搜索「writing」的结果

io.clawhub.ckchzh/story-writer

小说创作、角色设计、情节设计(三幕式)、对话生成、世界观构建、续写。Story writing with character design, three-act plot structure, dialogue generation, worldbuilding. Supports bilingual docum...

io.clawhub.rotbit/topic-to-article-kit

Turn a chosen AI topic into a public-account writing package: collect evidence from X/Twitter and other sources, extract high-value comments, and produce title options + structured outline written into Obsidian. Use when user asks for topic-based research and article prep.

io.clawhub.ckchzh/short-drama-writer

短剧剧本生成器。竖屏短剧、微短剧、剧情设计、角色塑造。Short drama script generator for vertical video dramas, plot design, character building. 短剧脚本、微短剧、编剧工具。Use when writing short dram...

io.clawhub.analsharqy/react-best-practices-2

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.j...

io.clawhub.zways/automate-excel

Automates reading, writing, merging, transforming, and validating Excel (.xlsx/.xls) files. Use when the user works with spreadsheets, .xlsx files, Excel dat...

io.clawhub.tristanmanchester/notion-api-automation

Manage Notion notes, pages, and data sources with a JSON-first CLI for search, read/export, write/import, append, and move operations. Use when working with Notion, organising notes, moving pages, triaging an inbox, or reading/writing page content.

io.clawhub.gitgoodordietrying/shell-scripting

Write robust, portable shell scripts. Use when parsing arguments, handling errors properly, writing POSIX-compatible scripts, managing temp files, running commands in parallel, managing background processes, or adding --help to scripts.

Test Master

v0.1.0

io.clawhub.veeramanikandanr48/test-master

Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.

io.clawhub.ivangdavila/writer

Fix AI writing patterns that create repetitive and robotic content

io.clawhub.idanmann10/startclaw-optimizer

Master optimization system - APPLIES TO EVERY RESPONSE. Before responding, classify task complexity (simple question vs analysis vs coding). Use Haiku for simple/navigation/extraction/status. Use Sonnet ONLY for writing/analysis/planning/debugging. Monitor context size - if >50k tokens, recommend /compact. For automations, use scheduler wrapper. Never load full conversation history for simple tasks. Heartbeats always Haiku, single-line only. Never use Opus. This skill MUST run before every response to prevent 100k+ token bloat.

io.clawhub.ethagent/prompt

A comprehensive AI agent skill for writing prompts that get consistently excellent results from AI models. Teaches the principles behind effective prompting,...

Codebase Documenter

v0.1.0

io.clawhub.veeramanikandanr48/codebase-documenter

This skill should be used when writing documentation for codebases, including README files, architecture documentation, code comments, and API documentation. Use this skill when users request help documenting their code, creating getting-started guides, explaining project structure, or making codebases more accessible to new developers. The skill provides templates, best practices, and structured approaches for creating clear, beginner-friendly documentation.

io.clawhub.ivangdavila/aws

Architects, debugs, secures, and cost-optimizes AWS infrastructure — EC2, Lambda, RDS, VPC, IAM, ECS, CloudFront. Use when deploying or reviewing anything on AWS, when a bill jumps or spend has to come down, when an AccessDenied, throttle, timeout, 502/503/504, or unreachable-database error has no obvious cause, when choosing between Lambda, Fargate, EC2, RDS, DynamoDB, SQS, or EventBridge, when hardening IAM policies, S3 exposure, security groups, or secrets, when writing Terraform/CloudFormation/CDK against AWS, when auditing an account you inherited, or when a service quota, cold start, connection limit, or failover is the thing that broke. Covers VPC and subnet design, NAT versus VPC endpoints, Organizations and cross-account roles, backups and disaster recovery, and CLI/SSO profiles. Not for object-storage patterns in depth (`s3`), DynamoDB key modeling (`dynamodb`), Kubernetes manifest authoring (`k8s`), or Terraform language mechanics (`terraform`).

io.clawhub.shashwatgtm/social-media-management

B2B content writing with daily workflows and batching systems across Sales/HR/Fintech/Ops Tech

io.clawhub.mupengi-bot/content-pipeline

Orchestrate full content workflow (planning→writing→design→publishing→tracking). Use when automating full content workflow from planning to publishing.

io.clawhub.ivangdavila/chinese

Writes and edits Mandarin Chinese that reads as if a native wrote it — casual or formal, mainland or Taiwan. Use when composing anything in Chinese (WeChat message, work email, 小红书 or 公众号 post, resume, 请假条, speech, toast, 通知, contract clause), or when Chinese text sounds stiff, textbook, translated, or AI-generated; when choosing 你 versus 您, 口语 versus 书面语, simplified versus traditional, or mainland versus Taiwan vocabulary; when 的/地/得, 了, 把, 被 or measure words come out wrong; when full-width punctuation, Han-Latin spacing, or 万/亿 number grouping is off; when internet slang, 成语, emoji or 表情包 need calibrating to an audience; when a refusal, apology, compliment or request has to land politely; or when naming a product or a person in Chinese. Not for translating an existing source text (`translate`), Traditional-only writing (`traditional-chinese`), or travelling in China (`china`).

io.clawhub.artur-zhdan/humanize

Remove AI writing patterns from text. Use when editing, reviewing, or rewriting text to sound more natural and human-written. Detects patterns like inflated symbolism, promotional language, em dash overuse, AI vocabulary, and sycophantic tone.

