[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M777E4EV63VBPX5YZPBCWMC8":3,"skill-same:01M777E4EV63VBPX5YZPBCWMC8":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M777E4EV63VBPX5YZPBCWMC8","b3ehive",null,"javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweiyangzen\u002Fb3ehive\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# b3ehive Skill Specification\n## PCTF-Compliant Multi-Agent Competition System\n\n---\n\n## 1. Purpose (PCTF: Purpose)\n\nEnable competitive code generation where three isolated AI agents implement the same functionality, evaluate each other objectively, and deliver the optimal solution through data-driven selection.\n\n---\n\n## 2. Task Definition (PCTF: Task)\n\n### Input\n- **task_description**: String describing the coding task\n- **constraints**: Optional constraints (time\u002Fspace complexity, language, etc.)\n\n### Output\n- **final_solution**: Directory containing the winning implementation\n- **comparison_report**: Markdown analysis of all three approaches\n- **decision_rationale**: Explanation of why the winner was selected\n\n### Success Criteria\n```yaml\nassertions:\n  - final_solution\u002Fimplementation exists and is runnable\n  - comparison_report.md exists with objective metrics\n  - decision_rationale.md explains selection logic\n  - all three agent implementations are documented\n  - evaluation scores are numeric and justified\n```\n\n---\n\n## 3. Chain Flow (PCTF: Chain)\n\n```mermaid\ngraph TD\n    A[User Task] --> B[Phase 1: Parallel Spawn]\n    B --> C[Agent A: Simplicity]\n    B --> D[Agent B: Speed]\n    B --> E[Agent C: Robustness]\n    C --> F[Phase 2: Cross-Evaluation]\n    D --> F\n    E --> F\n    F --> G[6 Evaluation Reports]\n    G --> H[Phase 3: Self-Scoring]\n    H --> I[3 Scorecards]\n    I --> J[Phase 4: Final Delivery]\n    J --> K[Best Solution]\n```\n\n### Phase 1: Parallel Implementation\n**Agent Prompt Template**:\n```yaml\nrole: \"Expert Software Engineer\"\nfocus: \"{{agent_focus}}\"  # Simplicity \u002F Speed \u002F Robustness\ntask: \"{{task_description}}\"\nconstraints:\n  - Complete runnable code in implementation\u002F\n  - Checklist.md with ALL items checked\n  - SUMMARY.md with competitive advantages\n  - Must differ from other agents' approaches\n\nlinter_rules:\n  - code_compiles: true\n  - tests_pass: true\n  - no_todos: true\n  - documented: true\n\nassertions:\n  - implementation\u002Fmain.* exists\n  - tests exist and pass\n  - Checklist.md is complete\n  - SUMMARY.md explains unique approach\n```\n\n### Phase 2: Cross-Evaluation\n**Evaluation Prompt Template**:\n```yaml\nevaluator: \"Agent {{from}}\"\ntarget: \"Agent {{to}}\"\ntask: \"Objectively prove your solution is superior\"\n\ndimensions:\n  simplicity:\n    weight: 20\n    metrics:\n      - lines_of_code: count\n      - cyclomatic_complexity: calculate\n      - readability_score: 1-10\n  \n  speed:\n    weight: 25\n    metrics:\n      - time_complexity: big_o\n      - space_complexity: big_o\n      - benchmark_results: run_if_possible\n  \n  stability:\n    weight: 25\n    metrics:\n      - error_handling_coverage: percentage\n      - resource_cleanup: check\n      - fault_tolerance: test\n  \n  corner_cases:\n    weight: 20\n    metrics:\n      - input_validation: comprehensive\n      - boundary_conditions: covered\n      - edge_cases: tested\n  \n  maintainability:\n    weight: 10\n    metrics:\n      - documentation_quality: 1-10\n      - code_structure: logical\n      - extensibility: easy\u002Fhard\n\nassertions:\n  - evaluation is objective with data\n  - specific code snippets cited\n  - numeric scores provided\n  - persuasion argument is data-driven\n```\n\n### Phase 3: Objective Scoring\n**Scoring Prompt Template**:\n```yaml\nagent: \"Agent {{name}}\"\ntask: \"Fairly score yourself and competitors\"\n\nself_evaluation:\n  - dimension: simplicity\n    max: 20\n    score: \"{{self_score}}\"\n    justification: \"{{why}}\"\n  \n  - dimension: speed\n    max: 25\n    score: \"{{self_score}}\"\n    justification: \"{{why}}\"\n  \n  - dimension: stability\n    max: 25\n    score: \"{{self_score}}\"\n    justification: \"{{why}}\"\n  \n  - dimension: corner_cases\n    max: 20\n    score: \"{{self_score}}\"\n    justification: \"{{why}}\"\n  \n  - dimension: maintainability\n    max: 10\n    score: \"{{self_score}}\"\n    justification: \"{{why}}\"\n\npeer_evaluation:\n  - target: \"Agent {{other}}\"\n    scores: \"{{numeric_scores}}\"\n    comparison: \"{{objective_comparison}}\"\n\nfinal_conclusion:\n  best_implementation: \"[A\u002FB\u002FC\u002FMixed]\"\n  reasoning: \"{{data_driven_justification}}\"\n  recommendation: \"{{delivery_strategy}}\"\n\nassertions:\n  - all scores are numeric\n  - justifications are specific\n  - no inflation or bias\n  - conclusion is evidence-based\n```\n\n### Phase 4: Final Delivery\n**Decision Logic**:\n```python\ndef select_winner(scores):\n    \"\"\"\n    Select final