Repository
Peiiii/nextclaw agent skills
- skills
- 70
- GitHub stars
- 260
GitHub description: “A human-centered long-term AI partner—not a task-centered assistant.”
- Stars
- 260 (49 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Feb 2026
- Homepage
- nextclaw.io
- agentic-workflows
- ai-agent
- ai-assistant
- automation
- desktop-app
- feishu
- llm
- local-first
- mcp
- open-source
- self-hosted
- typescript
Install all skills
npx skills add Peiiii/nextclawAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in Peiiii/nextclaw, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | A skill your agent uses when a user wants to browse, apply, inspect, create, refine, switch, or remove a NextClaw skin; wants a personal skin with arbitrary CSS, JavaScript, images, SVG, DOM… | Peiiii/ | 260 | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 2 | A skill your agent uses when a development task needs visible phase tracing, task-level or phase-level Token measurement, model/effort comparison, or a deterministic usage report or local dashboard… | Peiiii/ | 260 | — | ~802 | Automated safety check: Pass | MIT | yesterday |
| 3 | 当 NextClaw 产品更新后需要生成、替换、挑毛病或检查官网、GitHub README、用户文档或社交传播中的真实截图、AI 宣传视觉、整页 HTML 宣传预览、社区二维码等对外视觉资产时使用；也用于“更新截图”“重新截一批图”“做宣传页”“生成 campaign 页面”“视觉审稿”“五星挑刺法”或发布前检查视觉资产。普通站点布局开发或只写文章不触发。 | Peiiii/ | 260 | — | ~801 | Automated safety check: Pass | MIT | yesterday |
| 4 | A skill your agent uses when the user wants professional UI/UX design guidance, design-system generation, UX review, or stack-specific frontend guidance through a bundled local UI/UX Pro Max dataset… | Peiiii/ | 260 | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 5 | A skill your agent uses when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable… | Peiiii/ | 260 | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 6 | Curate NextClaw skill resources, including OpenClaw and community sources. | Peiiii/ | 260 | — | ~479 | Automated safety check: Pass | MIT | yesterday |
| 7 | 7.Mmx CLI Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. | Peiiii/ | 260 | 4 repos | ~2.7k | Automated safety check: Pass | MIT | yesterday |
| 8 | Create or update the Service component of a NextClaw Mini App, choosing between Portable Rust/WASI Components and native-process MCP services. | Peiiii/ | 260 | — | ~1k | Automated safety check: Pass | MIT | yesterday |
| 9 | A skill your agent uses when the user wants a disciplined software development workflow with design-first planning, implementation plans, TDD, systematic debugging, code review, or… | Peiiii/ | 260 | — | ~2.1k | Automated safety check: Pass | MIT | yesterday |
| 10 | Create clear, restrained visual presentations for answers and results by choosing among Markdown, tables, Mermaid, images, and self-contained inline HTML. | Peiiii/ | 260 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 11 | 当用户需要搜索或读取 X/Twitter、操作 X 账号，或希望扩大 X 账号的相关关注者时使用；账号增长下转专门 Skill，单篇内容写作另有 owner。 | Peiiii/ | 260 | — | ~757 | Automated safety check: Pass | MIT | yesterday |
| 12 | Use Agent Browser for real browser navigation, dynamic pages, and web interaction; also use it as a distinct browser-based path when websearch is unavailable or fails. | Peiiii/ | 260 | — | ~815 | Automated safety check: Pass | MIT | yesterday |
| 13 | Use the local aigen CLI to generate images through configured providers such as OpenRouter or OpenAI. | Peiiii/ | 260 | — | ~1.3k | Automated safety check: Pass | MIT | yesterday |
| 14 | 14.Bb Browser A skill your agent uses when the user wants browser-backed web data access, authenticated fetches, website adapters, or safe browser automation through a local bb-browser installation. | Peiiii/ | 260 | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 15 | Use the local browser-connector CLI to inspect and operate the user's current Chrome tabs through the Browser Connector extension and Native Host. | Peiiii/ | 260 | — | ~3.6k | Automated safety check: Pass | MIT | yesterday |
