[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSCVZ0V2GAT2ZVS7VEK852":3,"skill-same:01M7CSCVZ0V2GAT2ZVS7VEK852":48},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7CSCVZ0V2GAT2ZVS7VEK852","token-budget-advisor",null,"Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: \"token budget\", \"token count\", \"token usage\", \"token limit\", \"response length\", \"answer depth\", \"short version\", \"brief answer\", \"detailed answer\", \"exhaustive answer\", \"respuesta corta vs larga\", \"cuántos tokens\", \"ahorrar tokens\", \"responde al 50%\", \"dame la versión corta\", \"quiero controlar cuánto usas\", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or \"token\" refers to auth\u002Fsession\u002Fpayment tokens rather than response size.","Henrique1601\u002FSkiilsToIAs","Henrique1601","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92006691?v=4","01M7CRXVT0GVXVK80JT1GR687S","Henrique Bezerra Dos Santos","01M7CRXVTN5Y8TMWJ1MDSKCQ1T",0,"MIT","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Ftoken-budget-advisor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: token-budget-advisor\ndescription: >-\n  Offers the user an informed choice about how much response depth to\n  consume before answering. Use this skill when the user explicitly\n  wants to control response length, depth, or token budget.\n  TRIGGER when: \"token budget\", \"token count\", \"token usage\", \"token limit\",\n  \"response length\", \"answer depth\", \"short version\", \"brief answer\",\n  \"detailed answer\", \"exhaustive answer\", \"respuesta corta vs larga\",\n  \"cuántos tokens\", \"ahorrar tokens\", \"responde al 50%\", \"dame la versión\n  corta\", \"quiero controlar cuánto usas\", or clear variants where the\n  user is explicitly asking to control answer size or depth.\n  DO NOT TRIGGER when: user has already specified a level in the current\n  session (maintain it), the request is clearly a one-word answer, or\n  \"token\" refers to auth\u002Fsession\u002Fpayment tokens rather than response size.\nmetadata:\n  origin: community\n---\n\n# Token Budget Advisor (TBA)\n\nIntercept the response flow to offer the user a choice about response depth **before** Claude answers.\n\n## When to Use\n\n- User wants to control how long or detailed a response is\n- User mentions tokens, budget, depth, or response length\n- User says \"short version\", \"tldr\", \"brief\", \"al 25%\", \"exhaustive\", etc.\n- Any time the user wants to choose depth\u002Fdetail level upfront\n\n**Do not trigger** when: user already set a level this session (maintain it silently), or the answer is trivially one line.\n\n## How It Works\n\n### Step 1 — Estimate input tokens\n\nUse the repository's canonical context-budget heuristics to estimate the prompt's token count mentally.\n\nUse the same calibration guidance as [context-budget](..\u002Fcontext-budget\u002FSKILL.md):\n\n- prose: `words × 1.3`\n- code-heavy or mixed\u002Fcode blocks: `chars \u002F 4`\n\nFor mixed content, use the dominant content type and keep the estimate heuristic.\n\n### Step 2 — Estimate response size by complexity\n\nClassify the prompt, then apply the multiplier range to get the full response window:\n\n| Complexity   | Multiplier range | Example prompts                                      |\n|--------------|------------------|------------------------------------------------------|\n| Simple       | 3× – 8×          | \"What is X?\", yes\u002Fno, single fact                   |\n| Medium       | 8× – 20×         | \"How does X work?\"                                  |\n| Medium-High  | 10× – 25×        | Code request with context                           |\n| Complex      | 15× – 40×        | Multi-part analysis, comparisons, architecture      |\n| Creative     | 10× – 30×        | Stories, essays, narrative writing                  |\n\nResponse window = `input_tokens × mult_min` to `input_tokens × mult_max` (but don’t exceed your model’s configured output-token limit).\n\n### Step 3 — Present depth options\n\nPresent this block **before** answering, using the actual estimated numbers:\n\n```\nAnalyzing your prompt...\n\nInput: ~[N] tokens  |  Type: [type]  |  Complexity: [level]  |  Language: [lang]\n\nChoose your depth level:\n\n[1] Essential   (25%)  ->  ~[tokens]   Direct answer only, no preamble\n[2] Moderate    (50%)  ->  ~[tokens]   Answer + context + 1 example\n[3] Detailed    (75%)  ->  ~[tokens]   Full answer with alternatives\n[4] Exhaustive (100%)  ->  ~[tokens]   Everything, no limits\n\nWhich level? (1-4 or say \"25% depth\", \"50% depth\", \"75% depth\", \"100% depth\")\n\nPrecision: heuristic estimate ~85-90% accuracy (±15%).