AGENT SKILL

reveal-feedback

Interact with Reveal feedback infrastructure to manage products, create review tasks, read AI-analyzed user feedback, get sentiment insights, view submissions, manage notifications, and register webhooks. Use when the user asks about product feedback, user reviews, testing tasks, sentiment analysis, top issues, review submissions, marketing videos, or anything related to their Reveal account.

License 许可
MIT
最近更新
2026-06-07
Stars
★ 0
Forks
1

01 前言 Front Matter

name
reveal-feedback
metadata
{ "openclaw": { "emoji": "📊", "homepage": "https://testreveal.ai", "requires": { "env": [ "REVEAL_API_KEY" ] }, "primaryEnv": "REVEAL_API_KEY" } }
description
Interact with Reveal feedback infrastructure to manage products, create review tasks, read AI-analyzed user feedback, get sentiment insights, view submissions, manage notifications, and register webhooks. Use when the user asks about product feedback, user reviews, testing tasks, sentiment analysis, top issues, review submissions, marketing videos, or anything related to their Reveal account.

03 SKILL.md 正文

Reveal Feedback Infrastructure

Reveal is a universal feedback platform where human reviewers screen-record themselves using products and provide AI-analyzed feedback. This skill connects to the Reveal REST API to manage the full feedback lifecycle.

Authentication

All API calls require the REVEAL_API_KEY environment variable. The key is a vendor API key generated from the Reveal dashboard under Settings → API Keys.

Every request uses this header:

Authorization: Bearer $REVEAL_API_KEY

Base URL: https://www.testreveal.ai/api/v1 (Override with REVEAL_BASE_URL env var if set.)

Capabilities

1. Check dashboard overview

Fetch products, active review tasks, and unread notifications to give the user a quick status update.

Steps:

  1. GET /products to list vendor products
  2. GET /review-tasks?status=active to list active tasks
  3. GET /notifications?unread=true&limit=5 to get unread notifications
  4. Summarize: product count, active tasks with submission progress, and recent notifications

2. Get feedback insights for a product

Fetch AI-aggregated insights: top issues, top positives, sentiment distribution, and suggestions.

Steps:

  1. GET /products to find the product ID matching the user's request
  2. GET /insights/{productId} to get aggregated insights
  3. Present: sentiment breakdown, top issues ranked by frequency, top positives, unique issue count

3. Get product analytics

Fetch quantitative metrics for a product.

Steps:

  1. GET /products/{productId}/analytics
  2. Present: total submissions, analyzed count, average completion rate, sentiment distribution, top issues, top positives

4. View review submissions

Get individual review submissions with transcripts, AI analysis, sentiment, and issue counts.

Steps:

  1. GET /review-tasks?status=active&limit=5 to find the relevant task (or use a task ID if provided)
  2. GET /review-tasks/{taskId}/submissions to get all submissions
  3. For each submission, present: status, sentiment, issue count, positive count, transcript preview

5. Create a review task

Create a new user-testing task so reviewers can test a product.

Steps:

  1. GET /products to find the product matching the user's description
  2. Extract from the user's message: title, objective, steps, feedback focus, reviewer count
  3. POST /review-tasks with body:
{
  "title": "extracted title",
  "productId": "matched product ID",
  "requiredReviewers": 5,
  "instructions": {
    "objective": "what the reviewer should accomplish",
    "steps": "step-by-step instructions",
    "feedback": "what feedback to focus on"
  }
}
  1. Confirm creation with task ID and details

6. Update a review task

Close, pause, or modify an existing review task.

Steps:

  1. PATCH /review-tasks/{taskId} with fields to update (status, title, description, requiredReviewers)
  2. Confirm the update

7. List products

Show all products registered on the vendor's Reveal account.

Steps:

  1. GET /products?limit=50
  2. Present each product: name, category, platform support (web/mobile), website

8. Get notifications

Check for new activity on Reveal.

Steps:

  1. GET /notifications?unread=true&limit=20
  2. Present notification messages with timestamps
  3. If user says to mark as read: PATCH /notifications with {"markAllRead": true}

9. Register a webhook

Set up real-time event notifications.

Steps:

  1. POST /webhooks with body:
{
  "url": "https://user-provided-url",
  "events": ["review.submitted", "review.analyzed", "task.completed", "video.generated"]
}
  1. Return the webhook ID and signing secret. Instruct user to store the secret securely.

10. List webhooks

Steps:

  1. GET /webhooks
  2. Present each webhook: URL, subscribed events, active status

Response format

All API responses follow this structure:

  • Success: { "data": { ... } }
  • Error: { "error": { "code": "ERROR_CODE", "message": "description" } }

Guardrails

  • Never expose or log the API key in responses to the user
  • If an API call fails with 401, tell the user their API key may be invalid or expired
  • If a product is not found, suggest listing products first
  • When creating review tasks, always confirm the details with the user before sending the POST
  • Do not fabricate feedback data — only report what the API returns

04 同仓库更多 Skills

javimosch
javimosch/open-claw-skills

crowd-prompting

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

★ 0
javimosch
javimosch/open-claw-skills

ceaser

Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).

★ 0
javimosch
javimosch/open-claw-skills

ceaser-send

Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.

★ 0
javimosch
javimosch/open-claw-skills

dilemm-ai

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

★ 0
javimosch
javimosch/open-claw-skills

moldium

Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.

★ 0
javimosch
javimosch/open-claw-skills

arxiv-paper-reviews

Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.

★ 0