Skip to content

aiskillstore/marketplace / skills/727474430/browser-task-and-automation-and-delegation

browser-task-and-automation-and-delegation

Verified

【强制】所有浏览器操作必须使用本技能,禁止在主对话中直接使用 mcp__chrome-devtools 工具。触发关键词:打开/访问/浏览网页、点击/填写/提交表单、截图/快照、性能分析、自动化测试、数据采集/爬取、网络模拟。本技能通过 chrome-devtools-expert agent 执行浏览器操作,避免大量页面快照、截图、网络请求数据污染主对话上下文。

FileKindSize
SKILL.mdskill md5.4 KB
skill-report.jsonconfig26.0 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-04T17:08:32.705Z",
    "slug": "727474430-browser-task-and-automation-and-delegation",
    "source_url": "https://github.com/727474430/cli-rule-swtich/tree/main/templates/claude/jige/skills/browser-task-and-automation-and-delegation",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "14c1a99f13809da30f8918625c7d35b1f893a97a25070e60c4cad99a73025220",
    "tree_hash": "fb906a76f4e7c014a982716851aa8a623c73e0d9f2fb893c895c14140431ad8b",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "browser-task-and-automation-and-delegation",
    "description": "Delegates browser automation tasks to a Chrome DevTools expert agent for navigation, form interaction, screenshots, performance analysis, testing, data extraction, and network simulation.",
    "summary": "Delegate browser automation to a Chrome DevTools agent while keeping main chat context concise.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "727474430",
    "license": "MIT",
    "tags": [
      "browser-automation",
      "chrome-devtools",
      "web-testing",
      "screenshots",
      "performance-analysis"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network"
    ],
    "category": "productivity"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All static command-execution findings are Markdown backticks or fenced examples, not executable Ruby or shell code. The hardcoded URLs are example.com placeholders, and the entropy alert is explained by readable Chinese Markdown. No prompt injection or data-exfiltration intent was found.",
    "remediation": [
      {
        "issue": "Ambiguous code fences triggered command-execution scanning.",
        "suggestion": "Mark examples as plain text and avoid standalone triple backticks around tool parameters when possible.",
        "severity": "low"
      },
      {
        "issue": "Examples show placeholder login credentials.",
        "suggestion": "Label credentials as dummy values and advise users never to place real passwords in reusable prompts.",
        "severity": "low"
      },
      {
        "issue": "Browser automation includes data extraction and authenticated workflows.",
        "suggestion": "Add explicit consent and scope guidance for private pages, scraping, screenshots, and network monitoring.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 8,
            "line_end": 8
          },
          {
            "file": "SKILL.md",
            "line_start": 12,
            "line_end": 12
          },
          {
            "file": "SKILL.md",
            "line_start": 62,
            "line_end": 62
          },
          {
            "file": "SKILL.md",
            "line_start": 64,
            "line_end": 69
          },
          {
            "file": "SKILL.md",
            "line_start": 69,
            "line_end": 78
          },
          {
            "file": "SKILL.md",
            "line_start": 78,
            "line_end": 83
          },
          {
            "file": "SKILL.md",
            "line_start": 83,
            "line_end": 90
          },
          {
            "file": "SKILL.md",
            "line_start": 90,
            "line_end": 95
          },
          {
            "file": "SKILL.md",
            "line_start": 95,
            "line_end": 102
          },
          {
            "file": "SKILL.md",
            "line_start": 102,
            "line_end": 107
          },
          {
            "file": "SKILL.md",
            "line_start": 107,
            "line_end": 114
          },
          {
            "file": "SKILL.md",
            "line_start": 114,
            "line_end": 119
          },
          {
            "file": "SKILL.md",
            "line_start": 119,
            "line_end": 126
          },
          {
            "file": "SKILL.md",
            "line_start": 126,
            "line_end": 131
          },
          {
            "file": "SKILL.md",
            "line_start": 131,
            "line_end": 138
          },
          {
            "file": "SKILL.md",
            "line_start": 138,
            "line_end": 143
          },
          {
            "file": "SKILL.md",
            "line_start": 143,
            "line_end": 150
          },
          {
            "file": "SKILL.md",
            "line_start": 150,
            "line_end": 160
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 82,
            "line_end": 82
          },
          {
            "file": "SKILL.md",
            "line_start": 106,
            "line_end": 106
          },
          {
            "file": "SKILL.md",
            "line_start": 142,
            "line_end": 142
          },
          {
            "file": "SKILL.md",
            "line_start": 154,
            "line_end": 154
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:8:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 8,
        "line_end": 8,
        "snippet": "本技能负责将浏览器自动化任务委派给专业的 `chrome-devtools-expert` agent 执行,通过 agent 隔离来保持主对话上下文的清晰,避免浏览器操作过程中的大量 token 消"
      },
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 12,
        "line_end": 12,
        "snippet": "识别需要浏览器自动化操作的场景,并将任务委派给 `chrome-devtools-expert` agent,该 agent 专门使用 Chrome DevTools MCP 工具进行 Web 界面交"
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 62,