io.clawhub.ivangdavila/flutter

Builds, debugs, and ships Flutter apps: widgets, layout constraints, state management, navigation, performance, and store releases. Use when writing Dart widgets or screens; when a RenderFlex overflows, a viewport is given unbounded height, or a RenderBox was not laid out; when setState is called during build or after dispose, or BuildContext is used across an async gap; when the UI janks, scrolling stutters, or images exhaust memory; when hot reload stops applying changes; when Provider, Riverpod, or Bloc rebuild too much or too little; when routing with Navigator or go_router, deep links, or back-button handling; when the keyboard covers a form field or validation misfires; when a platform channel throws MissingPluginException; when localizing strings or mirroring a layout for right-to-left; when widget, golden, or integration tests hang or fail in CI; or when a build works in debug but the release APK, IPA, or web bundle breaks. Not for React Native or native-only Swift and Kotlin work.

io.clawhub.peterokase42/save-money

Auto-detect task complexity for Claude models (Haiku + Sonnet). Route simple tasks to Haiku, escalate complex ones to Sonnet. Save 50%+ on API costs. | 適用 Claude 模型（Haiku + Sonnet），自動偵測任務難度，簡單用 Haiku，複雜升級 Sonnet，輕鬆省下 50% 以上的費用。— RULES: Before responding, classify the task. If it matches an escalation trigger, call sessions_spawn with the full task and model anthropic/claude-sonnet-4-20250514 IMMEDIATELY. Do NOT answer complex tasks yourself. ESCALATE: analysis, comparisons, planning, strategy, code >10 lines, reports, proposals, multi-step reasoning, tables, outlines, charts, long writing >3 paragraphs, summarization, long translation. NEVER on Haiku: comparison tables, code >10 lines, multi-step analysis, reports, complex reasoning. STAY on Haiku: factual Q&A, definitions, greetings, reminders, short lookups, casual chat, 1-2 sentence tasks. When in doubt, escalate. Keep Haiku replies concise.

io.clawhub.ivangdavila/k8s

Debugs Kubernetes workloads and reviews manifests: pods, probes, resources, rollouts, Services, storage, RBAC. Use when a pod is Pending, CrashLoopBackOff, ImagePullBackOff, OOMKilled or stuck Terminating, when a Service or Ingress serves nothing or returns 502/503/504, when cluster DNS is flaky, a rollout hangs or silently ships a broken version, an HPA refuses to scale, a PVC stays unbound, a node goes NotReady or a drain never finishes, when writing or reviewing YAML, Helm charts or kustomize overlays, when tuning requests, limits, QoS, probes and graceful shutdown, when locking down RBAC, NetworkPolicy, Pod Security and Secrets, when the API server throttles or an admission webhook blocks every create, when a GPU pod never schedules, when a mesh sidecar breaks a Job, or when planning a cluster upgrade, a backup, or a restore. Covers kubectl triage, StatefulSets, Jobs and CronJobs, autoscaling, operators, node drains and DaemonSet agents. Not for building container images — that is `docker`.

io.clawhub.ivangdavila/fastapi

Builds, debugs, and hardens FastAPI services: async endpoints, Pydantic models, dependency injection, auth, and deployment. Use when writing or reviewing a FastAPI app, router, or schema; when the API hangs or every route slows because a sync driver or CPU work blocks the event loop; when a request returns an unexpected 422, a POST becomes a 307, or a 500 arrives with no CORS headers; when migrating pydantic v1 to v2 (`model_dump`, `from_attributes`, `field_validator`); when `Depends` runs too often, `yield` cleanup misfires, or dependency overrides do not take; when SQLAlchemy raises `QueuePool limit` or `MissingGreenlet`, or connections leak across workers; when TestClient, httpx `AsyncClient`, or pytest-asyncio fail with a closed event loop; when uvicorn or gunicorn workers, graceful shutdown, `root_path`, or proxy headers need deciding; or when background tasks, WebSockets, SSE, uploads, or the OpenAPI docs misbehave. Not for Django, Flask, or general Python — `django`, `flask`, `py`.

io.clawhub.ivangdavila/react

Builds, debugs, and reviews React apps: components, hooks, state, Server Components, forms, performance, testing. Use when writing or refactoring components, choosing state management (useState, Context, Zustand, TanStack Query, Redux), when a component rerenders too often, loops infinitely ("too many re-renders"), shows stale or not-updating state, fails with a hydration mismatch or hook-order error, when an effect fires twice or fetches race, when typing lags or long lists scroll slowly, when adopting React 19, Server Actions, or the React Compiler, when testing components with Testing Library, typing props in TypeScript, or reviewing AI-generated React code. Not for React Native (mobile) or Next.js routing and deployment — use react-native or nextjs.

io.clawhub.ivangdavila/typescript

Writes, reviews, and debugs type-safe TypeScript: type errors, narrowing, generics, tsconfig strictness, and declaration files. Use when a build hits type errors ("not assignable", "possibly undefined", "excessively deep", "cannot find module"), when eliminating any or unchecked as casts, designing generics or discriminated unions, writing .d.ts files or typing untyped npm packages, configuring tsconfig or module resolution, fixing ESM/CJS import crashes ("ERR_REQUIRE_ESM", "x is not a function"), validating API or JSON data at runtime, migrating JavaScript to TypeScript or upgrading the TypeScript version, or when tsc or the editor gets slow or runs out of memory.

io.clawhub.xiongjjlj/feishu-docx-powerwrite

High-quality Feishu/Lark Docx writing via OpenClaw. Use when you want to turn Markdown into well-formatted Feishu Docx (headings, lists, nesting, code blocks) using feishu_docx_write_markdown; includes safe workflows, templates, and troubleshooting. Trigger on Feishu doc/docx links, “write to Feishu doc”, “generate a Feishu doc”, “append/replace docx”, “convert markdown to feishu doc”, or when users want consistently good doc formatting.