[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DFGZCS6KFD2C6DRGH8969F":3,"skill-same:01M6DFGZCS6KFD2C6DRGH8969F":73},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6DFGZCS6KFD2C6DRGH8969F","one-three-one-rule",null,"Structured decision-making framework for technical proposals and trade-off analysis. When the user faces a choice between multiple approaches (architecture decisions, tool selection, refactoring strategies, migration paths), this skill produces a 1-3-1 format: one clear problem statement, three distinct options with pros\u002Fcons, and one concrete recommendation with definition of done and implementation plan. Use when the user asks for a \"1-3-1\", says \"give me options\", or needs help choosing between competing approaches.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F4c\u002F4cdc4bde4d44af5e4821ffea50bc6c7093ad2d550da96d73a78da949c5f6e70a\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"one three one rule","three","proposals","strategies","decision-making","trade","me","done","selection","use","definition of done","decisions","technical","choice","decision","tool","plan","analysis","communication","architecture","2026-11-10 10:12:30",false,"---\r\nname: one-three-one-rule\r\ndescription: >\r\n  Structured decision-making framework for technical proposals and trade-off analysis.\r\n  When the user faces a choice between multiple approaches (architecture decisions,\r\n  tool selection, refactoring strategies, migration paths), this skill produces a\r\n  1-3-1 format: one clear problem statement, three distinct options with pros\u002Fcons,\r\n  and one concrete recommendation with definition of done and implementation plan.\r\n  Use when the user asks for a \"1-3-1\", says \"give me options\", or needs help\r\n  choosing between competing approaches.\r\nversion: 1.0.0\r\nauthor: Willard Moore\r\nlicense: MIT\r\ncategory: communication\r\nmetadata:\r\n  hermes:\r\n    tags: [communication, decision-making, proposals, trade-offs]\r\n---\r\n\r\n# 1-3-1 Communication Rule\r\n\r\nStructured decision-making format for when a task has multiple viable approaches and the user needs a clear recommendation. Produces a concise problem framing, three options with trade-offs, and an actionable plan for the recommended path.\r\n\r\n## When to Use\r\n\r\n- The user explicitly asks for a \"1-3-1\" response.\r\n- The user says \"give me options\" or \"what are my choices\" for a technical decision.\r\n- A task has multiple viable approaches with meaningful trade-offs (architecture, tooling, migration strategy).\r\n- The user needs a proposal they can forward to a team or stakeholder.\r\n\r\nDo NOT use for simple questions with one obvious answer, debugging sessions, or tasks where the user has already decided on an approach.\r\n\r\n## Procedure\r\n\r\n1. **Problem** (one sentence)\r\n   - State the core decision or desired outcome in a single concise sentence.\r\n   - Focus on the *what*, not the *how* — no implementation details, tool names, or specific technologies.\r\n   - Keep it tight. If you need \"and\", you're describing two problems.\r\n\r\n2. **Options** (exactly three)\r\n   - Present three distinct, viable approaches labeled A, B, C.\r\n   - Each option gets a brief description, pros, and cons.\r\n   - Options should represent genuinely different strategies, not minor variations of the same approach.\r\n\r\n3. **Recommendation** (one option)\r\n   - State which option you recommend and why, based on the user's context and priorities.\r\n   - Be direct — this is your professional judgment, not a hedge.\r\n\r\n4. **Definition of Done**\r\n   - List the specific success criteria for the recommended option.\r\n   - These are concrete, verifiable outcomes — not vague aspirations.\r\n   - If the user picks a different option, revise this section to match.\r\n\r\n5. **Implementation Plan**\r\n   - Concrete steps to execute the recommended option.\r\n   - Include specific commands, tools, or actions where applicable.\r\n   - If the user picks a different option, revise this section to match.\r\n\r\n## Verification\r\n\r\n- Response has exactly one Problem sentence.\r\n- Response has exactly three Options (A, B, C) with pros and cons for each.\r\n- Response has a single Recommendation that picks one option with reasoning.\r\n- Definition of Done and Implementation Plan align with the recommended option.\r\n- If the user selects a different option, Recommendation, DoD, and Implementation Plan update accordingly.\r\n\r\n## Example\r\n\r\nUser: \"Give me a 1-3-1 for adding retry logic to our API client.\"\r\n\r\nAgent:\r\n\r\n**Problem:** API calls to external services fail intermittently under load and need graceful retry handling.\r\n\r\n**Options:**\r\n\r\n- **Option A: Exponential backoff with jitter in a shared utility.**\r\n  Pros: Simple, well-understood pattern; single implementation shared across all callers.