1076 个 · 按相关度排序
Measure a target repository's queue and find a live open issue the contribution would close, before opening a pull request there. Reports how many PRs are open, how many of the last N closed ones were actually merged, and which issue to attach to, because a cold PR into a dead queue is a wasted artifact. Triggers: "/issue-match", "is this repo worth a PR", "measure the queue".
中文简介正在准备中。当前显示原文说明。
Use at the end of every important response. Save your decision-making thoughts as a signed A2A insight so they become training data for future fine-tuning.
中文简介正在准备中。当前显示原文说明。
Train an OpenAmer-specific small model from the collected brain data (QLoRA on NVIDIA, CPU smoke-test on laptop). 'The organism becomes its own brain' — build a fine-tune dataset, train, eval, export.
中文简介正在准备中。当前显示原文说明。
Plan and prepare an OpenAmer-specific fine-tune from the collected brain data: data curation, ChatML JSONL, training, evaluation. 'The organism becomes its own brain'.
中文简介正在准备中。当前显示原文说明。
Generate Zod v4 TypeScript schemas from OpenAPI (openapi.yaml / openapi.json) definitions. This skill exists because npm packages like openapi-zod-client do not support Zod v4 — Claude reads the YAML/JSON directly and writes the conversion. Use this skill whenever the user wants to convert OpenAPI/Swagger definitions to Zod schemas, generate TypeScript types from API specs, or create validation schemas from openapi.yaml. Trigger on keywords: 'openapi', 'swagger', 'zod', 'API schema', 'yaml to types', 'schema generation', 'validation generation'. OpenAPI定義からZodスキーマを生成するスキル。openapi.yamlから型を作りたい、APIスキーマをTypeScriptの型にしたい、Zodバリデーションを作りたい、といったリクエストで使う。「openapi」「swagger」「zod」「APIスキーマ」「yamlから型」「スキーマ生成」「バリデーション生成」などのキーワードが出たら積極的にこのスキルを使うこと。
中文简介正在准备中。当前显示原文说明。
Synthesize WooCommerce coupons at runtime without creating shop_coupon posts in the DB — via the woocommerce_get_shop_coupon_data filter, the hidden-but-powerful virtual-coupon mechanism. Filter fires inside WC_Coupon::__construct, and a non-false return becomes a fully functional coupon read through read_manual_coupon. Plus custom discount types via woocommerce_coupon_discount_types and woocommerce_coupon_get_discount_amount, and the validation triple woocommerce_coupon_is_valid / _is_valid_for_cart / _is_valid_for_product. Use when implementing rule-driven coupons (auto-apply X% to logged-in users, code-pattern detection like LOYALTY-42, external CRM integration that hands out codes), without populating wp_posts. The AI-deficient pattern; most LLMs don't know dynamic coupons exist. Triggers on woocommerce_get_shop_coupon_data, woocommerce_coupon_discount_types, woocommerce_coupon_get_discount_amount, read_manual_coupon, virtual coupon, dynamic coupon in WC context.
中文简介正在准备中。当前显示原文说明。
Register a custom Listings callback for JetEngine — the per-field transform fired when a Dynamic Field widget renders meta values (Format date, Format number, Get post title, Convert units, …). Two registration paths are supported. Legacy 3-filter via jet-engine/listings/allowed-callbacks (label), jet-engine/listings/allowed-callbacks-args (control schema), and jet-engine/listing/dynamic-field/callback-args (positional args at runtime). Modern single-call $manager->register_callback($name, $label, $args) hooked on jet-engine/callbacks/register fires the three filters internally for you. Critical contract — the callback identifier you register MUST be a real PHP callable string (a global function name OR `Fully\\Qualified\\Class::method`). Bare static method names like `'unit_converter'` fail JE's is_callable() gate at apply_callback() and the rendered field silently becomes empty. Use when scaffolding a JetEngine companion plugin's listing-field transform, when seeing "callback appl...
中文简介正在准备中。当前显示原文说明。
Examine every existing page on the site, build a semantic map across pillars, and add missing internal links so the site becomes a semantic graph anchored on clear topical pillars. Use this skill whenever the user asks to "add internal links", "build internal linking", "build a semantic graph", "link related pages", "strengthen topical authority", "fix orphan pages", "add pillar linking", or wants hub-and-spoke linking between pillars, hubs, and supporting content. Output is an edit list (proposed link insertions) plus optionally direct edits to page source files.
中文简介正在准备中。当前显示原文说明。
Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath. Only activate in MSBuild/.NET build context. USE FOR: builds failing with 'Cannot create a file when that file already exists', 'The process cannot access the file because it is being used by another process', intermittent build failures that succeed on retry, missing outputs in multi-project builds, multi-targeting builds where project.assets.json conflicts. Diagnoses when multiple projects or TFMs write to the same bin/obj directories due to shared OutputPath, missing AppendTargetFrameworkToOutputPath, or extra global properties like PublishReadyToRun creating redundant evaluations. DO NOT USE FOR: file access errors unrelated to MSBuild (OS-level locking), single-project single-TFM builds, non-MSBuild build systems. INVOKES: binlog MCP server tools (overview, projects, evaluations, properties, double_writes); falls back to dotnet msbuild binlog replay + grep when the MCP is unavailable.