solution based on competitive scores\n    \"\"\"\n    margins = calculate_score_margins(scores)\n    \n    if margins.winner - margins.second > 15:\n        # Clear winner\n        return SingleWinner(scores.winner)\n    elif margins.winner - margins.second > 5:\n        # Close competition, consider hybrid\n        return HybridSolution(scores.top_two)\n    else:\n        # Very close, pick simplest\n        return SimplestImplementation(scores.all)\n\nassertions:\n  - final_solution is runnable\n  - comparison_report explains all approaches\n  - decision_rationale is transparent\n  - attribution is given to winning agent\n```\n\n---\n\n## 4. Format Specifications (PCTF: Format)\n\n### Directory Structure\n```\nworkspace\u002F\n├── run_a\u002F\n│   ├── implementation\u002F      # Agent A code\n│   ├── Checklist.md         # Completion checklist\n│   ├── SUMMARY.md           # Approach summary\n│   ├── evaluation\u002F          # Evaluations of B, C\n│   └── SCORECARD.md         # Self-scoring\n├── run_b\u002F                   # Same structure\n├── run_c\u002F                   # Same structure\n├── final\u002F                   # Winning solution\n├── COMPARISON_REPORT.md     # Full analysis\n└── DECISION_RATIONALE.md    # Why winner selected\n```\n\n### File Formats\n- **Checklist.md**: Markdown with `- [x]` checkboxes\n- **SUMMARY.md**: Markdown with sections\n- **EVALUATION_*.md**: Markdown with tables\n- **SCORECARD.md**: Markdown with score tables\n- **Implementation**: Runnable code files\n\n---\n\n## 5. Linter & Validation\n\n### Pre-commit Checks\n```bash\n#!\u002Fbin\u002Fbash\n# scripts\u002Flint.sh\n\nlint_agent_output() {\n    local agent_dir=\"$1\"\n    local errors=0\n    \n    # Check required files exist\n    for file in Checklist.md SUMMARY.md implementation\u002Fmain.*; do\n        if [[ ! -f \"${agent_dir}\u002F${file}\" ]]; then\n            echo \"ERROR: Missing ${file}\"\n            ((errors++))\n        fi\n    done\n    \n    # Check Checklist is complete\n    if grep -q \"\\[ \\]\" \"${agent_dir}\u002FChecklist.md\"; then\n        echo \"ERROR: Checklist has unchecked items\"\n        ((errors++))\n    fi\n    \n    # Check code compiles (language-specific)\n    # ... implementation-specific checks\n    \n    return $errors\n}\n\n# Run on all agents\nfor agent in a b c; do\n    lint_agent_output \"workspace\u002Frun_${agent}\" || exit 1\ndone\n```\n\n### Runtime Assertions\n```python\ndef assert_phase_complete(phase_name):\n    \"\"\"Assert that a phase has completed successfully\"\"\"\n    assertions = {\n        \"phase1\": [\n            \"workspace\u002Frun_a\u002Fimplementation exists\",\n            \"workspace\u002Frun_b\u002Fimplementation exists\", \n            \"workspace\u002Frun_c\u002Fimplementation exists\",\n            \"All Checklist.md are complete\"\n        ],\n        \"phase2\": [\n            \"6 evaluation reports exist\",\n            \"All evaluations have numeric scores\"\n        ],\n        \"phase3\": [\n            \"3 scorecards exist\",\n            \"All scores are numeric\",\n            \"Conclusions are provided\"\n        ],\n        \"phase4\": [\n            \"final\u002Fsolution exists\",\n            \"COMPARISON_REPORT.md exists\",\n            \"DECISION_RATIONALE.md exists\"\n        ]\n    }\n    \n    for assertion in assertions[phase_name]:\n        assert evaluate(assertion), f\"Assertion failed: {assertion}\"\n```\n\n---\n\n## 6. Configuration\n\n```yaml\nb3ehive:\n  # Agent configuration\n  agents:\n    count: 3\n    model: openai-proxy\u002Fgpt-5.3-codex\n    thinking: high\n    focuses:\n      - simplicity\n      - speed\n      - robustness\n  \n  # Evaluation weights (must sum to 100)\n  evaluation:\n    dimensions:\n      simplicity: 20\n      speed: 25\n      stability: 25\n      corner_cases: 20\n      maintainability: 10\n  \n  # Delivery strategy\n  delivery:\n    strategy: auto  # auto \u002F best \u002F hybrid\n    threshold: 15   # Point margin for clear winner\n  \n  # Quality gates\n  quality:\n    lint: true\n    test: true\n    coverage_threshold: 80\n```\n\n---\n\n## 7. Usage\n\n```bash\n# Basic usage\nb3ehive \"Implement a thread-safe rate limiter\"\n\n# With constraints\nb3ehive \"Implement quicksort\" --lang python --max-lines 50\n\n# Using OpenClaw CLI\nopenclaw skills run b3ehive --task \"Your task\"\n```\n\n---\n\n## 8. License\n\nMIT © Weiyang ([@weiyangzen](https:\u002F\u002Fgithub.com\u002Fweiyangzen))\n",{},"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fweiyangzen\u002Fb3ehive",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill b3ehive",{"tool":37,"command":38},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill b3ehive",{"tool":40,"command":41},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill b3ehive","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweiyangzen\u002Fb3ehive\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]