[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CJRB99Y8002VRJDCTV148C":3,"skill-same:01M7CJRB99Y8002VRJDCTV148C":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7CJRB99Y8002VRJDCTV148C","evaluation",null,"Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fskills\u002Fevaluation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: evaluation\ndescription: \"Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.\"\nrisk: safe\nsource: \"https:\u002F\u002Fgithub.com\u002Fmuratcankoylan\u002FAgent-Skills-for-Context-Engineering\u002Ftree\u002Fmain\u002Fskills\u002Fevaluation\"\ndate_added: \"2026-02-27\"\n---\n\n## When to Use This Skill\n\nBuild evaluation frameworks for agent systems\n\nUse this skill when working with build evaluation frameworks for agent systems.\n# Evaluation Methods for Agent Systems\n\nEvaluation of agent systems requires different approaches than traditional software or even standard language model applications. Agents make dynamic decisions, are non-deterministic between runs, and often lack single correct answers. Effective evaluation must account for these characteristics while providing actionable feedback. A robust evaluation framework enables continuous improvement, catches regressions, and validates that context engineering choices achieve intended effects.\n\n## When to Use\nActivate this skill when:\n- Testing agent performance systematically\n- Validating context engineering choices\n- Measuring improvements over time\n- Catching regressions before deployment\n- Building quality gates for agent pipelines\n- Comparing different agent configurations\n- Evaluating production systems continuously\n\n## Core Concepts\n\nAgent evaluation requires outcome-focused approaches that account for non-determinism and multiple valid paths. Multi-dimensional rubrics capture various quality aspects: factual accuracy, completeness, citation accuracy, source quality, and tool efficiency. LLM-as-judge provides scalable evaluation while human evaluation catches edge cases.\n\nThe key insight is that agents may find alternative paths to goals—the evaluation should judge whether they achieve right outcomes while following reasonable processes.\n\n**Performance Drivers: The 95% Finding**\nResearch on the BrowseComp evaluation (which tests browsing agents' ability to locate hard-to-find information) found that three factors explain 95% of performance variance:\n\n| Factor | Variance Explained | Implication |\n|--------|-------------------|-------------|\n| Token usage | 80% | More tokens = better performance |\n| Number of tool calls | ~10% | More exploration helps |\n| Model choice | ~5% | Better models multiply efficiency |\n\nThis finding has significant implications for evaluation design:\n- **Token budgets matter**: Evaluate agents with realistic token budgets, not unlimited resources\n- **Model upgrades beat token increases**: Upgrading to Claude Sonnet 4.5 or GPT-5.2 provides larger gains than doubling token budgets on previous versions\n- **Multi-agent validation**: The finding validates architectures that distribute work across agents with separate context windows\n\n## Detailed Topics\n\n### Evaluation Challenges\n\n**Non-Determinism and Multiple Valid Paths**\nAgents may take completely different valid paths to reach goals. One agent might search three sources while another searches ten. They might use different tools to find the same answer. Traditional evaluations that check for specific steps fail in this context.\n\nThe solution is outcome-focused evaluation that judges whether agents achieve right outcomes while following reasonable processes.\n\n**Context-Dependent Failures**\nAgent failures often depend on context in subtle ways. An agent might succeed on simple queries but fail on complex ones. It might work well with one tool set but fail with another. Failures may emerge only after extended interaction when context accumulates.\n\nEvaluation must cover a range of complexity levels and test extended interactions, not just isolated queries.\n\n**Composite Quality Dimensions**\nAgent quality is not a single dimension. It includes factual accuracy, completeness, coherence, tool efficiency, and process quality. An agent might score high on accuracy but low in efficiency, or vice versa.\n\nEvaluation rubrics must capture multiple dimensions with appropriate weighting for the use case.