中文简介正在准备中。当前显示原文说明。
Fix MSBuild targets that generate files during the build but those files are missing from compilation or output. Only activate in MSBuild/.NET build context. USE FOR: generated source files not compiling (CS0246 for a type that should exist), custom build tasks that create files but they are invisible to subsequent targets, globs not capturing build-generated files because they expand at evaluation time before execution creates them, ensuring generated files are cleaned by the Clean target. Covers correct BeforeTargets timing (CoreCompile, BeforeBuild, AssignTargetPaths), adding to Compile/FileWrites item groups, using $(IntermediateOutputPath) instead of hardcoded obj/ paths. DO NOT USE FOR: C# source generators that already work via the Roslyn pipeline, T4 design-time generation that runs in Visual Studio, non-MSBuild build systems. INVOKES: no tools — pure knowledge skill.
中文简介正在准备中。当前显示原文说明。
사회복지 기관(복지관, 생활시설, 센터, 비영리단체)의 실무자가 업무용 앱을 만들거나, 업무를 자동화하거나, 엑셀·양식을 전산화하고 싶다고 할 때 코드를 만들기 전에 업무의 필요성, 개인정보 등급, 사람에 관한 기록의 윤리, 플랫폼 경로, 운영 조건을 판단하고 DECISION.md로 정리하는 절차. "프로그램일지 앱", "이용자 명부", "출석 체크", "사례관리 기록", "후원자 관리", "차량 운행일지", "복지 앱", "바이브코딩", "희망이음 자동 입력", "에이전트 브라우저로 동기화" 같은 말이 나오거나 사회복지 현장의 행정 업무를 자동화하려 할 때 사용한다. Use before writing any code when a Korean social-welfare practitioner wants to build an app or automate a workflow. Not for general coding tasks.
中文简介正在准备中。当前显示原文说明。
사용자가 HWP나 HWPX 양식 파일을 주면서 "이 양식으로 앱을 만들어 달라", "양식을 전산화하자", "이 서식에 입력하고 출력하고 통계 내는 웹앱"이라고 할 때 사용한다. 양식의 칸을 그대로 데이터베이스로 옮기지 않고, 칸을 분류해 이용자 명부와 연결하고, 판정을 거쳐 앱과 HWP 출력을 만드는 절차다. 사회복지 기관의 일지, 명단, 대장, 보고서 서식에 쓴다. Use when a Korean social-welfare practitioner hands over an HWP/HWPX form and wants an app built from it. For app ideas without a form file, use welfare-app-assess instead.
中文简介正在准备中。当前显示原文说明。
Control FriendlyBet operating cost, free-tier viability, provider/API cost, GitHub Actions/Supabase/Vercel usage, documentation hygiene, company memory updates, playbook maintenance, and skill validation. Use when evaluating cost, operational burden, tooling, internal docs, company memory, or whether agent profiles should become full skills.
中文简介正在准备中。当前显示原文说明。
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
中文简介正在准备中。当前显示原文说明。
Synchronize and verify code examples in documentation. Use when function signatures change, API interfaces update, imports shift, or documentation snippets become outdated and need correction.
中文简介正在准备中。当前显示原文说明。
Use for explicit undergraduate data-science teaching, assignment guidance, concept clarification, method selection, or output interpretation. Do not activate merely because a task contains data or Python code.
中文简介正在准备中。当前显示原文说明。
Navigate the gap between what you can see and what you can make. The Ira Glass gap. Use when a designer is frustrated by the distance between their taste and their output, when mentoring someone through a creative plateau, or when someone is considering quitting because their work doesn't match their vision.
中文简介正在准备中。当前显示原文说明。
Use when turning something that happened into something that makes the next run better - "write a retro", "record this paper cut", "this bug escaped verification", "make this an eval", "why do we keep hitting this", "did that change actually help", "scorecard", "what did we learn from that run", "lessons keep getting re-learned". Covers the six-step loop (capture, classify, convert, change, measure, retro), the repo artifact each step produces, and how escaped bugs become eval cases. Do NOT use to design or judge a single workflow experiment (see `workflow-experimentation`, which this loop feeds), to decide where to run work (see `dogfooding`), or to debug one failed execution in the moment.
中文简介正在准备中。当前显示原文说明。
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "escalate privileges", "get root access", "become administrator", "privesc techniques", "abuse sudo", "exploit SUID binaries", "Kerberoasting", "pass-the-ticket", "token impersonation", or needs guidance on post-exploitation privilege escalation for Linux or Windows systems.
中文简介正在准备中。当前显示原文说明。
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa
中文简介正在准备中。当前显示原文说明。
Parse Office 365 Unified Audit Logs via Microsoft Graph API to tespit etmeemail forwarding rule creation, inbox delegation, suspicious OAuth app grants, and other indicators of account compromise.
中文简介正在准备中。当前显示原文说明。
Auditing Kubernetes cluster RBAC configurations to identify overly permissive roles, wildcard permissions, dangerous ClusterRoleBindings, service account abuse, and privilege escalation paths using kubectl, rbac-tool, KubiScan, and Kubeaudit.
中文简介正在准备中。当前显示原文说明。
Product-research (选品) desk (Busabase App-in-Skill) for a cross-border e-commerce seller. The agent sweeps trend sources — Amazon BSR movers, TikTok viral product videos, Temu/AliExpress rising items, Google Trends terms, competitor new launches — and files product candidates with margin cards (landed cost, fees, breakeven ACOS) and competition reads; Kelly verdicts them develop / watch / drop, and develop items become sourcing and listing briefs handed to kelly-listing. Use when the user invokes $kelly-picks or /kelly-picks, or asks for 选品, product research, a product sourcing radar, BSR movers, TikTok viral products, a margin calculator, breakeven ACOS, competition reads, or product candidate triage.
中文简介正在准备中。当前显示原文说明。