MUST use when writing Bun Native scripts. The script must start with //native to run on the native worker.
Use when writing code inside a feature — a handler, query, service, event, or integration test. Control flow, async (Promise.all), query performance (N+1, upsert, joins, indexes),…
Develop a premise, novel, synopsis, or source story into a production-ready vertical short-drama series bible, episode outline, continuity ledger, and requested episode scripts.
当用户明确要求"生成技能 README"、"编写用户指南"或"更新技能文档"时使用。为 Agent Skills 编写符合最佳实践的 README.md 用户使用指南。自动分析技能结构（SKILL.md、config.yaml、scripts/），按模板生成小白友好的文档。
Create or update SKILL.md files for this repo. Use when authoring skills in .codex/skills/.
Use when a plan's increment has to be cut into slices, or when an approved plan exists and one of its slices needs the document an agent will carry it out from, including a slice…
Use when starting a new initiative spike, investigating technical feasibility, assessing impact across services, or writing an engineering discovery document — produces a…
Write a GxP-compliant Standard Operating Procedure (SOP). Covers regulatory SOP template structure (purpose, scope, definitions, responsibilities, procedure, references, revision…
Use when creating, drafting, or generating a new standard page for quality.arc42.org — a file under `_standards//.md`.
How to generate bulletproof Standard Operating Procedures (SOPs) and technical tutorials with exact click paths, expected visual results, and failure troubleshooting.
Write CakePHP Table-layer PHPUnit tests for validation, rules, finders, and persistence behavior.
Use after Design review to create or change Task.md: milestone task decomposition, AC-to-task mapping, dependencies, orchestration status, and pointers to per-card execution…
Escreve uma especificação técnica para implementar uma feature com arquitetura, dados, contratos, riscos, testes e plano de rollout.
Write comprehensive testthat (edition 3) tests for R package functions. Covers test organization, expectations, fixtures, mocking, snapshot tests, parameterized tests, and…
Use after any incident (or near-miss) — write a blameless postmortem that finds the systemic/contributing causes, not a person to blame, and produces tracked action items so the…
Use when filing a finding — write the bug report as a persuasive document that gets it fixed (Kaner's bug advocacy): exact repro, expected vs actual, severity, and the expectation…
Use when you actually draft or edit the artifact — a landing page, hero, email, ad, onboarding screen, empty state, changelog, CTA — and need it to be clear, scannable, and…
Turn findings into a defensible intelligence product — BLUF key judgements, standardised estimative probability language, per-claim sourcing with timestamps and archived copies,…
Use when the user says "write a how-to for {feature}" / "tutorial for {integration}" / "walk a user through {flow}" — produces a Diátaxis-aligned tutorial (learning-oriented,…
Multi-format tweet studio - standalone drafts (10 across 5 size tiers), a 5-10 tweet thread, or 10 remixes of past tweets, selected via ${var}
Use when the user wants help composing a tweet on X (Twitter). Generates tweet ideas, drafts, algorithm-optimized variants, and scores tweets for engagement.
Генерирует новые Use Case (UC) файлы для проекта Travel App Belarus, соблюдая установленный шаблон, структуру и кросс-зависимости.
Use when writing any words inside the UI — button verbs, labels, empty/error/success messages, tooltips, confirmations, onboarding.
Redactar documentación de validación IQ/OQ/PQ para sistemas informatizados en entornos regulados. Cubre protocolos, informes, scripts de prueba, gestión de desviaciones y flujos…
Use when writing a new ViewModel or modifying an existing one in the Alkaa project. Triggers on tasks like "add a ViewModel", "create VM for X screen", "implement state handling",…
R MarkdownまたはQuartoを使用してRパッケージのビネットを作成する。 ビネットのセットアップ、YAML設定、コードチャンクオプション、ビルドとテスト、 ビネットのCRAN要件を網羅。「はじめに」チュートリアルの追加、複数の関数にまたがる 複雑なワークフローの文書化、ドメイン固有のガイド作成、またはCRAN投稿で…
MUST use when writing or modifying Windmill Workflow-as-Code scripts using workflow, task, step, sleep, approvals, taskScript, taskFlow, task_script, or task_flow.
