[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7APGXSKH24PDMEXFSRX7CJA":3,"skill-same:01M7APGXSKH24PDMEXFSRX7CJA":57},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7APGXSKH24PDMEXFSRX7CJA","nowait-reasoning-optimizer",null,"Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on \"optimize reasoning\", \"reduce thinking tokens\", \"efficient inference\", \"suppress reflection tokens\", or when working with verbose CoT outputs.","GongYuanCaiJi\u002Fdsh-claude-code-templates","GongYuanCaiJi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F129952120?v=4","01M7AK39Q4W3VPF7C1K8M58BFX","劉昱廷 Yu-Ting Liu","01M7AK39QPS2RAJKRQY0EPQJPZ",0,"MIT","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fnowait\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nowait-reasoning-optimizer\ndescription: Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on \"optimize reasoning\", \"reduce thinking tokens\", \"efficient inference\", \"suppress reflection tokens\", or when working with verbose CoT outputs.\n---\n\n# NOWAIT Reasoning Optimizer\n\nImplements the NOWAIT technique from the paper \"Wait, We Don't Need to 'Wait'! Removing Thinking Tokens Improves Reasoning Efficiency\" (Wang et al., 2025).\n\n## Overview\n\nNOWAIT is a training-free inference-time intervention that suppresses self-reflection tokens (e.g., \"Wait\", \"Hmm\", \"Alternatively\") during generation, reducing chain-of-thought (CoT) trajectory length by **27-51%** without compromising model utility.\n\n## When to Use\n\n- Deploying R1-style reasoning models with limited compute\n- Reducing inference latency for production systems\n- Optimizing token costs for reasoning tasks\n- Working with verbose CoT outputs that need streamlining\n\n## Supported Models\n\n| Model Series | Type | Token Reduction |\n|--------------|------|-----------------|\n| QwQ-32B | RL-based | 16-31% |\n| Phi4-Reasoning-Plus | RL-based | 23-28% |\n| Qwen3-32B | RL-based | 13-16% |\n| Kimi-VL-A3B | Multimodal | 40-60% |\n| QvQ-72B-Preview | Multimodal | 20-30% |\n\n**Important**: NOWAIT works best with RL-based models. Distilled models (Qwen3-4B\u002F8B\u002F14B) show degraded performance when reflection tokens are suppressed.\n\n## Quick Start\n\n### 1. Basic Implementation\n\n```python\nfrom scripts.nowait_processor import NOWAITLogitProcessor\n\n# Initialize processor for your model's tokenizer\nprocessor = NOWAITLogitProcessor(tokenizer)\n\n# Use during generation\noutputs = model.generate(\n    inputs,\n    logits_processor=[processor],\n    max_new_tokens=32768\n)\n```\n\n### 2. Keywords Suppressed\n\nSee `references\u002Fkeywords.md` for the complete list. Core keywords:\n\n```\nwait, alternatively, hmm, but, however, check, \ndouble-check, maybe, verify, again, oh, ah\n```\n\n## How It Works\n\n1. **Initialize Keywords**: Identify reflection keywords from empirical analysis\n2. **Expand to Token Variants**: Map keywords to all token variants in vocabulary (e.g., \"wait\" → \" wait\", \"Wait\", \" Wait\", \".wait\", \"WAIT\")\n3. **Suppress During Inference**: Set logits of reflection tokens to large negative values during decoding\n\n```\nLogits (Before)         Logits (After)\nWait     0.8     →     Wait     -inf\nFirst    0.6     →     First    0.6\nHmm      0.5     →     Hmm      -inf\nLet      0.4     →     Let      0.4\n```\n\n## Key Findings\n\n### Why It Works\n\n- NOWAIT doesn't eliminate self-reflection entirely—it guides models to skip **unnecessary** \"waiting\" reasoning\n- Models still perform essential verification at key decision points\n- Results in more linear, straightforward reasoning paths\n\n### RL vs Distilled Models\n\n| Model Type | NOWAIT Effect | Recommendation |\n|------------|---------------|----------------|\n| RL-based (QwQ, Phi4, Qwen3-32B) | Stable accuracy, significant token reduction | ✅ Recommended |\n| Distilled (Qwen3-4B\u002F8B\u002F14B) | Accuracy degradation on hard tasks | ⚠️ Use with caution |\n\nDistilled models rely heavily on CoT structure from training data—removing reflection tokens disrupts their reasoning patterns.