菜单
Generates data-driven reports about the project. Use for initial project reports or session summaries.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build evaluation datasets for AIFindr agents by adding queries with expected responses extracted from a knowledge base. Use when asked to add queries to a W&B dataset, create evaluation test cases, or build ground truth datasets from documents. Requires W&B dataset name, project, query, and knowledge base path.
Comprehensive evaluation of AIFindr agents against their knowledge base. Use when asked to evaluate an AIFindr agent, test agent responses, run evaluations from a W&B dataset, or generate evaluation reports. Supports single queries, multiple queries, or full dataset evaluation. Generates markdown reports and XLSX files.
Execute comprehensive E2E tests for aifindr-knowledge-base application using agent-browser. Use this skill when asked to test the knowledge base app, verify UI functionality, test CRUD operations (tenants, promotions, documents, web URLs), test the publish workflow, or verify data ingestion in Weaviate. Creates a new project for test isolation, uses XLSX test data with images, verifies image uploads display correctly, and tests cascade delete of promotions when tenant is deleted.
| name | ai-data-report |
| description | Generates data-driven reports about the project. Use for initial project reports or session summaries. |
Generates data-driven reports about the project. Use /ai-data-report to invoke.
.claude/reports/YYYY-MM-DD-[type].md (e.g., 2026-01-22-session.md, 2026-01-22-initial.md)Generates a complete report with:
## 📊 Project Report
**Production URL:** [production URL]
**GitHub URL:** [repo URL]
**Development time:** [estimated hours and context]
### Services used:
| Service | Purpose |
|---------|---------|
| [Service 1] | [What it does] |
| [Service 2] | [What it does] |
...
### Flow when someone uses the app:
1. [Step 1]
2. [Step 2]
...
### Tech stack:
- Backend: [technology]
- Frontend: [technology]
- Database: [technology]
- Hosting: [technology]
### Deployment:
- [How it deploys]
- [Where env variables are stored]
Generates a session summary:
## 📝 Session Summary
**Date:** [date]
**Approximate duration:** [time]
### Changes made:
| Area | Change | Files |
|------|--------|-------|
| [area] | [description] | [files] |
### Commits:
- `[hash]` [message]
### Bugs found/fixed:
- [bug 1]
### Suggested next steps:
- [ ] [task 1]
- [ ] [task 2]
### Metrics:
| Metric | Value |
|--------|-------|
| Lines changed | +X / -Y |
| Files modified | N |
| Commits | N |
| **Time - Claude** | ~Xh Xmin (coding, debugging, testing) |
| **Time - Human** | ~Xmin (reviewing, testing, giving feedback) |
When user invokes /project-report:
Detect mode:
Gather data:
package.json, requirements.txt, .env.example to detect servicesgit log for recent commitsgit remote -v for URLsBe data-driven:
Format: