Skill 与 AgentSKILLS & AGENTS· BROWSER
elophanto/EloPhanto
能自我进化、操控浏览器、运营公司的自主AI程序An autonomous AI agent that writes its own tools, drives a real browser, and grades itself — for developers who want to see AI work independently.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
自动编写新功能并操控真实浏览器
根据实际结果自我评分和改进
运营公司业务
执行网页无障碍合规检查
Write custom tools on the fly
Drive a real browser autonomously
Run a company end to end
Grade itself on measured outcomes
Stop before actions it cannot undo
上手GET STARTED
git clone https://github.com/elophanto/EloPhanto.git && cd EloPhanto选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01控制浏览器Controls a browserskills/api-testing/SKILL.md
- Build automated test suites using modern frameworks (Playwright, REST Assured, k6)
02控制浏览器Controls a browserskills/browser-automation/SKILL.md
stdin/stdout with a Node.js subprocess running Playwright with stealth plugins
03读取 API KeyReads an API keyskills/coingecko-market-data/SKILL.md
const apiKey = process.env.COINGECKO_API_KEY;
04读取 API KeyReads an API keyskills/dflow-trading/SKILL.md
const API_KEY = process.env.DFLOW_API_KEY; // Optional but recommended
静态扫描发现中等风险:项目能控制浏览器(通过Playwright)并读取API Key(如COINGECKO_API_KEY、DFLOW_API_KEY),可能带来安全或隐私问题。Static scan found it controls a browser and reads API keys — both are by design. Review the code before running it with sensitive credentials.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
-5.7%-5.7%
106 → 100 stars · 49 个快照106 → 100 stars · 49 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
1 条外部提及1 external mentions
状态STATUS
持续活跃Active
质量 A-Quality A-
近7天有15次提交,项目正在快速迭代中Source-available with a self-model grounded in real psychology
HN_STORY · 1 points · 1 comments
{
"agents": [
{
"agent": "vscode",
"evidence": "readme: …rom the CLI, a web dashboard, VS Code, Telegram, Discord, Slack, Si…"
},
{
"agent": "claude-code",
"evidence": "skills/agent-organization/SKILL.md: …meral external coding agents (Claude Code, Codex, Gemini CLI) for code…"
},
{
"agent": "gemini-cli",
"evidence": "skills/agent-organization/SKILL.md: …g agents (Claude Code, Codex, Gemini CLI) for code tasks. No learning,…"
}
],
"apiKey": "nt Setup ```bash # .env file COINGECKO_API_KEY=your_api_key_here COINGECKO_API_TYPE=de",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 5,
"dev-tools": 2,
"indie-web": 0,
"skill-agent": 0,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "browser"
},
"localRuntime": "ter.ai/keys) is the easiest; [Ollama](https://ollama.ai) keeps it entirely l",
"skillMdTotal": 185,
"skillMdErrors": [
{
"path": "skills/_template/SKILL.md",
"error": "no frontmatter"
},
{
"path": "skills/agent-commune/SKILL.md",
"error": "no frontmatter"
},
{
"path": "skills/agent-organization/SKILL.md",
"error": "no frontmatter"
},
{
"path": "skills/agentcash-onboarding/SKILL.md",
"error": "no frontmatter"
},
{
"path": "skills/autonomous-experimentation/SKILL.md",
"error": "no frontmatter"
},
{
"path": "skills/browser-automation/SKILL.md",
"error": "no frontmatter"
},
{
"path": "skills/business-launcher/SKILL.md",
"error": "no frontmatter"
},
{
"path": "skills/email-agent/SKILL.md",
"error": "no frontmatter"
},
{
"path": "skills/file-management/SKILL.md",
"error": "no frontmatter"
}
],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 6,
"media": 0,
"design": 1,
"browser": 0,
"devtool": 3,
"security": 0,
"marketing": 0,
"productivity": 1
},
"classification": [
{
"signal": "49 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 477 markdown files",
"weight": 0.75
},
{
"signal": "MCP SDK dependency",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/12-principles-of-animation/SKILL.md",
"skills/_template/SKILL.md",
"skills/accessibility-auditing/SKILL.md",
"skills/agency-phase-0-discovery/SKILL.md",
"skills/agency-phase-1-strategy/SKILL.md",
"skills/agency-phase-2-foundation/SKILL.md",
"skills/agency-phase-3-build/SKILL.md",
"skills/agency-phase-4-hardening/SKILL.md",
"skills/agency-phase-5-launch/SKILL.md",
"skills/agency-phase-6-operate/SKILL.md",
"skills/agency-strategy/SKILL.md",
"skills/agent-activation/SKILL.md",
"skills/agent-commune/SKILL.md",
"skills/agent-handoff/SKILL.md",
"skills/agent-orchestration/SKILL.md",
"skills/agent-organization/SKILL.md",
"skills/agentcash-onboarding/SKILL.md",
"skills/agentic-identity/SKILL.md",
"skills/ai-engineering/SKILL.md",
"skills/alphascala/SKILL.md",
"skills/analytics-reporting/SKILL.md",
"skills/api-playbook/SKILL.md",
"skills/api-testing/SKILL.md",
"skills/app-store-optimization/SKILL.md",
"skills/autonomous-experimentation/SKILL.md",
"skills/autonomous-optimization/SKILL.md",
"skills/b2c-marketing-voice/SKILL.md",
"skills/backend-architecture/SKILL.md",
"skills/baseline-ui/SKILL.md",
"skills/behavioral-nudge/SKILL.md",
"skills/booking-flows/SKILL.md",
"skills/brand-guardian/SKILL.md",
"skills/browser-automation/SKILL.md",
"skills/business-launcher/SKILL.md",
"skills/canvas-design/SKILL.md",
"skills/coingecko-market-data/SKILL.md",
"skills/composition-patterns/SKILL.md",
"skills/content-creation/SKILL.md",
"skills/crypto-launch-ops/SKILL.md",
"skills/cultural-intelligence/SKILL.md",
"skills/data-analytics/SKILL.md",
"skills/data-consolidation/SKILL.md",
"skills/data-engineering/SKILL.md",
"skills/debridge-crosschain/SKILL.md",
"skills/deep-research/SKILL.md",
"skills/design-lab/SKILL.md",
"skills/developer-advocacy/SKILL.md",
"skills/devops-automation/SKILL.md",
"skills/dflow-trading/SKILL.md",
"skills/drift-trading/SKILL.md",
"skills/drive-business/SKILL.md",
"skills/email-agent/SKILL.md",
"skills/evidence-collection/SKILL.md",
"skills/executive-summaries/SKILL.md",
"skills/experiment-tracking/SKILL.md",
"skills/feedback-synthesis/SKILL.md",
"skills/file-management/SKILL.md",
"skills/finance-tracking/SKILL.md",
"skills/fixing-accessibility/SKILL.md",
"skills/fixing-metadata/SKILL.md"
],
"skillMdFetched": 60
}