\n\n### Evaluation Rubric Design\n\n**Multi-Dimensional Rubric**\nEffective rubrics cover key dimensions with descriptive levels:\n\nFactual accuracy: Claims match ground truth (excellent to failed)\n\nCompleteness: Output covers requested aspects (excellent to failed)\n\nCitation accuracy: Citations match claimed sources (excellent to failed)\n\nSource quality: Uses appropriate primary sources (excellent to failed)\n\nTool efficiency: Uses right tools reasonable number of times (excellent to failed)\n\n**Rubric Scoring**\nConvert dimension assessments to numeric scores (0.0 to 1.0) with appropriate weighting. Calculate weighted overall scores. Determine passing threshold based on use case requirements.\n\n### Evaluation Methodologies\n\n**LLM-as-Judge**\nLLM-based evaluation scales to large test sets and provides consistent judgments. The key is designing effective evaluation prompts that capture the dimensions of interest.\n\nProvide clear task description, agent output, ground truth (if available), evaluation scale with level descriptions, and request structured judgment.\n\n**Human Evaluation**\nHuman evaluation catches what automation misses. Humans notice hallucinated answers on unusual queries, system failures, and subtle biases that automated evaluation misses.\n\nEffective human evaluation covers edge cases, samples systematically, tracks patterns, and provides contextual understanding.\n\n**End-State Evaluation**\nFor agents that mutate persistent state, end-state evaluation focuses on whether the final state matches expectations rather than how the agent got there.\n\n### Test Set Design\n\n**Sample Selection**\nStart with small samples during development. Early in agent development, changes have dramatic impacts because there is abundant low-hanging fruit. Small test sets reveal large effects.\n\nSample from real usage patterns. Add known edge cases. Ensure coverage across complexity levels.\n\n**Complexity Stratification**\nTest sets should span complexity levels: simple (single tool call), medium (multiple tool calls), complex (many tool calls, significant ambiguity), and very complex (extended interaction, deep reasoning).\n\n### Context Engineering Evaluation\n\n**Testing Context Strategies**\nContext engineering choices should be validated through systematic evaluation. Run agents with different context strategies on the same test set. Compare quality scores, token usage, and efficiency metrics.\n\n**Degradation Testing**\nTest how context degradation affects performance by running agents at different context sizes. Identify performance cliffs where context becomes problematic. Establish safe operating limits.\n\n### Continuous Evaluation\n\n**Evaluation Pipeline**\nBuild evaluation pipelines that run automatically on agent changes. Track results over time. Compare versions to identify improvements or regressions.\n\n**Monitoring Production**\nTrack evaluation metrics in production by sampling interactions and evaluating randomly. Set alerts for quality drops. Maintain dashboards for trend analysis.\n\n## Practical Guidance\n\n### Building Evaluation Frameworks\n\n1. Define quality dimensions relevant to your use case\n2. Create rubrics with clear, actionable level descriptions\n3. Build test sets from real usage patterns and edge cases\n4. Implement automated evaluation pipelines\n5. Establish baseline metrics before making changes\n6. Run evaluations on all significant changes\n7. Track metrics over time for trend analysis\n8. Supplement automated evaluation with human review\n\n### Avoiding Evaluation Pitfalls\n\nOverfitting to specific paths: Evaluate outcomes, not specific steps.\nIgnoring edge cases: Include diverse test scenarios.\nSingle-metric obsession: Use multi-dimensional rubrics.\nNeglecting context effects: Test with realistic context sizes.\nSkipping human evaluation: Automated evaluation misses subtle issues.\n\n## Examples\n\n**Example 1: Simple Evaluation**\n```python\ndef evaluate_agent_response(response, expected):\n    rubric = load_rubric()\n    scores = {}\n    for dimension, config in rubric.items():\n        scores[dimension] = assess_dimension(response, expected, dimension)\n    overall = weighted_average(scores, config[\"weights\"])\n    return {\"passed\": overall >= 0.7, \"scores\": scores}\n```\n\n**Example 2: Test Set Structure**\n\nTest sets should span multiple complexity levels to ensure comprehensive evaluation:\n\n```python\ntest_set = [\n    {\n        \"name\": \"simple_lookup\",\n        \"input\": \"What is the capital of France?