Skip to main content
ClaudeWave
Skill3.1k estrellas del repoactualizado 1mo ago

static-deploy

Static-deploy uploads HTML, CSS, JS, and other static assets from a workspace directory to a Cloudflare Pages site at `<project-slug>.nexu.space`. Use it when a user requests deployment, publishing, or going live with a static website, single-page app, landing page, or documentation site. The script automatically injects cache headers to reduce stale asset issues on redeployments and handles both initial deploys and updates to existing sites.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/nexu-io/nexu /tmp/static-deploy && cp -r /tmp/static-deploy/skills/nexubot/static-deploy ~/.claude/skills/static-deploy
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Static Deploy

Deploy static files to `<project-slug>.nexu.space` via Wrangler + Cloudflare Pages.

The deploy script stages a temporary copy of the site and injects a `_headers`
file (if needed) with cache revalidation rules for HTML/CSS/JS to reduce stale
asset issues after redeploys. Source files are not modified.

## What it deploys

Any static files: HTML, CSS, JS, images, fonts, etc. Common use cases:
- Single-page apps (React, Vue, etc. — deploy the `dist/` or `build/` folder)
- Landing pages, portfolios, documentation sites
- Quick prototypes or demos
- Any folder with an `index.html`

## Usage

1. Identify the directory containing files to deploy (must have an `index.html`)
2. Derive a project-slug from context (e.g., "family budget" → `family-budget`)
   - Lowercase alphanumeric + hyphens only, max 63 characters
   - Reuse the same slug for redeployments
   - Ask user to confirm if ambiguous
3. Run deploy with the inbound structured context:

```bash
"$SKILL_DIR/scripts/deploy.sh" <project-slug> <directory> <agent-id> <chat-id> [thread-id] [message-ref] [account-id] [channel] [chat-type] [sender-ref]
```

`agent-id` is required. The script uses it to resolve the corresponding `botId`
from `nexu-context.json` when recording deployment artifacts.

`chat-id` is the raw inbound chat identifier from the message context.

- DM example: `U0AHLMC6C8G`
- Channel example: `C0AJKG60H6D`

`chat-type` tells the script whether to send that id to Nexu as `user:<chat-id>`
or `channel:<chat-id>`. The script does that translation; do not concatenate
those prefixes yourself.

`thread-id` is optional — pass it when deploying from within a thread context.
4. Parse the JSON output and report to user:
   - Brief summary of what was deployed
   - Live URL from the `url` field
   - **Important:** Tell the user that Cloudflare Pages propagation takes ~3 minutes. The URL may not work immediately after the first deploy. For redeployments, it's usually faster.

## Example reply

> Deployed! Your site is live at https://family-budget.nexu.space
>
> Note: First-time deploys take ~3 minutes to propagate on Cloudflare. If you see a "not found" page, wait a few minutes and refresh.

## Rules

- Never read, echo, or log `SKILL_API_TOKEN`, `CLOUDFLARE_API_TOKEN`, or `CLOUDFLARE_ACCOUNT_ID`
- Never pass credentials as command arguments
- Always use the bundled `deploy.sh` — do not call Cloudflare API directly
- Do not set `DEPLOY_BACKEND` or any other env overrides — the script handles everything
- Always pass the caller `<agent-id>` as arg #3 to `deploy.sh`
- Always pass raw inbound `<chat-id>` as arg #4
- Never pass `<agent-id>` as `<chat-id>`; they are different values
- If deploying from a thread, pass `<thread-id>` as arg #5
- Always pass `<channel>` and `<chat-type>` when available so Nexu can resolve the correct session deterministically
- Do not try to look up or persist a canonical session key in this skill; Nexu resolves it server-side
- Do not hand-edit source files just to add cache-busting query params; the deploy script handles cache revalidation via a staged `_headers` file
- If the script fails, show the `message` field from the JSON error to the user
- Cloudflare credentials are fetched at runtime via the scoped secrets API using `SKILL_API_TOKEN` from env — do not attempt to read or inject them manually

## Output Format

Success:
```json
{
  "status": "success",
  "url": "https://<slug>.nexu.space",
  "deployment_url": "https://<id>.<slug>.pages.dev",
  "files_total": 10,
  "files_uploaded": 2,
  "files_cached": 8
}
```

Error:
```json
{
  "status": "error",
  "message": "Description of what went wrong"
}
```
process-pr-reviewsSkill

Use when the user asks to process, triage, fetch, view, count, list, or resolve review feedback in a GitHub PR. Supports both CodeRabbit and Codex review workflows. In this workflow, “real review feedback” is strictly defined as actionable inline comments; for CodeRabbit, exclude review summaries and nitpicks, and for Codex, exclude review summary cards and use PR main-thread reactions only as status signals.

clawhubSkill

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

coding-agentSkill

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.

deep-researchSkill

|

gh-issuesSkill

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

libtv-videoSkill

Seedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation, style transfer, and text-to-image using Seedance 2.0 model. Also supports Kling 3.0, Wan 2.6, Midjourney, Seedream 5.0. Trigger phrases: seedance, generate video, make a video, generate image, make an image, draw, libtv, liblib.

nano-banana-one-shopSkill

All-in-one image generation with Gemini models. Supports Nano Banana (3.1 Flash), Nano Banana Pro (3 Pro), and Nano Banana 2 (2.5 Flash). Triggers on "generate image", "image generation", "nano banana", "edit image".

qiaomu-mondo-poster-designSkill

一句话生成大师级海报、书籍封面、专辑封面和各类设计作品。无需懂PS、配色或艺术史,AI自动选择最佳风格(基于33+位传奇设计师)。支持多平台多比例:公众号封面(21:9)、小红书配图(3:4)、文章配图(16:9)、书籍封面(9:16)、专辑封面(1:1)、电影海报(9:16)。包含AI提示词优化、风格对比、图生图转换功能。触发词:"Mondo风格"、"书籍封面设计"、"专辑封面"、"海报设计"、"读书笔记配图"、"公众号封面"、"小红书配图"、"文章配图"。One-sentence generation of master-level posters, book covers, album covers and designs. 33+ legendary designer styles with multi-platform aspect ratio support (21:9, 16:9, 3:4, 1:1, 9:16).