| 16 | A skill your agent uses when the user wants to search external ClawHub skills or install a ClawHub skill into a NextClaw workspace's skills directory without treating ClawHub as the NextClaw… | Peiiii/ | 260 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 17 | A skill your agent uses when deciding how to deliver an AI result: reply now, put durable news, reports, recommendations, or articles in the NextClaw inbox, or send to an explicitly requested chat… | Peiiii/ | 260 | — | ~3.2k | Automated safety check: Pass | MIT | yesterday |
| 18 | 18.Find Skills A skill your agent uses when the user wants to discover, evaluate, and install external agent skills from the open skills ecosystem, especially through the Vercel Skills CLI. | Peiiii/ | 260 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 19 | 19.Gemigo CLI A skill your agent uses when the user wants to publish an already-built static website or front-end app through GemiGo, such as a Vite/React/Vue static build, plain HTML/CSS/JS page, landing page… | Peiiii/ | 260 | — | ~3k | Automated safety check: Pass | MIT | yesterday |
| 20 | 20.Lark CLI A skill your agent uses when the user wants to operate Lark or Feishu via the local lark-cli (@larksuite/cli), including install, app credentials, OAuth, readiness checks, and safe read/write… | Peiiii/ | 260 | — | ~4.8k | Automated safety check: Pass | MIT | yesterday |
| 21 | 21.Linear CLI A skill your agent uses when the user wants to list, view, start, create, or update Linear issues from the terminal via schpet/linear-cli, including setup, auth, repo config, and safe read/write… | Peiiii/ | 260 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 22 | Create or update complete NextClaw Mini Apps by first choosing a Panel-only, Service-only, or Panel + Service composition, then choosing Portable WASI or native-process only when a Service exists. | Peiiii/ | 260 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 23 | Validate, package, and submit schema v2 NextClaw Mini Apps with Panel-only, Service-only, or Panel + Service composition, supporting Portable WASI and native-process Service runtimes. | Peiiii/ | 260 | — | ~1.3k | Automated safety check: Pass | MIT | yesterday |
| 24 | A skill your agent uses when integrating or debugging a Hermes-style external HTTP agent runtime in NextClaw, including runtime config, session selection, readiness, streaming, and adapter behavior. | Peiiii/ | 260 | — | ~1.9k | Automated safety check: Pass | MIT | yesterday |
| 25 | A skill your agent uses when a commit/release, cross-module delivery, important root-cause fix, red-zone change, large governance rewrite, NPM release, work note, or goal anchor may require… | Peiiii/ | 260 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 26 | 26.Opencli A skill your agent uses when the user wants to use websites, browser login sessions, Electron apps, or external CLIs through a local OpenCLI setup, especially when setup guidance, readiness checks… | Peiiii/ | 260 | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 27 | Create or update an engineering-style NextClaw Panel component with pnpm, Vite, React, TypeScript, and Tailwind CSS, then build it into a static .panel directory inside a schema v2 package or an… | Peiiii/ | 260 | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 28 | 当用户希望把本机 Codex、ChatGPT Codex 或 Claude Code 订阅通过 localhost 暴露为 OpenAI 兼容端点，或希望在代理验证成功后把它添加成 NextClaw 自定义 provider 时使用。负责 CLIProxyAPI 安装检查、安全配置、OAuth 登录、Homebrew/systemd 持久托管、重启存活验收、NextClaw provider… | Peiiii/ | 260 | — | ~1.9k | Automated safety check: Notes | MIT | yesterday |
| 29 | A skill your agent uses when the user wants to publish or update a local skill in the NextClaw marketplace, especially when they need clear guidance for version readiness, platform login, username… | Peiiii/ | 260 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 30 | 通用开发生命周期的「开发实现」阶段 owner；当目标、证据和适用设计已经明确且需要修改产物时使用，负责以单一路径完成实现和迭代检查，不负责最终验证、Review 或交付发布。 | Peiiii/ | 260 | — | ~461 | Automated safety check: Pass | MIT | yesterday |
| 31 | 通用开发的 Review 方法 owner；mode=design 审查实现前方案与验收设计，mode=implementation 审查已验证产物；返回 findings 和返工目标，不修改产物或执行发布。 | Peiiii/ | 260 | — | ~663 | Automated safety check: Pass | MIT | yesterday |