\",\n        \"expected\": {\"type\": \"fact\", \"answer\": \"Paris\"},\n        \"complexity\": \"simple\",\n        \"description\": \"Single tool call, factual lookup\"\n    },\n    {\n        \"name\": \"medium_query\",\n        \"input\": \"Compare the revenue of Apple and Microsoft last quarter\",\n        \"complexity\": \"medium\",\n        \"description\": \"Multiple tool calls, comparison logic\"\n    },\n    {\n        \"name\": \"multi_step_reasoning\",\n        \"input\": \"Analyze sales data from Q1-Q4 and create a summary report with trends\",\n        \"complexity\": \"complex\",\n        \"description\": \"Many tool calls, aggregation, analysis\"\n    },\n    {\n        \"name\": \"research_synthesis\",\n        \"input\": \"Research emerging AI technologies, evaluate their potential impact, and recommend adoption strategy\",\n        \"complexity\": \"very_complex\",\n        \"description\": \"Extended interaction, deep reasoning, synthesis\"\n    }\n]\n```\n\n## Guidelines\n\n1. Use multi-dimensional rubrics, not single metrics\n2. Evaluate outcomes, not specific execution paths\n3. Cover complexity levels from simple to complex\n4. Test with realistic context sizes and histories\n5. Run evaluations continuously, not just before release\n6. Supplement LLM evaluation with human review\n7. Track metrics over time for trend detection\n8. Set clear pass\u002Ffail thresholds based on use case\n\n## Integration\n\nThis skill connects to all other skills as a cross-cutting concern:\n\n- context-fundamentals - Evaluating context usage\n- context-degradation - Detecting degradation\n- context-optimization - Measuring optimization effectiveness\n- multi-agent-patterns - Evaluating coordination\n- tool-design - Evaluating tool effectiveness\n- memory-systems - Evaluating memory quality\n\n## References\n\nInternal reference:\n- Metrics Reference - Detailed evaluation metrics and implementation\n\n## References\n\nInternal skills:\n- All other skills connect to evaluation for quality measurement\n\nExternal resources:\n- LLM evaluation benchmarks\n- Agent evaluation research papers\n- Production monitoring practices\n\n---\n\n## Skill Metadata\n\n**Created**: 2025-12-20\n**Last Updated**: 2025-12-20\n**Author**: Agent Skills for Context Engineering Contributors\n**Version**: 1.0.0\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","## When to Use This Skill\n\nBuild evaluation frameworks for agent systems\n\nUse this skill when working with build evaluation frameworks for agent systems.\n# Evaluation Methods for Agent Systems\n\nEvaluation of agent systems requires different approaches than traditional software or even standard language model applications. Agents make dynamic decisions, are non-deterministic between runs, and often lack single correct answers. Effective evaluation must account for these characteristics while providing actionable feedback. A robust evaluation framework enables continuous improvement, catches regressions, and validates that context engineering choices achieve intended effects.\n\n## When to Use\nActivate this skill when:\n- Testing agent performance systematically\n- Validating context engineering choices\n- Measuring improvements over time\n- Catching regressions before deployment\n- Building quality gates for agent pipelines\n- Comparing different agent configurations\n- Evaluating production systems continuously\n\n## Core Concepts\n\nAgent evaluation requires outcome-focused approaches that account for non-determinism and multiple valid paths. Multi-dimensional rubrics capture various quality aspects: factual accuracy, completeness, citation accuracy, source quality, and tool efficiency. LLM-as-judge provides scalable evaluation while human evaluation catches edge cases.\n\nThe key insight is that agents may find alternative paths to goals—the evaluation should judge whether they achieve right outcomes while following reasonable processes.\n\n**Performance Drivers: The 95% Finding**\nResearch on the BrowseComp evaluation (which tests browsing agents' ability to locate hard-to-find information) found that three factors explain 95% of performance variance:\n\n| Factor | Variance Explained | Implication |\n|--------|-------------------|-------------|\n| Token usage | 80% | More tokens = better performance |\n| Number of tool calls | ~10% | More exploration helps |\n| Model choice | ~5% | Better models multiply efficiency |\n\nThis finding has significant implications for evaluation design:\n- **Token budgets matter**: Evaluate agents with realistic token budgets, not unlimited resources\n- **Model upgrades beat token increases**: Upgrading to Claude Sonnet 4.5 or GPT-5.2 provides larger gains than doubling token budgets on previous versions\n- **Multi-agent validation**: The finding validates architectures that distribute work across agents with separate context windows\n\n## Detailed Topics\n\n### Evaluation Challenges\n\n**Non-Determinism and Multiple Valid Paths**\nAgents may take completely different valid paths to reach goals. One agent might search three sources while another searches ten. They might use different tools to find the same answer. Traditional evaluations that check for specific steps fail in this context.