instructions, ADR and RFC folders, contributor docs, internal pages of a published docs site, recoverable git history — into native typed documents with no import marks, staged by a plan when the volume is large; init refresh adds facts that appeared since, or drills into one domain with init refresh <domain>. Use on a fresh clone, empty `.archcore/`, 'set up archcore', 'migrate our CLAUDE.md to archcore', 'import our docs and ADRs', or to wire host configs. Not for individual docs or planning.
The English summary is being prepared. Showing the original description.
project-init 的兼容别名；当用户按 cc-use-exp 前缀显式调用 cc-project-init 时，转入标准 project-init 初始化流程。
The English summary is being prepared. Showing the original description.
Initialize a Harness Engineering framework in the current project. Use when user says 'harness', 'init harness', 'initialize framework', 'setup harness engineering', '/harness', or wants to set up a Plan-Build-Verify development workflow with specialized agents (planner, generator, evaluator). Creates CLAUDE.md, agent definitions, command templates, hooks, and documentation structure for autonomous AI-driven development.
The English summary is being prepared. Showing the original description.
One-time setup for absolute: interview how you want it to behave (output style, autonomy, TDD strictness, spec dir, families) + detect the stack once, then write `.absolute.config.json` (project, committed) and `~/.absolute/config.json` (user defaults + per-project overrides). Every other absolute-* command reads it instead of re-detecting; non-blocking — commands proceed without it and soft-recommend it. Triggers on "absolute init", "set up absolute", "initialize absolute", "configure absolute", "first-time setup", "remember my conventions for this repo".
The English summary is being prepared. Showing the original description.
Seed a fresh (greenfield) repository with the PRD-Driven Context Engineering scaffold — PRD.md, SoT/ knowledge files, EPIC templates, domain-profile config, and agent MEMORY starters. Invoked as /prd-ce:init when the plugin is installed. The framework itself (skills, agents, hooks, scripts) ships LIVE in the plugin; this skill only plants the consumer-owned files the plugin cannot carry as behavior. Triggers on "/prd-ce:init", "set up PRD lifecycle here", "scaffold a new PRD-CE project", "initialize the methodology". Outputs a seeded scaffold + a verification report.
The English summary is being prepared. Showing the original description.
Use before proposing error definitions (propose_error_definitions) - how to read an error group, pick its category and action, write a match that catches one kind of error and nothing else, and when a definition should not be proposed at all
The English summary is being prepared. Showing the original description.
Initialize the UniKit framework in a project. Scans the current project to detect the engine and real tech stack, then generates the base framework documents that give AI agents context about the project — the resolved project description, the architecture doc, AGENTS.md, and the user-editable .unikit/config.yaml. This is the one-time, whole-project setup run before any other unikit skill. Use whenever the user wants to initialize, set up, or onboard the framework, e.g. "initialize unikit", "init the framework", "set up unikit", "set up the project", "configure AI context", "scan my project and set it up", "bootstrap the project". It also actualizes the config of a project already set up — say "update the config", "add missing settings", "actualize configuration", "fix my config".
The English summary is being prepared. Showing the original description.
工程ごとの完了判定、品質ゲート、証跡、標準検証コマンド、例外運用を設計するスキル。 実装完了・テスト実施・品質確認完了・出荷可能を分離し、再利用可能な gate matrix を作る。 「全OK」「完了」などの曖昧な完了表現を排除し、証跡に基づく退出条件を定義する。 Use when defining Definition of Done, quality gates, exit criteria, release readiness gates, evidence requirements, exception handling, or standardized verification commands. Covers: definition of done, quality gate, exit criteria, release readiness, 完了判定, 品質ゲート. Distinct from project-completeness-scorer (which scores) -- this skill designs the gates and criteria themselves.
The English summary is being prepared. Showing the original description.
Turns a list of KPIs or metrics into a DRAFT definition sheet: one row per KPI with the name as stated, formula quoted from a source, source system, owner, refresh cadence, unit, filters and known caveats, with UNKNOWN in every cell no source fills and a gap list grouped by data owner. Never composes a formula, sets a target or names an owner the sources do not state. Use when the user asks to "define these KPIs", "build a metrics definition sheet", "document how each KPI is calculated", "which of our KPIs have no owner or formula" or "reconcile the two KPI lists". Do not use for the weekly numbers report, use kpi-weekly-report-writer instead; for field-level definitions of a table, use data-dictionary-builder; for logging a wrong figure as a defect, use data-quality-issue-log. Drafts for human review; never approves, authorises or signs off.