Generate MADR-format Architectural Decision Records using a multi-agent pipeline
Write or update duplojs-utils JSDoc documentation files under jsDoc/{namespace}/{function}/, including index.md structure, @example includes, and example.ts usage pattern — from…
Write or update duplojs-utils JSDoc documentation files under jsDoc/{namespace}/{function}/, including index.md structure, @example includes, and example.ts usage pattern — from…
Create, modify, review, and harden agentic prompts/slash commands. USE WHEN create prompt OR new command OR slash command OR modify prompt OR update workflow OR improve prompt OR…
Document work and learnings for publication. Assesses session work, recommends format (tweet, thread, week notes, full write-up), drafts in your voice, writes to draft folder.
Use when writing or editing a comment, a README, CLAUDE.md, or any prose in this repository that states a reason, cites a file or a test, quotes a number, or describes how…
Use when a spec document has been approved during brainstorming and you need to produce testable acceptance criteria before writing the implementation plan - converts spec…
Use whenever creating, updating, editing, drafting, restructuring, or fixing documentation in the Actual Budget repo — specifically anything under `packages/docs/` (the Docusaurus…
Generates structured admission order sets with diagnosis-specific protocols and safety checks. Use when admitting patients, creating admission orders, or setting up inpatient care…
How to write great agent instructions for an agent-native app or template: AGENTS.md, skills, and tool/action descriptions.
Use when building multi-agent workflows with the relay broker-sdk - covers conversation-shape vs pipeline-shape coordination, the WorkflowBuilder API, DAG step dependencies, agent…
How to write Claude Code agents — standard format, 2-phase review, severity/confidence, dispatch patterns
Where writing artifacts live: kb/ for durable knowledge, work/ for scratch. Use when deciding where to read from or write to.
核心能力: 内容创作领域的专业化 AI 辅助工具,提供企业级高级功能支持。Use when 需要生成营销文案、写作内容、标题优化、内容创作时使用。不适用于纯技术文档撰写。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。提供结构化输出和错误处理机制。
Write a bot to continuously listen and respond to events on a public blockchain network.
Writes human-friendly changelog entries and release notes. Use when populating changelog, preparing releases, or reviewing release notes quality.
Use when creating a changeset file during spectra:archive, writing or editing changeset body content, running release:version, reviewing a CHANGELOG.md entry, or asking how the…
Writes and improves checklist-based professional communications -- requests for action, handoffs, meeting agendas/follow-ups, and process runbooks.
Use when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts.
Use when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and…
Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text.
Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text.
Creates ICH E3-compliant clinical study reports with required sections and data presentation. Use when writing CSRs, formatting study reports, or preparing regulatory submissions.
新手写作双模式 Skill。面向学员和用户，不要求先有个人 profile、长期记忆沉淀或代表作。 当用户想“先写出一篇很强的文章”，但自己没有足够素材、经历或风格资产时，优先使用这个 skill。 当用户明确说想“像某个内置作者写”，尤其是当前内置作者 Dan Koe、粥左罗、Justin Welsh、刘润、梁宁、薛辉时，也应使用这个 skill。…
How to write Claude Code slash commands — orchestrator pattern, agent dispatch, auto-detection
Critique a frozen writing artifact against an explicit rubric for purpose, structure, evidence, consistency, clarity, and voice without editing it.
Use after brainstorming completes - writes validated designs to docs/design-plans/ with structured format and discrete implementation phases required for creating detailed…
Guides writing HMR/Dev Server tests in test/bake/. Use when creating or modifying dev server, hot reloading, or bundling tests.
Structures developer guides for optimal AI agent and human consumption. Use when creating or updating files in contributing/, or when documentation needs to support autonomous…
Creates procedure-specific discharge instructions with activity restrictions, wound care, and return precautions.
Expert at writing high-quality documentation for code, APIs, and projects. Auto-invokes when generating docstrings, creating README files, writing API documentation, adding code…
Use when creating or editing documentation pages in docs/content/guides/ - covers YAML frontmatter, page structure, framework-specific example embedding, writing style, and…
Use when writing or modifying any function, method, class, or source file in a repo using repo-hygiene — public API, internal helpers, and new files all require docstrings; only…