\n```\n\nLevel token estimates (within the response window):\n- 25%  → `min + (max - min) × 0.25`\n- 50%  → `min + (max - min) × 0.50`\n- 75%  → `min + (max - min) × 0.75`\n- 100% → `max`\n\n### Step 4 — Respond at the chosen level\n\n| Level            | Target length       | Include                                             | Omit                                              |\n|------------------|---------------------|-----------------------------------------------------|---------------------------------------------------|\n| 25% Essential    | 2-4 sentences max   | Direct answer, key conclusion                       | Context, examples, nuance, alternatives           |\n| 50% Moderate     | 1-3 paragraphs      | Answer + necessary context + 1 example              | Deep analysis, edge cases, references             |\n| 75% Detailed     | Structured response | Multiple examples, pros\u002Fcons, alternatives          | Extreme edge cases, exhaustive references         |\n| 100% Exhaustive  | No restriction      | Everything — full analysis, all code, all perspectives | Nothing                                        |\n\n## Shortcuts — skip the question\n\nIf the user already signals a level, respond at that level immediately without asking:\n\n| What they say                                      | Level |\n|----------------------------------------------------|-------|\n| \"1\" \u002F \"25% depth\" \u002F \"short version\" \u002F \"brief answer\" \u002F \"tldr\"  | 25%   |\n| \"2\" \u002F \"50% depth\" \u002F \"moderate depth\" \u002F \"balanced answer\"        | 50%   |\n| \"3\" \u002F \"75% depth\" \u002F \"detailed answer\" \u002F \"thorough answer\"       | 75%   |\n| \"4\" \u002F \"100% depth\" \u002F \"exhaustive answer\" \u002F \"full deep dive\"     | 100%  |\n\nIf the user set a level earlier in the session, **maintain it silently** for subsequent responses unless they change it.\n\n## Precision note\n\nThis skill uses heuristic estimation — no real tokenizer. Accuracy ~85-90%, variance ±15%. Always show the disclaimer.\n\n## Examples\n\n### Triggers\n\n- \"Give me the short version first.\"\n- \"How many tokens will your answer use?\"\n- \"Respond at 50% depth.\"\n- \"I want the exhaustive answer, not the summary.\"\n- \"Dame la version corta y luego la detallada.\"\n\n### Does Not Trigger\n\n- \"What is a JWT token?\"\n- \"The checkout flow uses a payment token.\"\n- \"Is this normal?\"\n- \"Complete the refactor.\"\n- Follow-up questions after the user already chose a depth for the session\n\n## Source\n\nStandalone skill from [TBA — Token Budget Advisor for Claude Code](https:\u002F\u002Fgithub.com\u002FXabilimon1\u002FToken-Budget-Advisor-Claude-Code-).\nOriginal project also ships a Python estimator script, but this repository keeps the skill self-contained and heuristic-only.\n","# Token Budget Advisor (TBA)\n\nIntercept the response flow to offer the user a choice about response depth **before** Claude answers.\n\n## When to Use\n\n- User wants to control how long or detailed a response is\n- User mentions tokens, budget, depth, or response length\n- User says \"short version\", \"tldr\", \"brief\", \"al 25%\", \"exhaustive\", etc.\n- Any time the user wants to choose depth\u002Fdetail level upfront\n\n**Do not trigger** when: user already set a level this session (maintain it silently), or the answer is trivially one line.\n\n## How It Works\n\n### Step 1 — Estimate input tokens\n\nUse the repository's canonical context-budget heuristics to estimate the prompt's token count mentally.\n\nUse the same calibration guidance as [context-budget](..\u002Fcontext-budget\u002FSKILL.md):\n\n- prose: `words × 1.3`\n- code-heavy or mixed\u002Fcode blocks: `chars \u002F 4`\n\nFor mixed content, use the dominant content type and keep the estimate heuristic.\n\n### Step 2 — Estimate response size by complexity\n\nClassify the prompt, then apply the multiplier range to get the full response window:\n\n| Complexity   | Multiplier range | Example prompts                                      |\n|--------------|------------------|------------------------------------------------------|\n| Simple       | 3× – 8×          | \"What is X?\", yes\u002Fno, single fact                   |\n| Medium       | 8× – 20×         | \"How does X work?\"                                  |\n| Medium-High  | 10× – 25×        | Code request with context                           |\n| Complex      | 15× – 40×        | Multi-part analysis, comparisons, architecture      |\n| Creative     | 10× – 30×        | Stories, essays, narrative writing                  |\n\nResponse window = `input_tokens × mult_min` to `input_tokens × mult_max` (but don’t exceed your model’s configured output-token limit).\n\n### Step 3 — Present depth options\n\nPresent this block **before** answering, using the actual estimated numbers:\n\n```\nAnalyzing your prompt...\n\nInput: ~[N] tokens  |  Type: [type]  |  Complexity: [level]  |  Language: [lang]\n\nChoose your depth level:\n\n[1] Essential   (25%)  ->  ~[tokens]   Direct answer only, no preamble\n[2] Moderate    (50%)  ->  ~[tokens]   Answer + context + 1 example\n[3] Detailed    (75%)  ->  ~[tokens]   Full answer with alternatives\n[4] Exhaustive (100%)  ->  ~[tokens]   Everything, no limits\n\nWhich level? (1-4 or say \"25% depth\", \"50% depth\", \"75% depth\", \"100% depth\")\n\nPrecision: heuristic estimate ~85-90% accuracy (±15%).