Каталог навыков агентов

'WPF Popup 컨트롤의 포커스 관리 패턴 (PreviewMouseDown 이벤트 활용)'

"WPF 솔루션 및 프로젝트 구조 설계 가이드 (Abstractions, Core, ViewModels, Services)"

Define and evolve WPF XAML styling for the widget host app: control styles, templates, visual states, typography, and th...

Thread-safe WebView2 bridge messaging in WPF with async handlers

Wpig ZAG im Plugin Regulatorisches Recht: fachlicher Arbeitsgang mit Prüffeldwahl, Norm-/Quellencheck, Risikoampel und v...

Audit whether a WordPress plugin or classic theme is WPML-compatible end to end. Use when asked "is this plugin WPML com...

Make a WordPress plugin/theme translatable with WPML by shipping a wpml-config.xml file. Covers the sections WPML honors...

Use WPML's runtime language hook API from plugin/theme code — read the current/active/default language, resolve the tran...

Orient a developer making a WordPress plugin or theme compatible with WPML (sitepress-multilingual-cms). Explains WPML's...

Register and translate a WordPress plugin's dynamic strings with WPML — option values, admin-entered labels, and other f...

WPS Office workflow for Chinese users: create, edit, review, convert, and troubleshoot Writer/Spreadsheets/Presentation...

Guide for working with Wave Terminal's WPS (Wave PubSub) event system. Use when implementing new event types, publishing...

WPS 表格智能助手，通过自然语言操控 Excel，解决公式编写、数据清洗、图表创建等痛点问题

Use local WPS Office on Windows to safely inspect, edit, format, export, and reopen-verify DOCX, XLSX, and PPTX files wh...

WPS Office 跨应用智能助手，统一管理 Excel、Word、PPT 三大应用，处理跨应用操作和通用功能

WPS 演示智能助手，通过自然语言操控 PPT，解决排版美化、内容生成、动画设置等痛点问题

使用 Windows 本地 WPS 整理可编辑 Word 报告与附件册，按范本校排、还原扫描材料、核对正式题名、整理目录页码、保留真实修订并重开验收。适用于 WPS 转换稿整编及既有报告校审，不用于单纯写作、PPT设计或云端文档管理。

WPS 文字智能助手，通过自然语言操控 Word 文档，解决排版、格式、内容编辑等痛点问题

Use for writing any English text like docs, notes, summaries, explanations, answers, README sections.

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, C...

Use Cloudflare Wrangler CLI for Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, P...

Deploy and manage Cloudflare Workers, Pages, KV, R2, D1, and other Cloudflare services using the `wrangler` CLI.

Run or troubleshoot Wrangler CLI commands and configure Worker projects for local development, deployment, and Cloudflar...

Run or troubleshoot Wrangler CLI commands and configure Worker projects for local development, Previews, deployment, and...

Run or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file,...

Runs Cloudflare Wrangler CLI work: deploying and tailing Workers, managing KV, R2, D1, and Queues, secrets, bindings, an...

Use when deploying, developing, or managing Cloudflare Workers and related resources with Wrangler.

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, C...

This skill guides Cloudflare Workers and Pages development with Wrangler CLI. Use when creating Workers, configuring D1...

Cloudflare Wrangler deployment patterns for Pitchey. Activates when deploying, publishing, or releasing to Cloudflare Pa...

Non-interactive wrangler OAuth login using playwriter to automate the Cloudflare consent flow in the user's browser. Use...

Manage Cloudflare R2 object storage for file hosting using Wrangler CLI. Use when uploading files to R2, managing bucket...

This skill should be used when the user mentions "wrangler", "wrangler.toml", "wrangler.jsonc", "wrangler commands", "lo...

Validates project wrangler version on session start, detects breaking changes, and recommends updates

Validates project wrangler version on session start, detects breaking changes, and recommends updates

Close the current Egregore session with a personal, canonical summary. Use for /wrap or when the user says they are done...

End-of-session ritual — check for uncommitted or unpushed work, release any issue claim left standing, list anything dan...

Write an end-of-session recap to .claude/last-session.md. Triggered by /wrap, "wrap up", "recap this session", or automa...

Full session close-out ritual — commit, export conversation, teaching narrative, handoff, memory harvest; use for "wrap...

End work session intentionally. Use at natural stopping points, before context limits, or when switching contexts.

Freezes and wraps up inbox task work — reads ongoing tasks, cross-checks each against the project registry to catch misf...

Add, import, normalize, recover, or synchronize reusable agent skills into this repository's canonical agent-plugins/ski...

End-of-session documentation workflow that updates README, CHANGELOG, agent context files, and creates session logs. Use...

End a work session - verify, update PROGRESS.md and the session log, commit, push to main and confirm CI is green.

End-of-day command to capture what happened, consolidate notes, and set up for tomorrow. Use when the user types /wrap_u...