\n\n## Integration Examples\n\n### HuggingFace Transformers\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\nfrom scripts.nowait_processor import NOWAITLogitProcessor\n\nmodel = AutoModelForCausalLM.from_pretrained(\"Qwen\u002FQwQ-32B\")\ntokenizer = AutoTokenizer.from_pretrained(\"Qwen\u002FQwQ-32B\")\n\nprocessor = NOWAITLogitProcessor(tokenizer)\n\nresponse = model.generate(\n    tokenizer(prompt, return_tensors=\"pt\").input_ids,\n    logits_processor=[processor],\n    max_new_tokens=32768,\n    do_sample=True,\n    temperature=0.7\n)\n```\n\n### vLLM\n\n```python\nfrom vllm import LLM, SamplingParams\nfrom scripts.nowait_processor import get_nowait_bad_words_ids\n\nllm = LLM(model=\"Qwen\u002FQwQ-32B\")\nbad_words_ids = get_nowait_bad_words_ids(llm.get_tokenizer())\n\nsampling_params = SamplingParams(\n    max_tokens=32768,\n    bad_words_ids=bad_words_ids\n)\n```\n\n## Expected Results\n\n| Task Type | Original Tokens | NOWAIT Tokens | Reduction |\n|-----------|-----------------|---------------|-----------|\n| Math (AIME) | 15,000 | 10,500 | 30% |\n| Visual QA (MMMU) | 2,900 | 1,450 | 50% |\n| Video QA (MMVU) | 1,700 | 1,250 | 27% |\n\n## Limitations\n\n- Less effective on very simple problems where CoT overhead is already minimal\n- Distilled models may suffer accuracy loss on challenging tasks\n- Some domains may require model-specific keyword tuning\n\n## References\n\n- Paper: arXiv:2506.08343v2\n- Complete keyword list: `references\u002Fkeywords.md`\n- Implementation: `scripts\u002Fnowait_processor.py`","# NOWAIT Reasoning Optimizer\n\nImplements the NOWAIT technique from the paper \"Wait, We Don't Need to 'Wait'! Removing Thinking Tokens Improves Reasoning Efficiency\" (Wang et al., 2025).\n\n## Overview\n\nNOWAIT is a training-free inference-time intervention that suppresses self-reflection tokens (e.g., \"Wait\", \"Hmm\", \"Alternatively\") during generation, reducing chain-of-thought (CoT) trajectory length by **27-51%** without compromising model utility.\n\n## When to Use\n\n- Deploying R1-style reasoning models with limited compute\n- Reducing inference latency for production systems\n- Optimizing token costs for reasoning tasks\n- Working with verbose CoT outputs that need streamlining\n\n## Supported Models\n\n| Model Series | Type | Token Reduction |\n|--------------|------|-----------------|\n| QwQ-32B | RL-based | 16-31% |\n| Phi4-Reasoning-Plus | RL-based | 23-28% |\n| Qwen3-32B | RL-based | 13-16% |\n| Kimi-VL-A3B | Multimodal | 40-60% |\n| QvQ-72B-Preview | Multimodal | 20-30% |\n\n**Important**: NOWAIT works best with RL-based models. Distilled models (Qwen3-4B\u002F8B\u002F14B) show degraded performance when reflection tokens are suppressed.\n\n## Quick Start\n\n### 1. Basic Implementation\n\n```python\nfrom scripts.nowait_processor import NOWAITLogitProcessor\n\n# Initialize processor for your model's tokenizer\nprocessor = NOWAITLogitProcessor(tokenizer)\n\n# Use during generation\noutputs = model.generate(\n    inputs,\n    logits_processor=[processor],\n    max_new_tokens=32768\n)\n```\n\n### 2. Keywords Suppressed\n\nSee `references\u002Fkeywords.md` for the complete list. Core keywords:\n\n```\nwait, alternatively, hmm, but, however, check, \ndouble-check, maybe, verify, again, oh, ah\n```\n\n## How It Works\n\n1. **Initialize Keywords**: Identify reflection keywords from empirical analysis\n2. **Expand to Token Variants**: Map keywords to all token variants in vocabulary (e.g., \"wait\" → \" wait\", \"Wait\", \" Wait\", \".wait\", \"WAIT\")\n3. **Suppress During Inference**: Set logits of reflection tokens to large negative values during decoding\n\n```\nLogits (Before)         Logits (After)\nWait     0.8     →     Wait     -inf\nFirst    0.6     →     First    0.6\nHmm      0.5     →     Hmm      -inf\nLet      0.4     →     Let      0.4\n```\n\n## Key Findings\n\n### Why It Works\n\n- NOWAIT doesn't eliminate self-reflection entirely—it guides models to skip **unnecessary** \"waiting\" reasoning\n- Models still perform essential verification at key decision points\n- Results in more linear, straightforward reasoning paths\n\n### RL vs Distilled Models\n\n| Model Type | NOWAIT Effect | Recommendation |\n|------------|---------------|----------------|\n| RL-based (QwQ, Phi4, Qwen3-32B) | Stable accuracy, significant token reduction | ✅ Recommended |\n| Distilled (Qwen3-4B\u002F8B\u002F14B) | Accuracy degradation on hard tasks | ⚠️ Use with caution |\n\nDistilled models rely heavily on CoT structure from training data—removing reflection tokens disrupts their reasoning patterns.