\n```\n\nLevel token estimates (within the response window):\n- 25%  → `min + (max - min) × 0.25`\n- 50%  → `min + (max - min) × 0.50`\n- 75%  → `min + (max - min) × 0.75`\n- 100% → `max`\n\n### Step 4 — Respond at the chosen level\n\n| Level            | Target length       | Include                                             | Omit                                              |\n|------------------|---------------------|-----------------------------------------------------|---------------------------------------------------|\n| 25% Essential    | 2-4 sentences max   | Direct answer, key conclusion                       | Context, examples, nuance, alternatives           |\n| 50% Moderate     | 1-3 paragraphs      | Answer + necessary context + 1 example              | Deep analysis, edge cases, references             |\n| 75% Detailed     | Structured response | Multiple examples, pros\u002Fcons, alternatives          | Extreme edge cases, exhaustive references         |\n| 100% Exhaustive  | No restriction      | Everything — full analysis, all code, all perspectives | Nothing                                        |\n\n## Shortcuts — skip the question\n\nIf the user already signals a level, respond at that level immediately without asking:\n\n| What they say                                      | Level |\n|----------------------------------------------------|-------|\n| \"1\" \u002F \"25% depth\" \u002F \"short version\" \u002F \"brief answer\" \u002F \"tldr\"  | 25%   |\n| \"2\" \u002F \"50% depth\" \u002F \"moderate depth\" \u002F \"balanced answer\"        | 50%   |\n| \"3\" \u002F \"75% depth\" \u002F \"detailed answer\" \u002F \"thorough answer\"       | 75%   |\n| \"4\" \u002F \"100% depth\" \u002F \"exhaustive answer\" \u002F \"full deep dive\"     | 100%  |\n\nIf the user set a level earlier in the session, **maintain it silently** for subsequent responses unless they change it.\n\n## Precision note\n\nThis skill uses heuristic estimation — no real tokenizer. Accuracy ~85-90%, variance ±15%. Always show the disclaimer.\n\n## Examples\n\n### Triggers\n\n- \"Give me the short version first.\"\n- \"How many tokens will your answer use?\"\n- \"Respond at 50% depth.\"\n- \"I want the exhaustive answer, not the summary.\"\n- \"Dame la version corta y luego la detallada.\"\n\n### Does Not Trigger\n\n- \"What is a JWT token?\"\n- \"The checkout flow uses a payment token.\"\n- \"Is this normal?\"\n- \"Complete the refactor.\"\n- Follow-up questions after the user already chose a depth for the session\n\n## Source\n\nStandalone skill from [TBA — Token Budget Advisor for Claude Code](https:\u002F\u002Fgithub.com\u002FXabilimon1\u002FToken-Budget-Advisor-Claude-Code-).\nOriginal project also ships a Python estimator script, but this repository keeps the skill self-contained and heuristic-only.\n",{"name":5,"metadata":24,"description":7},{"origin":25},"community","main","a73152352c0612252131e5cf84e91312a6cf17dc","ai-agents\u002Ftoken-budget-advisor","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs","https:\u002F\u002Fgithub.com\u002FHenrique1601","https:\u002F\u002Fbezerraportifolio.netlify.app\u002F","Full Stack Developer | React, Next.js, TypeScript, Node.js & IA | Construindo produtos digitais e soluções SaaS","2026-11-15 02:56:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Henrique1601\u002FSkiilsToIAs --skill token-budget-advisor",{"tool":40,"command":41},"bunx","bunx skills add Henrique1601\u002FSkiilsToIAs --skill token-budget-advisor",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Henrique1601\u002FSkiilsToIAs --skill token-budget-advisor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Ftoken-budget-advisor\u002FSKILL.md",true,[],[49,56,63,71,78,85],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7E2ANBW9V6AVX5JXNCEAWF8","rag-architect-agent","Agente Arquiteto de RAG, Embeddings & Busca Vetorial. Especialista em design e implementação de pipelines de Retrieval-Augmented Generation de alta fidelidade: chunking semântico, modelagem pgvector no PostgreSQL (Neon\u002FSupabase), busca híbrida (cosseno + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fcustom-agents\u002Frag-architect-agent\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7E29KKF8R02ZRGYE2MJM67G","rag-architecture-patterns","Padrões arquiteturais e implementação de pipelines RAG (Retrieval-Augmented Generation) de alta fidelidade para qualquer projeto ou sistema. Cobre chunking semântico, embeddings, busca híbrida (pgvector + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Frag-architecture-patterns\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CWRA8E3BJ7CPY8N8EG28J1","skill-repair","Use this to fix and re-install agent skills that have failed installation.\nThis skill provides the necessary context and permissions to surgically update\nthe `manifest.json` after a fix has been applied.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fskill-repair\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CWR66FZP8FA47WVZ4Z2EXC","security-scan","Scan your Claude Code configuration (.claude\u002F directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-scan\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CWR0QPY58QPTR1P759TFNG","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-review\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CWQXCE40XWT4FZ3VWZFGDP","security-bounty-hunter","Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-bounty-hunter\u002FSKILL.md",[],[]]