\r\n  Cons: No circuit-breaking; callers still block during retries.\r\n\r\n- **Option B: Retry library (tenacity) as a decorator on each endpoint call.**\r\n  Pros: Configurable per-endpoint; built-in support for circuit breakers and rate limits.\r\n  Cons: Adds a dependency; decorator pattern can obscure control flow.\r\n\r\n- **Option C: Queue-based async retry with dead letter handling.**\r\n  Pros: Non-blocking; failed calls are tracked and replayable; scales well.\r\n  Cons: Significant complexity increase; requires a queue backend; overkill for low-volume services.\r\n\r\n**Recommendation:** Option A. The call volume doesn't justify queue infrastructure, and a shared utility with exponential backoff + jitter covers the failure mode cleanly without new dependencies.\r\n\r\n**Definition of Done:**\r\n- `api_retry()` utility handles transient HTTP errors (429, 502, 503, 504).\r\n- Retries up to 3 times with exponential backoff and jitter.\r\n- All external API calls route through the retry utility.\r\n- Logs each retry attempt with endpoint and attempt number.\r\n- Tests cover retry exhaustion, immediate success, and transient-then-success scenarios.\r\n\r\n**Implementation Plan:**\r\n1. Create `utils\u002Fapi_retry.py` with configurable max retries, base delay, and retryable status codes.\r\n2. Add jitter using `random.uniform(0, base_delay)` to prevent thundering herd.\r\n3. Wrap existing API calls in `api_client.py` with the retry utility.\r\n4. Add unit tests mocking HTTP responses for each retry scenario.\r\n5. Verify under load with a simple stress test against a flaky endpoint mock.\r\n","# 1-3-1 Communication Rule\r\n\r\nStructured decision-making format for when a task has multiple viable approaches and the user needs a clear recommendation. Produces a concise problem framing, three options with trade-offs, and an actionable plan for the recommended path.\r\n\r\n## When to Use\r\n\r\n- The user explicitly asks for a \"1-3-1\" response.\r\n- The user says \"give me options\" or \"what are my choices\" for a technical decision.\r\n- A task has multiple viable approaches with meaningful trade-offs (architecture, tooling, migration strategy).\r\n- The user needs a proposal they can forward to a team or stakeholder.\r\n\r\nDo NOT use for simple questions with one obvious answer, debugging sessions, or tasks where the user has already decided on an approach.\r\n\r\n## Procedure\r\n\r\n1. **Problem** (one sentence)\r\n   - State the core decision or desired outcome in a single concise sentence.\r\n   - Focus on the *what*, not the *how* — no implementation details, tool names, or specific technologies.\r\n   - Keep it tight. If you need \"and\", you're describing two problems.\r\n\r\n2. **Options** (exactly three)\r\n   - Present three distinct, viable approaches labeled A, B, C.\r\n   - Each option gets a brief description, pros, and cons.\r\n   - Options should represent genuinely different strategies, not minor variations of the same approach.\r\n\r\n3. **Recommendation** (one option)\r\n   - State which option you recommend and why, based on the user's context and priorities.\r\n   - Be direct — this is your professional judgment, not a hedge.\r\n\r\n4. **Definition of Done**\r\n   - List the specific success criteria for the recommended option.\r\n   - These are concrete, verifiable outcomes — not vague aspirations.\r\n   - If the user picks a different option, revise this section to match.\r\n\r\n5. **Implementation Plan**\r\n   - Concrete steps to execute the recommended option.\r\n   - Include specific commands, tools, or actions where applicable.\r\n   - If the user picks a different option, revise this section to match.\r\n\r\n## Verification\r\n\r\n- Response has exactly one Problem sentence.\r\n- Response has exactly three Options (A, B, C) with pros and cons for each.\r\n- Response has a single Recommendation that picks one option with reasoning.\r\n- Definition of Done and Implementation Plan align with the recommended option.\r\n- If the user selects a different option, Recommendation, DoD, and Implementation Plan update accordingly.\r\n\r\n## Example\r\n\r\nUser: \"Give me a 1-3-1 for adding retry logic to our API client.\"\r\n\r\nAgent:\r\n\r\n**Problem:** API calls to external services fail intermittently under load and need graceful retry handling.\r\n\r\n**Options:**\r\n\r\n- **Option A: Exponential backoff with jitter in a shared utility.**\r\n  Pros: Simple, well-understood pattern; single implementation shared across all callers.\r\n  Cons: No circuit-breaking; callers still block during retries.\r\n\r\n- **Option B: Retry library (tenacity) as a decorator on each endpoint call.**\r\n  Pros: Configurable per-endpoint; built-in support for circuit breakers and rate limits.\r\n  Cons: Adds a dependency; decorator pattern can obscure control flow.\r\n\r\n- **Option C: Queue-based async retry with dead letter handling.