\n\nThe solution is outcome-focused evaluation that judges whether agents achieve right outcomes while following reasonable processes.\n\n**Context-Dependent Failures**\nAgent failures often depend on context in subtle ways. An agent might succeed on simple queries but fail on complex ones. It might work well with one tool set but fail with another. Failures may emerge only after extended interaction when context accumulates.\n\nEvaluation must cover a range of complexity levels and test extended interactions, not just isolated queries.\n\n**Composite Quality Dimensions**\nAgent quality is not a single dimension. It includes factual accuracy, completeness, coherence, tool efficiency, and process quality. An agent might score high on accuracy but low in efficiency, or vice versa.\n\nEvaluation rubrics must capture multiple dimensions with appropriate weighting for the use case.\n\n### Evaluation Rubric Design\n\n**Multi-Dimensional Rubric**\nEffective rubrics cover key dimensions with descriptive levels:\n\nFactual accuracy: Claims match ground truth (excellent to failed)\n\nCompleteness: Output covers requested aspects (excellent to failed)\n\nCitation accuracy: Citations match claimed sources (excellent to failed)\n\nSource quality: Uses appropriate primary sources (excellent to failed)\n\nTool efficiency: Uses right tools reasonable number of times (excellent to failed)\n\n**Rubric Scoring**\nConvert dimension assessments to numeric scores (0.0 to 1.0) with appropriate weighting. Calculate weighted overall scores. Determine passing threshold based on use case requirements.\n\n### Evaluation Methodologies\n\n**LLM-as-Judge**\nLLM-based evaluation scales to large test sets and provides consistent judgments. The key is designing effective evaluation prompts that capture the dimensions of interest.\n\nProvide clear task description, agent output, ground truth (if available), evaluation scale with level descriptions, and request structured judgment.\n\n**Human Evaluation**\nHuman evaluation catches what automation misses. Humans notice hallucinated answers on unusual queries, system failures, and subtle biases that automated evaluation misses.\n\nEffective human evaluation covers edge cases, samples systematically, tracks patterns, and provides contextual understanding.\n\n**End-State Evaluation**\nFor agents that mutate persistent state, end-state evaluation focuses on whether the final state matches expectations rather than how the agent got there.\n\n### Test Set Design\n\n**Sample Selection**\nStart with small samples during development. Early in agent development, changes have dramatic impacts because there is abundant low-hanging fruit. Small test sets reveal large effects.\n\nSample from real usage patterns. Add known edge cases. Ensure coverage across complexity levels.\n\n**Complexity Stratification**\nTest sets should span complexity levels: simple (single tool call), medium (multiple tool calls), complex (many tool calls, significant ambiguity), and very complex (extended interaction, deep reasoning).\n\n### Context Engineering Evaluation\n\n**Testing Context Strategies**\nContext engineering choices should be validated through systematic evaluation. Run agents with different context strategies on the same test set. Compare quality scores, token usage, and efficiency metrics.\n\n**Degradation Testing**\nTest how context degradation affects performance by running agents at different context sizes. Identify performance cliffs where context becomes problematic. Establish safe operating limits.\n\n### Continuous Evaluation\n\n**Evaluation Pipeline**\nBuild evaluation pipelines that run automatically on agent changes. Track results over time. Compare versions to identify improvements or regressions.\n\n**Monitoring Production**\nTrack evaluation metrics in production by sampling interactions and evaluating randomly. Set alerts for quality drops. Maintain dashboards for trend analysis.\n\n## Practical Guidance\n\n### Building Evaluation Frameworks\n\n1. Define quality dimensions relevant to your use case\n2. Create rubrics with clear, actionable level descriptions\n3. Build test sets from real usage patterns and edge cases\n4. Implement automated evaluation pipelines\n5. Establish baseline metrics before making changes\n6. Run evaluations on all significant changes\n7. Track metrics over time for trend analysis\n8. Supplement automated evaluation with human review\n\n### Avoiding Evaluation Pitfalls\n\nOverfitting to specific paths: Evaluate outcomes, not specific steps.\nIgnoring edge cases: Include diverse test scenarios.\nSingle-metric obsession: Use multi-dimensional rubrics.\nNeglecting context effects: Test with realistic context sizes.\nSkipping human evaluation: Automated evaluation misses subtle issues.\n\n## Examples\n\n**Example 1: Simple Evaluation**\n```python\ndef evaluate_agent_response(response, expected):\n    rubric = load_rubric()\n    scores = {}\n    for dimension, config in rubric.items():\n        scores[dimension] = assess_dimension(response, expected, dimension)\n    overall = weighted_average(scores, config[\"weights\"])\n    return {\"passed\": overall >= 0.7, \"scores\": scores}\n```\n\n**Example 2: Test Set Structure**\n\nTest sets should span multiple complexity levels to ensure comprehensive evaluation:\n\n```python\ntest_set = [\n    {\n        \"name\": \"simple_lookup\",\n        \"input\": \"What is the capital of France?\",\n        \"expected\": {\"type\": \"fact\", \"answer\": \"Paris\"},\n        \"complexity\": \"simple\",\n        \"description\": \"Single tool call, factual lookup\"\n    },\n    {\n        \"name\": \"medium_query\",\n        \"input\": \"Compare the revenue of Apple and Microsoft last quarter\",\n        \"complexity\": \"medium\",\n        \"description\": \"Multiple tool calls, comparison logic\"\n    },\n    {\n        \"name\": \"multi_step_reasoning\",\n        \"input\": \"Analyze sales data from Q1-Q4 and create a summary report with trends\",\n        \"complexity\": \"complex\",\n        \"description\": \"Many tool calls, aggregation, analysis\"\n    },\n    {\n        \"name\": \"research_synthesis\",\n        \"input\": \"Research emerging AI technologies, evaluate their potential impact, and recommend adoption strategy\",\n        \"complexity\": \"very_complex\",\n        \"description\": \"Extended interaction, deep reasoning, synthesis\"\n    }\n]\n```\n\n## Guidelines\n\n1. Use multi-dimensional rubrics, not single metrics\n2. Evaluate outcomes, not specific execution paths\n3. Cover complexity levels from simple to complex\n4. Test with realistic context sizes and histories\n5. Run evaluations continuously, not just before release\n6. Supplement LLM evaluation with human review\n7. Track metrics over time for trend detection\n8. Set clear pass\u002Ffail thresholds based on use case\n\n## Integration\n\nThis skill connects to all other skills as a cross-cutting concern:\n\n- context-fundamentals - Evaluating context usage\n- context-degradation - Detecting degradation\n- context-optimization - Measuring optimization effectiveness\n- multi-agent-patterns - Evaluating coordination\n- tool-design - Evaluating tool effectiveness\n- memory-systems - Evaluating memory quality\n\n## References\n\nInternal reference:\n- Metrics Reference - Detailed evaluation metrics and implementation\n\n## References\n\nInternal skills:\n- All other skills connect to evaluation for quality measurement\n\nExternal resources:\n- LLM evaluation benchmarks\n- Agent evaluation research papers\n- Production monitoring practices\n\n---\n\n## Skill Metadata\n\n**Created**: 2025-12-20\n**Last Updated**: 2025-12-20\n**Author**: Agent Skills for Context Engineering Contributors\n**Version**: 1.0.0\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":24,"source":25,"date_added":26,"description":7},"safe","https:\u002F\u002Fgithub.com\u002Fmuratcankoylan\u002FAgent-Skills-for-Context-Engineering\u002Ftree\u002Fmain\u002Fskills\u002Fevaluation","2026-02-27","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fskills\u002Fevaluation",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill evaluation",{"tool":42,"command":43},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill evaluation",{"tool":45,"command":46},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fskills\u002Fevaluation\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]