End of day - sync memory, clear done list, externalize knowledge, prep tomorrow

Post-implementation quality gate. Runs automated checks (tests, lint, types), invokes /flagrare:implementation-review fo...

End-of-session routine — commit, memory review, self-improvement. Run before closing terminal.

Use ONLY when the user's latest message explicitly contains the `/wrap-up` command. Harvests everything a long session p...

Save progress and leave a clean AgentBoard handoff for the next Codex session. Use when the user wants to end a session...

End-of-session automation. Creates a journey, consolidates learning notes, evolves skills, cross-pollinates shared patte...

Saves today's work session as a four-line entry (did, decided, open, next) at the top of the project's log.md, after the...

Session-closeout audit — check for unfinished work before ending a conversation, then give a clear verdict. ALWAYS use t...

Wind down a long-running session fast when the user must leave — freeze new work, preserve active subagents, secure fini...

End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use...

Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overv...

作業終了時の一連のフロー（検証、テスト、リント、ドキュメント更新、コミット）を一括実行する

Summarize session changes — update memory log, generate commit message, and create patch notes. Use after completing wor...

Close a task: list the changes, fix stale docs, run checks, draft the commit. Use when the user says "wrap up" or "ready...

Generate a Codex Wrapped usage recap from local Codex logs, including last 30 days, last 7 days, and an all-time focus-h...

Levenshtein 퍼지 매칭으로 스킬 명령 오타를 자동 교정하는 래퍼. source 후 모든 명령이 자동 교정된다. "오타 교정", "명령어 자동완성", "wrapper" 등에서 동작.

Close out a feature worktree once its PR has merged — confirm the merge, verify the deploy where one applies, remove the...

This skill should be used when the user asks to "query WRDS", "access Compustat", "get CRSP data", "pull Form 4 insider...

Connect to and query WRDS (Wharton Research Data Services) from any research project. Use this skill whenever the user n...

Read Wellington Region Emergency Management Office (WREMO) public news and updates through a lightweight no-login CLI: n...

Wren CLI for AI agents — a semantic SQL layer over 22+ databases (Postgres, MySQL, BigQuery, Snowflake, Spark, …). The a...

Wrike integration for AI agents via ClawLink — browser login, no API key setup. Connect Wrike through ClawLink's hosted...

Manage projects, tasks, and workflows via Wrike API. Create tasks, update statuses, and track work.

Automate Wrike project management via Rube MCP (Composio): create tasks/folders, manage projects, assign work, and track...

Handle smartwatch conversations, ambiguous voice transcripts, and recoverable background tasks within explicit permissio...

Use when writing technical content: documentation, changelogs, articles, pitches, sprint reviews, and presentation outli...

Deliberately write or revise one complete curated memory file.

Use for marketing, social, replies, product copy, launch copy, and writing in the user's voice when their Emulo writing...

Rewrites and polishes prose in Chinese or English, removes AI-like wording, and reviews product localization copy while...

Drafts Slack messages, emails, GitHub PR titles and descriptions, PR review comments and replies, and git commit message...

Rewrites and polishes Chinese or English prose, technical instructions, and product copy. Use when drafting, editing, lo...

Expert writing for technical content, social media, and developer documentation. Use when asked to write tweets, LinkedI...

中文写作的唯一入口，写文章、写稿、改稿、写文案、写脚本、去 AI 味都从这里进。 一个流程走到底：判断手上有什么，读对应的 references 自己执行（挖素材、定结构、诊断初稿、文案、传播与标题）， 最后强制过一遍内置中文体检（检测脚本...

Plan, draft, version, and refine written content with enforced versioning and quality audits.

Document architectural decisions with context and consequences.

Turn a rough ambition into a measurable, REACHABLE goal — a capability statement, a precisely-named metric, ≥2 numeric e...

The agent writes the full piece to the shape and the length that were agreed, whether that is an article, a customer sto...

Primary pipeline shaping step after /research and before /prd-to-issues. Use when the problem is understood well enough...

Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when us...

Use this skill when the user wants to turn an idea, feature request, architecture proposal, product requirement, vague e...

Create a PRD through user interview, codebase exploration, and module design, then save it as a local artifact under a d...

Generate a PRD from the client brief and write it as a local markdown file in issues/. Use when the user wants to turn a...

Create a PRD through user interview, codebase exploration, and module design, stored locally in the repo. Use when user...

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to cre...

Author, lint, and publish skill packages that satisfy the library authoring standard. Use when creating a new skill, rev...

Creating a new skill — one with no law above it — a showcase, a generator, a third-party service, a working technique of...

Author a single new skill — produce a SKILL.md plus optional bundled references and scripts following Anthropic's progre...

Create new agent skills with clear triggers, compact instructions, and optional bundled references or helper scripts. Us...

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to cre...

Write acceptance criteria for a Jira story using Given/When/Then scenarios. Use this skill when the user asks to write A...