        "line_end": 62,
        "snippet": "使用 Task tool 调用 `chrome-devtools-expert` agent:"
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 64,
        "line_end": 69,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 69,
        "line_end": 78,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 78,
        "line_end": 83,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 83,
        "line_end": 90,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 90,
        "line_end": 95,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:95:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 95,
        "line_end": 102,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 102,
        "line_end": 107,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 107,
        "line_end": 114,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:114:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 114,
        "line_end": 119,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 119,
        "line_end": 126,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:126:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 126,
        "line_end": 131,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:131:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 131,
        "line_end": 138,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:138:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 138,
        "line_end": 143,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:143:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 143,
        "line_end": 150,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:150:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 150,
        "line_end": 160,
        "snippet": "```"
      },
      {
        "id": "network:SKILL.md:82:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 82,
        "line_end": 82,
        "snippet": "- prompt: \"打开 https://example.com,等待页面加载完成后截图,将截图保存到桌面\""
      },
      {
        "id": "network:SKILL.md:106:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 106,
        "line_end": 106,
        "snippet": "- prompt: \"对 https://example.com 进行性能分析,启动性能跟踪,刷新页面,停止跟踪,提供核心 Web 指标和性能洞察\""
      },
      {
        "id": "network:SKILL.md:142:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 142,
        "line_end": 142,
        "snippet": "- prompt: \"设置网络模拟为 Slow 3G,打开 https://example.com,记录页面加载时间和用户体验,然后恢复正常网络\""
      },
      {
        "id": "network:SKILL.md:154:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 154,
        "line_end": 154,
        "snippet": "- prompt: \"1) 打开 https://example.com"
      },
      {
        "id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-6-87-bits-possible-b",
        "category": "obfuscation",
        "severity": "high",
        "pattern": "[HEURISTIC] High file entropy (6.87 bits) - possible binary/encrypted content",
        "file": "SKILL.md",
        "line_start": 1,
        "line_end": 1,
        "snippet": "File: SKILL.md"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:8:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The line uses Markdown inline code to name an agent or tool. It does not execute Ruby, shell, or user-controlled commands."
      },
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The line uses Markdown inline code to name an agent or tool. It does not execute Ruby, shell, or user-controlled commands."
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The line uses Markdown inline code to name an agent or tool. It does not execute Ruby, shell, or user-controlled commands."
      },
      {
        "id": "external_commands:SKILL.md:64:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:95:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:114:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:126:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:131:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:138:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:143:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "external_commands:SKILL.md:150:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This location is a Markdown fenced example for Task tool parameters. It does not invoke a shell or interpreter."
      },
      {
        "id": "network:SKILL.md:82:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The URL is the reserved example.com domain in documentation. It illustrates browser navigation and is not an exfiltration endpoint."
      },
      {
        "id": "network:SKILL.md:106:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The URL is the reserved example.com domain in documentation. It illustrates browser navigation and is not an exfiltration endpoint."
      },
      {
        "id": "network:SKILL.md:142:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The URL is the reserved example.com domain in documentation. It illustrates browser navigation and is not an exfiltration endpoint."
      },
      {
        "id": "network:SKILL.md:154:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The URL is the reserved example.com domain in documentation. It illustrates browser navigation and is not an exfiltration endpoint."
      },
      {
        "id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-6-87-bits-possible-b",
        "verdict": "false_positive",
        "confidence": 0.92,
        "reason": "The file is readable Markdown with Chinese prose and front matter, not encoded or encrypted content. The entropy heuristic appears caused by non-ASCII text."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 171,
    "audit_model": "codex",
    "audited_at": "2026-07-04T17:08:32.705Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Automate Browser Tasks with Delegated DevTools",
