feedback
The feedback skill captures user input following the `/feedback` command and forwards it to the Nexu team through an automated submission script. Use this skill when users want to report issues, share suggestions, or provide general feedback about the Nexu platform. The skill automatically extracts conversation history and images without requiring manual copying, then submits the feedback with sender and channel metadata.
git clone --depth 1 https://github.com/nexu-io/nexu /tmp/feedback && cp -r /tmp/feedback/skills/nexubot/feedback ~/.claude/skills/feedbackSKILL.md
# Feedback
Collect user feedback and forward it to the Nexu team. Conversation history and images are extracted automatically by a script — you do NOT need to copy-paste messages or scan for image URLs.
## When triggered
The user sends `/feedback <message>` to share feedback, report issues, or make suggestions about the Nexu platform.
## Steps
1. **Extract feedback content**: The text after `/feedback` is the user's feedback. If empty, ask the user to provide their feedback.
2. **Gather identifiers**:
- **agentId**: Your own agent ID. Find it from the `Runtime:` line in your system prompt — it appears as `agent=XXXXXX`. It is a cuid2 string like `y9cnvdlucvyaokp20mqrsoa9`. Do NOT use "main" or other placeholder values.
- **channel**: The current channel type — one of `feishu`, `slack`, or `discord`.
- **sender**: The sender's display name or username as shown in the conversation. If you only have a user ID, use that. Do NOT use generic "user" or "User".
3. **Run the submit script**: Use the exec tool to run the following command. The script automatically reads your conversation history and any images from the session file — you do NOT need to provide them manually.
```bash
SKILL_PATH="<SKILL_LOCATION>"
node "$(dirname "${SKILL_PATH/#\~/$HOME}")/submit-feedback.mjs" \
--content "<ESCAPED_FEEDBACK>" \
--sender "<SENDER>" \
--channel "<CHANNEL_TYPE>" \
--agent-id "<AGENT_ID>"
```
Important:
- Replace `<SKILL_LOCATION>` with the exact path from the `<location>` tag in your system prompt (may contain `~`)
- The `${SKILL_PATH/#\~/$HOME}` expansion handles tilde (`~`) → absolute path conversion automatically
- Replace ALL other `<...>` placeholders with actual values BEFORE running the command
- Properly escape shell special characters in the feedback content (single quotes → `'\''`, etc.)
4. **Confirm to user**:
- If the output contains `{"ok":true}`, reply: "Thanks for your feedback! It has been forwarded to the Nexu team."
- If it fails, reply: "Sorry, there was an issue sending your feedback. Please try again later."
## Important
- Do NOT modify, filter, or censor the user's feedback content. Forward it as-is.
- Do NOT ask for confirmation before sending — the user already expressed intent by using /feedback.
- Do NOT manually build conversationContext or imageUrls — the script handles this automatically.
- The API will automatically look up the bot owner's email and bot name from the agentId, so focus on getting the agentId right.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.
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.
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.
|
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]
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.
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".
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).