The English summary is being prepared. Showing the original description.
Registers a custom WooCommerce shipping method with explicit control over which fields appear in the per-zone settings modal — extend WC_Shipping_Method, declare your fields in init_form_fields (and ONLY those fields, no unset / DOM hacks / CSS hides), set the $supports array to control whether the modal opens (omit 'instance-settings' to suppress it entirely), register via the woocommerce_shipping_methods filter, load the class on woocommerce_shipping_init. Corrects the "this is React, removing fields is hard" misconception — the zone-method modal is Backbone with a PHP-rendered settings_html string; the field list is wholly PHP-controlled. Use when scaffolding a shipping method or when you want a feature-flag-only modal without WC defaults. Triggers on WC_Shipping_Method, woocommerce_shipping_methods, woocommerce_shipping_init, init_form_fields with shipping context, $supports shipping-zones, calculate_shipping, add_rate, or "remove default fields from shipping method".
The English summary is being prepared. Showing the original description.
既存プロジェクトをサブエージェントで並列分析し、 精度の高い overview.md を生成する。init-spec の前処理として使う。 「既存プロジェクトを分析して」「コードベースを理解して設計書を作って」 「overview.mdを作って」などのリクエストで使用する。 ファイル数が200を超えるプロジェクトで特に有効。 200以下の場合は単一エージェントで全体を読む方が精度が高いため、 init-spec をそのまま実行することを提案する。
The English summary is being prepared. Showing the original description.
プロジェクト（特にこのテンプレートから始める新規プロジェクト）にClaude Code用の.claude/環境を対話形式で段階的にセットアップする。settings.jsonの権限・hooks設定、必要に応じたカスタムskill・command・subagentの雛形作成、CLAUDE.mdのビルド/実行/テストコマンド欄の穴埋めを行う。「セットアップして」「環境構築して」「init」「このプロジェクトでClaude Codeを使えるようにして」「開発を始めたいので準備して」といった依頼で積極的に使うこと。エンジニアが常駐しない・少ない組織で「事故らないようにしたい」「危険な操作を防ぎたい」「lint/testやセキュリティレビューが誰もチェックしないまま放置されるのを防ぎたい」といった要望がある場合も、権限・hook・レビュー体制を通じた安全網の構築としてこのスキルが対応する。既存の/initスキルはCLAUDE.mdのコードベースドキュメント生成に特化しているが、権限設定やskill/command/agentの追加が絡む場合は必ずこちらを使う。
The English summary is being prepared. Showing the original description.
Build, scaffold, and deploy Power Automate cloud flows using the FlowStudio MCP server. Your agent constructs flow definitions, wires connections, deploys, and tests — all via MCP without opening the portal. Load this skill when asked to: create a flow, build a new flow, deploy a flow definition, scaffold a Power Automate workflow, construct a flow JSON, update an existing flow's actions, patch a flow definition, add actions to a flow, wire up connections, or generate a workflow definition from scratch. Requires a FlowStudio MCP subscription — see https://mcp.flowstudio.app
The English summary is being prepared. Showing the original description.
Configure a Claude hook, a check before tool execution, that pauses initial edits and file creation to request concrete facts. It prompts investigation of callers, data structures, and user instructions, with separate checks for destructive commands.
Set up gbrain so a coding agent can call it. Install its command-line tool, initialize a local PGLite or Supabase brain, register MCP, the agent connection mechanism, and record trust policies for each remote.
Audit page loading and defer offscreen images, videos, iframes, and heavy components until needed. Use measurements and page context to identify suitable changes while keeping images needed for the initial view loaded with priority.
Find optional features that slow the first page load and defer their code until a user interacts. Use dynamic imports, which load code on demand, and add immediate loading feedback while preserving the initial page experience.
Review CSS custom properties, often called CSS variables, used in animations and transitions. Add @property registrations with value types, initial values, and inheritance settings to support smooth changes and validate assigned values.