    "value_statement": "Browser work can flood the main chat with page state, screenshots, and request logs. This skill delegates those tasks to a Chrome DevTools agent and returns concise results.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "browser automation",
      "Chrome DevTools",
      "web testing",
      "screenshot automation",
      "performance analysis",
      "form automation",
      "web data extraction"
    ],
    "actual_capabilities": [
      "Delegates browser work to a chrome-devtools-expert agent through the Task tool.",
      "Opens pages, navigates tabs, and waits for page load states.",
      "Clicks elements, fills forms, selects options, and submits workflows.",
      "Captures full-page or element screenshots and page text snapshots.",
      "Runs performance traces and reports Core Web Vitals findings.",
      "Extracts page data with JavaScript and monitors network requests."
    ],
    "limitations": [
      "Requires a configured Chrome DevTools MCP server and the named subagent.",
      "Does not bypass authentication, paywalls, captchas, or site access controls.",
      "Can expose sensitive page data if used on private sessions.",
      "Example credentials are placeholders and should not be reused."
    ],
    "use_cases": [
      {
        "title": "Check a Web Flow",
        "target_user": "QA tester",
        "description": "Run browser steps, verify visible states, capture screenshots, and report whether the workflow behaves as expected."
      },
      {
        "title": "Diagnose Page Performance",
        "target_user": "Frontend developer",
        "description": "Collect loading metrics, console errors, network observations, and Core Web Vitals for a target page."
      },
      {
        "title": "Collect Page Evidence",
        "target_user": "Research analyst",
        "description": "Open specified pages, extract visible information, and return a concise summary with source page context."
      }
    ],
    "prompt_templates": [
      {
        "title": "Capture a Page Screenshot",
        "scenario": "Beginner screenshot task",
        "prompt": "Open the target URL, wait for the page to finish loading, capture a full-page screenshot, and summarize the visible page title."
      },
      {
        "title": "Test a Form Submission",
        "scenario": "Intermediate interaction task",
        "prompt": "Use the current page to fill the specified form fields, submit the form, wait for the response, and report success or failure."
      },
      {
        "title": "Measure Page Performance",
        "scenario": "Advanced performance task",
        "prompt": "Open the target URL, run a performance trace during reload, capture Core Web Vitals, and list the largest bottlenecks."
      },
      {
        "title": "Run a Multi-Step Audit",
        "scenario": "Advanced workflow task",
        "prompt": "Navigate through the requested pages, perform each browser action in order, collect screenshots or metrics, and return only key findings."
      }
    ],
    "output_examples": [
      {
        "input": "Open a product page and capture a screenshot.",
        "output": "The agent loaded the page, saved a full-page screenshot, and reported the product title and visible page status."
      },
      {
        "input": "Analyze a landing page under slow network conditions.",
        "output": "The agent simulated slow network speed, measured loading behavior, restored normal settings, and summarized the most important delays."
      },
      {
        "input": "Extract all visible article titles from the current page.",
        "output": "The agent collected the visible titles, removed duplicates, and returned a short list with the page context."
      }
    ],
    "best_practices": [
      "Use specific URLs and expected outcomes so the delegated agent can stop quickly.",
      "Request summaries of only important page state, errors, screenshots, or measurements.",
      "Confirm permission before using authenticated pages or collecting page data."
    ],
    "anti_patterns": [
      "Using the skill to bypass login, paywalls, captchas, or site rules.",
      "Sending real passwords or private tokens in reusable prompt examples.",
      "Asking for broad crawling without scope, rate limits, or data minimization."
    ],
    "faq": [
      {
        "question": "What does this skill delegate?",
        "answer": "It delegates browser navigation, page interaction, screenshots, performance checks, testing, data extraction, and network simulation."
      },
      {
        "question": "Does it run browser work in the main chat?",
        "answer": "No. It routes browser work to a chrome-devtools-expert agent and asks that agent to return concise results."
      },
      {
        "question": "Which tools does it depend on?",
        "answer": "It expects a Chrome DevTools MCP setup and access to the named browser automation subagent."
      },
      {
        "question": "Can it interact with private pages?",
        "answer": "Only when the user has permission and provides clear scope. Sensitive page data should be minimized."
      },
      {
        "question": "Can it perform scraping?",
        "answer": "It can extract page information, but users should respect site rules, privacy limits, and rate limits."
      },
      {
        "question": "Is it useful for Claude, Codex, and Claude Code?",
        "answer": "Yes. The marketplace metadata lists compatibility with Claude, Codex, and Claude Code."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 171
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall