gui-report
Track and report GUI agent task performance — automatic data collection, manual report command.
Best use case
gui-report is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Track and report GUI agent task performance — automatic data collection, manual report command.
Teams using gui-report should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/gui-report/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How gui-report Compares
| Feature / Agent | gui-report | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Track and report GUI agent task performance — automatic data collection, manual report command.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Top AI Agents for Productivity
See the top AI agent skills for productivity, workflow automation, operational systems, documentation, and everyday task execution.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# GUI Task Report Automatic performance tracking for GUI tasks. Data collection is fully automatic, report generation is one command. ## How It Works ``` detect_all() called → tracker auto-starts (records token baseline) GUI functions called → counters auto-tick (screenshots, clicks, OCR, etc.) task finished → run: tracker.py report (saves to log, prints summary) ``` Data collection needs zero manual effort. Only the final `report` command needs to be called. ## Quick Start ```bash # After a GUI task finishes, generate report: source ~/gui-agent-env/bin/activate python3 ~/.openclaw/workspace/skills/gui-agent/skills/gui-report/scripts/tracker.py report # View history: python3 ~/.openclaw/workspace/skills/gui-agent/skills/gui-report/scripts/tracker.py history ``` ## What's Tracked (all automatic) | Counter | Auto-ticked by | |---------|---------------| | detector_calls | `detect_all()` | | ocr_calls | `detect_all()` | | screenshots | `learn_from_screenshot()` | | learns | `learn_from_screenshot()` | | clicks | `record_page_transition()` | | transitions | `record_page_transition()` | | workflow_level0 | `quick_template_check()` | | workflow_level1 | `execute_workflow()` Level 1 | | workflow_level2 | `execute_workflow()` Level 2 | | workflow_auto_steps | `execute_workflow()` auto mode | | workflow_explore_steps | `execute_workflow()` explore mode | | **image_calls** | **manual: `tracker.py tick image_calls`** | ## Report Output ``` 📊 任务报告：chromium/united_com ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ⏱ 耗时：2min 35s 💰 Token 消耗： 总计 +26.8k tokens input +3.2k | output +1.8k | cache +21.8k 🔍 检测： detect_all 8 次 | OCR 8 次 | LLM 视觉 1 次 组件总量：96（+12） 🖱 操作： 点击 5 次 | 状态转移 3 个 | 学习 3 次 🗺 导航效率： 自动模式 3 步 | 探索模式 2 步 自动率 60% 📝 记忆变化： 组件 +12（84 → 96） 状态 +1（5 → 6） ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ``` ## Failsafe If `report` is not called, data stays in `.tracker_state.json`. Next time tracker starts (next `detect_all` call), it auto-saves the previous session's data to the log before starting fresh. **Data never lost.** ## Log Storage `skills/gui-report/logs/task_history.jsonl` — one JSON per completed task.
Related Skills
ESG & Sustainability Reporting Framework
You are an ESG reporting specialist. Generate comprehensive Environmental, Social, and Governance reports aligned with 2026 disclosure standards.
Board Reporting Framework
Generate investor-ready board decks and reporting packages. Covers monthly board updates, quarterly deep dives, and annual reviews with the metrics that actually matter.
Annual Report Generator
Build a complete annual business report from raw data. Covers financial performance, operational metrics, strategic highlights, and forward-looking guidance.
daily-report-generator
Automatically generate daily/weekly work reports from git commits, calendar events, and task lists. Use when you need to quickly create professional work reports without manual effort.
web3-weekly-report
自动抓取数据并生成 Web3 行业资本运作周报，涵盖融资事件、监管动态、上市公司 DAT 动态、并购交易与 RWA 项目追踪。当用户提到"写周报"、"生成周报"、"整理本周融资"、"Web3 周报"、"资本运作周报"、"采编周报"，或请求整理加密行业本周动态时，立即激活此 skill。即使用户只说"帮我写本周的"，只要上下文涉及 Web3、加密、融资、RWA、DAT，也应激活。
name: web3-weekly-report
description: 自动抓取数据并生成 Web3 行业资本运作周报，涵盖融资事件、监管动态、上市公司 DAT 动态、并购交易与 RWA 项目追踪。当用户提到"写周报"、"生成周报"、"整理本周融资"、"Web3 周报"、"资本运作周报"、"采编周报"，或请求整理加密行业本周动态时，立即激活此 skill。即使用户只说"帮我写本周的"，只要上下文涉及 Web3、加密、融资、RWA、DAT，也应激活。
CPMO Daily Report - 终端虾每日汇报技能
_最后更新：2026-03-15（合并 cpmo.md 内容）_
biz-reporter
Automated business intelligence reports pulling data from Google Analytics GA4, Google Search Console, Stripe revenue, social media metrics (Twitter/X, LinkedIn, Instagram), HubSpot CRM, and Airtable into formatted daily KPI snapshots, weekly marketing reports, and monthly business reviews with trend detection and anomaly alerts. Use this skill for: business reports, KPI dashboard, weekly metrics, marketing report, revenue summary, traffic report, analytics summary, performance report, "how are we doing", "show me our metrics", "what are our numbers", MRR tracking, conversion rate analysis, SEO performance report, social media analytics, sales pipeline report, automated reporting via cron, data visualization, business intelligence, growth metrics, churn analysis, or any request to combine data from multiple business tools into a single formatted report. Also works for ad-hoc questions like "how did our launch go" or "compare this month to last month". Delivers via Slack, email, Notion, or Markdown file.
generate-weekly-report
根据 git 提交记录自动生成本周周报，按功能模块归类输出编号列表格式
aws-finops-report
Generate executive-ready monthly AWS FinOps reports with team-level chargeback and savings opportunities
report
Generate test report. Use when user says "test report", "results summary", "test status", "show results", "test dashboard", or "how did tests go".
microbiome-diversity-reporter
Interpret Alpha and Beta diversity metrics from 16S rRNA sequencing results.