**\r\n  Pros: Non-blocking; failed calls are tracked and replayable; scales well.\r\n  Cons: Significant complexity increase; requires a queue backend; overkill for low-volume services.\r\n\r\n**Recommendation:** Option A. The call volume doesn't justify queue infrastructure, and a shared utility with exponential backoff + jitter covers the failure mode cleanly without new dependencies.\r\n\r\n**Definition of Done:**\r\n- `api_retry()` utility handles transient HTTP errors (429, 502, 503, 504).\r\n- Retries up to 3 times with exponential backoff and jitter.\r\n- All external API calls route through the retry utility.\r\n- Logs each retry attempt with endpoint and attempt number.\r\n- Tests cover retry exhaustion, immediate success, and transient-then-success scenarios.\r\n\r\n**Implementation Plan:**\r\n1. Create `utils\u002Fapi_retry.py` with configurable max retries, base delay, and retryable status codes.\r\n2. Add jitter using `random.uniform(0, base_delay)` to prevent thundering herd.\r\n3. Wrap existing API calls in `api_client.py` with the retry utility.\r\n4. Add unit tests mocking HTTP responses for each retry scenario.\r\n5. Verify under load with a simple stress test against a flaky endpoint mock.\r\n",{"name":5,"author":44,"license":15,"version":45,"category":37,"metadata":46,"description":50},"Willard Moore","1.0.0",{"hermes":47},{"tags":48},[37,23,21,49],"trade-offs","Structured decision-making framework for technical proposals and trade-off analysis. When the user faces a choice between multiple approaches (architecture decisions, tool selection, refactoring strategies, migration paths), this skill produces a 1-3-1 format: one clear problem statement, three distinct options with pros\u002Fcons, and one concrete recommendation with definition of done and implementation plan. Use when the user asks for a \"1-3-1\", says \"give me options\", or needs help choosing between competing approaches.\n","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F4c\u002F4cdc4bde4d44af5e4821ffea50bc6c7093ad2d550da96d73a78da949c5f6e70a",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add zapabob\u002FSkills --skill one-three-one-rule",{"tool":65,"command":66},"bunx","bunx skills add zapabob\u002FSkills --skill one-three-one-rule",{"tool":68,"command":69},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill one-three-one-rule","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F4c\u002F4cdc4bde4d44af5e4821ffea50bc6c7093ad2d550da96d73a78da949c5f6e70a\u002FSKILL.md",true,[],[74,112,147,173,200,217],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":93,"publishedAt":39},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[80,85,88],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":86,"categoryName":87,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[76,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,51,109,110,111],"openclaw","macos","cli","github","linux","windows","official","search","https","social-media","api","Media","hermes","hermes agent","twitter","social","via","post",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":129,"publishedAt":39},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[118,121,124,125,126],{"categoryNo":119,"categoryName":120,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":122,"categoryName":123,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":86,"categoryName":87,"taxonomyType":83,"taxonomyTypeDesc":84},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},{"categoryNo":127,"categoryName":128,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000036","内容创作者",[130,131,132,133,95,134,98,135,99,136,137,138,139,140,141,142,143,144,145,146],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":156,"publishedAt":39},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[153],{"categoryNo":154,"categoryName":155,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000016","图像与多媒体",[149,95,98,157,158,159,160,161,162,163,164,165,28,166,167,168,169,170,171,172],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":182,"publishedAt":39},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[179],{"categoryNo":180,"categoryName":181,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000013","分析与可视化",[183,95,184,185,99,186,187,188,189,190,191,164,192,193,194,195,196,197,198,199],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":207,"publishedAt":39},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[206],{"categoryNo":86,"categoryName":87,"taxonomyType":83,"taxonomyTypeDesc":84},[202,95,208,97,98,209,210,211,212,213,214,106,107,215,216],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":225,"publishedAt":39},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[223,224],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[226,227,228,98,229,157,230,231,232,160,233,104,234,235,236,237,238,239,240,241],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]