| 32 | A skill your agent uses when a complex task will span turns or sessions and needs structured working notes to survive context compression or handoff; short single-turn work does not trigger it. | Peiiii/ | 260 | — | ~509 | Automated safety check: Pass | MIT | yesterday |
| 33 | Create or update the Panel UI component of a complete schema v2 NextClaw Mini App or an explicitly loose local Panel. | Peiiii/ | 260 | — | ~4.2k | Automated safety check: Pass | MIT | yesterday |
| 34 | A skill your agent uses when integrating QQ group chat where users want one shared group session, but the assistant must still distinguish who said each message. | Peiiii/ | 260 | — | ~415 | Automated safety check: Pass | MIT | yesterday |
| 35 | 35.Qq URL Guard A skill your agent uses when sending replies to QQ where URL-like text (for example xx.xx, USER.md, markdown links, or http URLs) may trigger code 40034028 and get blocked. | Peiiii/ | 260 | — | ~296 | Automated safety check: Pass | MIT | yesterday |
| 36 | Turn a user request into a scheduled automation by configuring cron jobs, including session-bound follow-ups and periodic checks. | Peiiii/ | 260 | — | ~647 | Automated safety check: Pass | MIT | yesterday |
| 37 | 当用户希望把 Claude Code 作为 NextClaw 正式会话类型接入，尤其是通过 narp-stdio 配置、安装、修复、doctor、补齐 Runtime default 模型选项或真实冒烟时使用。 | Peiiii/ | 260 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 38 | 当用户希望把 Codex 或 Codex CLI/SDK 作为 NextClaw 正式会话类型接入，或要求安装、更新/升级 Codex NARP runtime、修复、doctor、排查版本或真实冒烟时使用。 | Peiiii/ | 260 | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 39 | A skill your agent uses when the user asks to keep watching an external state, notify them when something changes or a condition is met, remember fresh external state across turns, or manage an… | Peiiii/ | 260 | — | ~559 | Automated safety check: Pass | MIT | yesterday |
| 40 | 当新增、重命名、移动文件，改变文件角色/feature root/目录边界，或用户明确要求命名、文件组织和目录概况治理时使用；统一路由命名、角色、feature-root 和概况扫描，局部修改现有文件不触发。 | Peiiii/ | 260 | — | ~309 | Automated safety check: Pass | MIT | yesterday |
| 41 | A skill your agent uses when the user asks about NextClaw autostart, auto-start on login or reboot, daemon/service registration, LaunchAgent, systemd, Windows Scheduled Task, service autostart… | Peiiii/ | 260 | — | ~943 | Automated safety check: Notes | MIT | yesterday |
| 42 | 当用户要求扫描、识别、清理、常态化治理 NextClaw 仓库里的死代码、无用代码、unused files、unused exports、unused dependencies，尤其是核心包越来越臃肿、想删旧实现或做定期减债时使用。 | Peiiii/ | 260 | — | ~974 | Automated safety check: Pass | MIT | yesterday |
| 43 | 当把 Codex、Claude Code、Hermes 或其他外部 agent runtime 通过 NARP stdio 接入 NextClaw，或触达 narp-stdio entry、launcher、agent-side wrapper 和旧 runtime 插件迁移时使用。 | Peiiii/ | 260 | — | ~761 | Automated safety check: Pass | MIT | yesterday |
| 44 | 当为 NextClaw 及关联产品写博客、官网短文、发布叙事、功能优势、社区稿或配图 brief，并需要把用户兴趣、愿景与证据收敛成可信公开内容时使用。 | Peiiii/ | 260 | — | ~781 | Automated safety check: Pass | MIT | yesterday |
| 45 | 当确定要修改 AGENTS.md、commands、项目 AI 规则、skill/references、治理脚本，或明确优化 AI 驱动开发体系时使用；普通规则讨论和一次性纠偏不提前触发。 | Peiiii/ | 260 | — | ~485 | Automated safety check: Pass | MIT | yesterday |
| 46 | 通用开发生命周期的「交付、发布与部署」阶段 owner；当结果已经达到交付条件，或用户明确要求提交、发布、部署时使用，负责授权边界、结果交接和专项发布路由，不负责实现或 Review。 | Peiiii/ | 260 | — | ~521 | Automated safety check: Pass | MIT | yesterday |
| 47 | 通用开发生命周期的「方案设计」阶段 owner；当用户明确要求设计、风险达到 L3-L4，或用户可见 L2 功能存在真实方案空间时使用，负责冻结可执行设计，不负责实现、验证或发布。 | Peiiii/ | 260 | — | ~831 | Automated safety check: Pass | MIT | yesterday |
| 48 | 通用开发流程的唯一 Meta Skill；理解后选择 standard、trivial 或 bugfix，管理阶段门、返工、验收与整体完成；阶段 Skill 提供方法，知识库提供事实。 | Peiiii/ | 260 | — | ~1k | Automated safety check: Pass | MIT | yesterday |
Questions, answered from the data.
What is the best skill in Peiiii/nextclaw?
Nextclaw Skin Studio from Peiiii/nextclaw ranks first of the 70 skills in Peiiii/nextclaw listed here, with the highest score: its repository has 260 GitHub stars, its SKILL.md loads about 1.8k tokens and it passes the automated safety check with no findings. Next come Development Task Telemetry and Nextclaw Product Visual Assets.
Are the skills in Peiiii/nextclaw official?
None yet. All 70 skills in Peiiii/nextclaw listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from Peiiii/nextclaw?
Run npx skills add Peiiii/nextclaw in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.