\n\n## Integration Examples\n\n### HuggingFace Transformers\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\nfrom scripts.nowait_processor import NOWAITLogitProcessor\n\nmodel = AutoModelForCausalLM.from_pretrained(\"Qwen\u002FQwQ-32B\")\ntokenizer = AutoTokenizer.from_pretrained(\"Qwen\u002FQwQ-32B\")\n\nprocessor = NOWAITLogitProcessor(tokenizer)\n\nresponse = model.generate(\n    tokenizer(prompt, return_tensors=\"pt\").input_ids,\n    logits_processor=[processor],\n    max_new_tokens=32768,\n    do_sample=True,\n    temperature=0.7\n)\n```\n\n### vLLM\n\n```python\nfrom vllm import LLM, SamplingParams\nfrom scripts.nowait_processor import get_nowait_bad_words_ids\n\nllm = LLM(model=\"Qwen\u002FQwQ-32B\")\nbad_words_ids = get_nowait_bad_words_ids(llm.get_tokenizer())\n\nsampling_params = SamplingParams(\n    max_tokens=32768,\n    bad_words_ids=bad_words_ids\n)\n```\n\n## Expected Results\n\n| Task Type | Original Tokens | NOWAIT Tokens | Reduction |\n|-----------|-----------------|---------------|-----------|\n| Math (AIME) | 15,000 | 10,500 | 30% |\n| Visual QA (MMMU) | 2,900 | 1,450 | 50% |\n| Video QA (MMVU) | 1,700 | 1,250 | 27% |\n\n## Limitations\n\n- Less effective on very simple problems where CoT overhead is already minimal\n- Distilled models may suffer accuracy loss on challenging tasks\n- Some domains may require model-specific keyword tuning\n\n## References\n\n- Paper: arXiv:2506.08343v2\n- Complete keyword list: `references\u002Fkeywords.md`\n- Implementation: `scripts\u002Fnowait_processor.py`",{"name":5,"description":7},"main","51493f354fd03e3f941d4df7fd64c0b8c7a2632d","skills\u002Fproductivity\u002Fnowait","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi","漏洞研究、根因分析、黑箱測試｜做 AI agent 工具｜Vulnerability research, root-cause analysis, AI agent tooling","2026-08-16 02:24:07",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add GongYuanCaiJi\u002Fdsh-claude-code-templates --skill nowait-reasoning-optimizer",{"tool":37,"command":38},"bunx","bunx skills add GongYuanCaiJi\u002Fdsh-claude-code-templates --skill nowait-reasoning-optimizer",{"tool":40,"command":41},"pnpm","pnpm dlx skills add GongYuanCaiJi\u002Fdsh-claude-code-templates --skill nowait-reasoning-optimizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fnowait\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"refrences\u002Fkeywords.md","REFERENCE","参考文档",4115,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fnowait\u002Frefrences\u002Fkeywords.md",{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"scripts\u002Fnowait_processor.py","SCRIPT","脚本",10186,"https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fnowait\u002Fscripts\u002Fnowait_processor.py",[58,65,74,81,88,95],{"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},"01M7ARMYTZ5D4B7N5SKFXV345V","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fzapier-make-patterns\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":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7ARMX1BVNEAR98SBANMDF2V","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fyeet\u002FSKILL.md",[],[],{"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":80,"publishedAt":19},"01M7ARMPR4RQ417MG1HMPGNQHH","workflow-automation","Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off.  This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation.  Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fworkflow-automation\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7ARMHBERDMKGDMV7K6MQ6YP","trigger-dev","Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Ftrigger-dev\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7ARME0A7KFT330Q2H25HE2B","slack-automation","Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fslack-automation\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7ARM8D87V18WDG0GEZS11ZT","planning-with-files","Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.","https:\u002F\u002Fgithub.com\u002FGongYuanCaiJi\u002Fdsh-claude-code-templates\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-automation\u002Fplanning-with-files\u002FSKILL.md",[],[]]